--- schema_version: 1 rubric_version: "1.1" kind: pair canonical_url: "https://onaihq.com/compare/agents/chatgpt-vs-claude/" data_url: "https://onaihq.com/compare/agents/chatgpt-vs-claude/data.json" generated_at: 2026-10-27 last_checked_at: 2026-10-26 last_cross_checked_at: 2026-10-26 next_check_at: 2026-12-20 publisher: "onAI" --- # ChatGPT Business / Enterprise vs Claude Team / Enterprise > Published by onAI. onAI also sells one of the products compared here. Findings about other products link to public sources so you can check them; statements about onAI are marked as stated by onAI. > ChatGPT Business / Enterprise lifecycle: sunset. The current custom-GPT FAQ says the transition affects all ChatGPT plans and schedules retirement for December 11, 2026, subject to account/workspace-specific notices. Qualified Enterprise deferrals may extend to February 11, 2027. Enterprise creation/publishing restrictions are separate from retirement. Scope: Custom GPTs on Business and Enterprise within this profile, according to each workspace notice. The FAQ also covers other plans. This is not a shutdown of ChatGPT, Work, plugins or the workspace service. Continuation: Migration to plugins. Under the planned workflow, GPT instructions become a skill, knowledge files become reference files, and connected apps are added; model choice, custom actions and sharing settings do not automatically transfer. Follow the affected workspace notice and test the replacement. Checked 2026-10-26; agent cross-checked 2026-10-26; check again by 2026-12-20. Sources: chatgpt:oa-gpt-migration-r2-20261026, chatgpt:oa-enterprise-notes-20261026. > Claude Team / Enterprise lifecycle: sunset. Standalone Claude Design at claude.ai/design is scheduled to close on December 14, 2026; design creation continues inside Claude Artifacts. Scope: Only standalone Claude Design at claude.ai/design. This is not a sunset of Claude Team or Enterprise chat, Cowork or in-Claude Design. Continuation: Claude Artifacts Design inside Claude; the admin guide describes existing Design projects appearing there. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: claude:cl-artifacts-admin. This comparison has 49 criteria with sourced findings for both products, including 49 that a second agent cross-checked for both. 50 criteria have a sourced finding for at least one product. "Sourced" findings passed publication validation: they are scoped, fresh and cite public resolved sources. "Agent cross-checked" findings also received a separate agent source pass, not necessarily a hands-on test. "Stated by onAI" marks the publisher's own statements about its product (evidence type vendor-statement), which cite no third-party source. Humans approve the rubric, templates and generator; they do not review every finding. It does not declare a winner. A missing sourced finding is not evidence that a capability is absent. - ChatGPT Business / Enterprise source checks: 2026-10-21 to 2026-10-26. - Claude Team / Enterprise source checks: 2026-10-21 to 2026-10-26. - Canonical HTML: https://onaihq.com/compare/agents/chatgpt-vs-claude/ - Machine-readable JSON: https://onaihq.com/compare/agents/chatgpt-vs-claude/data.json - Methodology: https://onaihq.com/compare/agents/methodology/ ## Models ### MOD-01: Model catalogue and providers Judgment rule: List each available model by provider and plan, including reasoning, fast and multimodal variants. Record whether the user picks the model, the product routes automatically, or both. A provider counts only if at least one of its current models is selectable on the scoped plan. #### ChatGPT Business / Enterprise Verification status: Agent cross-checked (agent-cross-checked) Support: partial Business and Enterprise Chat use GPT6/Sol and Pro/Astra names; Work exposes a separate picker and model set. Availability: generally-available Delivery: native Scope: surfaces=ChatGPT Business and Enterprise web workspaces, ChatGPT desktop and mobile clients, ChatGPT Work and team tasks, distinct from regular Chat and coding-only Codex; version=Continuously updated hosted service, retrieved 2026-10-21; plan=Business Standard/Premium Chat and Work; Enterprise/Edu model access only as specified in their dedicated model guide; add_ons=Purchased workspace credits or contracted token billing where stated, External app/provider subscriptions and Microsoft add-in approval where required, Enterprise residency, EKM and compliance entitlements only where stated; deployment_mode=multi-tenant-saas; region=Supported commercial regions; Europe means EEA + Switzerland when explicitly configured; app/client availability varies; os=not specified. Limitations: - Reconciliation: Work overview uses a broad not-in-regular-Chat sentence for its picker labels; dedicated Business/Enterprise Chat guides explicitly explain Sol powering the GPT6 Chat alias. GPT6.1Sol and Luna are not selectable in regular Chat. - No tenant picker, per-model modality matrix or routing trace was observed. - providers — Which model providers are available? [supported]: These plan-specific Chat and Work catalogues use OpenAI models; connected apps are not additional chat-model providers. Sources: chatgpt:oa-business-models-r2, chatgpt:oa-enterprise-models-r2. - current_models — Which current models are selectable on this plan? [partial]: Business and eligible Enterprise Chat: GPT6 at Instant–ExtraHigh is powered by GPT6 Sol; GPT6 Pro uses Astra. Business Work lists GPT6 Sol/6.1Sol/Luna, with other options only when enabled. Enterprise/Edu Work access also depends on rollout and roles. These are experience-specific names, not one universal picker. Sources: chatgpt:oa-business-models-r2, chatgpt:oa-enterprise-models-r2. - user_choice — Can users pick the model per chat? [supported]: Business and Enterprise dedicated guides describe their Chat picker/effort choices; Work has a separate model/effort selector. Available options depend on seat/workspace/rollout. Sources: chatgpt:oa-business-models-r2, chatgpt:oa-enterprise-models-r2, chatgpt:oa-work-r2. - auto_routing — Does the product route between models automatically, and is the chosen model shown? [partial]: Business can add reasoning while Instant is selected and exposes Higher intelligence in Settings>General. Enterprise/Edu document workspace automatic-routing controls. Exact per-request routed identity was not observed. Sources: chatgpt:oa-business-models-r2, chatgpt:oa-enterprise-models-r2. - multimodal_input — Which models accept images, audio or files? [partial]: Paid workspaces accept supported image/file/audio inputs; per-model modality mapping was not completely verified. Sources: chatgpt:oa-files. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: chatgpt:oa-business-models-r2, chatgpt:oa-enterprise-models-r2, chatgpt:oa-work-r2, chatgpt:oa-files #### Claude Team / Enterprise Verification status: Agent cross-checked (agent-cross-checked) Support: partial Team and Enterprise offer Anthropic model families with seat-specific Fable billing and visible safety fallback; organization controls can restrict the picker. Availability: unknown Delivery: native Scope: surfaces=Claude Team and Enterprise web workspaces, Claude desktop and mobile clients; version=Hosted commercial Chat documentation checked 2026-10-26; plan=Team Standard/Premium; current usage-based Enterprise; legacy seat-based Enterprise only where explicitly identified; add_ons=Usage credits for Fable on Team Standard and legacy Enterprise Standard; consumption billed separately on current Enterprise; deployment_mode=multi-tenant-saas; region=Commercial supported regions; default global inference and US storage where documented; no EU/Swiss-only residency assumption; os=not specified. Limitations: - current_models: The current selector/context guides list Haiku 5.5, Sonnet 5.5, Opus 5.5 and Fable 5.1, plus older choices. Pricing includes the Opus/Sonnet/Haiku families on Team and Enterprise. Fable 5/5.1 use paid credits on Team Standard and legacy Enterprise Standard, a capped included share on Premium, and API-rate consumption on current Enterprise. Admin restrictions can remove access; no authenticated tenant picker was observed. - user_choice: Users select a chat model and effort from the menu; changes apply to the next response. Enterprise model controls may restrict choices. Office and Cowork defaults are scoped separately. - auto_routing: Fable 5/5.1 safety fallback is enabled by default and may rerun a flagged request on an Opus model in the same chat. A visible notice and responding-model label disclose the switch, and users can disable it. General task-complexity routing is not established. - multimodal_input: The chat attachment guide documents images/PDF/documents; exact per-model modality and paid-seat compatibility remains unverified. - providers — Which model providers are available? [supported]: The commercial plan table includes Anthropic Fable, Opus, Sonnet and Haiku families; this is a single-provider hosted chat catalogue. Sources: claude:cl-pricing-20261026. - current_models — Which current models are selectable on this plan? [partial]: The current selector/context guides list Haiku 5.5, Sonnet 5.5, Opus 5.5 and Fable 5.1, plus older choices. Pricing includes the Opus/Sonnet/Haiku families on Team and Enterprise. Fable 5/5.1 use paid credits on Team Standard and legacy Enterprise Standard, a capped included share on Premium, and API-rate consumption on current Enterprise. Admin restrictions can remove access; no authenticated tenant picker was observed. Sources: claude:cl-model-menu-r2-20261026, claude:cl-context-plans-r2-20261026, claude:cl-pricing-20261026, claude:claude:fable-plan-20261026. - user_choice — Can users pick the model per chat? [partial]: Users select a chat model and effort from the menu; changes apply to the next response. Enterprise model controls may restrict choices. Office and Cowork defaults are scoped separately. Sources: claude:cl-model-menu-r2-20261026, claude:cl-model-control-20261026. - auto_routing — Does the product route between models automatically, and is the chosen model shown? [partial]: Fable 5/5.1 safety fallback is enabled by default and may rerun a flagged request on an Opus model in the same chat. A visible notice and responding-model label disclose the switch, and users can disable it. General task-complexity routing is not established. Sources: claude:claude:transparent-fallback-20261026, claude:claude:fable-plan-20261026. - multimodal_input — Which models accept images, audio or files? [partial]: The chat attachment guide documents images/PDF/documents; exact per-model modality and paid-seat compatibility remains unverified. Sources: claude:cl-upload-r2-20261026. Checked 2026-10-26; agent cross-checked 2026-10-26; check again by 2026-12-20. Sources: claude:cl-model-menu-r2-20261026, claude:cl-context-plans-r2-20261026, claude:cl-upload-r2-20261026, claude:cl-pricing-20261026, claude:claude:fable-plan-20261026, claude:cl-model-control-20261026, claude:claude:transparent-fallback-20261026 ### MOD-02: Model freshness Judgment rule: Measure the days from a provider's general release to availability in the product for the last three major releases from OpenAI, Anthropic and Google (and Mistral where offered). Use dated changelogs or observation. Record deprecation notice for retired models. #### ChatGPT Business / Enterprise Verification status: Agent cross-checked (agent-cross-checked) Support: partial Dated release notes exist; a three-release provider/product lag series remains unverified. Availability: generally-available Delivery: native Scope: surfaces=ChatGPT Business and Enterprise web workspaces, ChatGPT desktop and mobile clients, ChatGPT connected apps and custom MCP apps; version=Continuously updated hosted service, retrieved 2026-10-21; plan=ChatGPT Business Standard/Premium versus Enterprise; Edu only where explicitly named for eligibility differences; add_ons=Purchased workspace credits or contracted token billing where stated, External app/provider subscriptions and Microsoft add-in approval where required, Enterprise residency, EKM and compliance entitlements only where stated; deployment_mode=multi-tenant-saas; region=Supported commercial regions; Europe means EEA + Switzerland when explicitly configured; app/client availability varies; os=not specified. Limitations: - No three-release provider/product lag series or general guaranteed model-removal notice period was established. - Retained explicit model selection is documented separately for Business and Enterprise; no permanent pinned-service promise. - release_lag_days — What was the lag for each of the last three major releases, per provider? [unknown]: What was the lag for each of the last three major releases, per provider? Unverified after checking OpenAI Business/Enterprise documentation, current model and app pages, service agreement and release notes retrieved 2026-10-21; no paid workspace or shared fixture. - changelog — Is there a dated public model changelog? [supported]: Business and Enterprise/Edu have dated release notes. Sources: chatgpt:oa-business-notes, chatgpt:oa-enterprise-notes. - deprecation_notice — How much notice is given before a model is removed? [unknown]: No universal model-removal notice or three current model retirement examples were established from the checked release notes. Planned custom-GPT retirement is recorded separately in roadmapReview. - version_pinning — Can an admin keep an older model version? [partial]: Both current Business and Enterprise model guides say an explicit GPT5.6Sol selection remains during the GPT6 rollout. This is preserved selection, not indefinite administrator version pinning. Sources: chatgpt:oa-business-models-r2, chatgpt:oa-enterprise-models-r2. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: chatgpt:oa-business-notes, chatgpt:oa-enterprise-notes, chatgpt:oa-business-models-r2, chatgpt:oa-enterprise-models-r2 #### Claude Team / Enterprise Verification status: Agent cross-checked (agent-cross-checked) Support: partial Release notes and scoped retirement notices exist; comparative lag and pinning remain open. Availability: generally-available Delivery: native Scope: surfaces=Claude Team and Enterprise web workspaces, Claude desktop and mobile clients, Claude connectors and remote MCP integrations, Claude for Microsoft 365 official add-ins, Claude Cowork cloud and desktop task execution; version=Continuously updated commercial service, retrieved 2026-10-21; plan=Claude Team Standard/Premium versus current usage-based Enterprise; legacy Enterprise only when explicitly named; add_ons=Enterprise token usage at API rates, Optional US-only inference surcharge, External provider/app subscriptions and Office deployment approval where applicable, CMEK and compliance only on eligible Enterprise configurations; deployment_mode=multi-tenant-saas; region=Commercial supported regions; default global inference and US storage where documented; no EU/Swiss-only residency assumption; os=not specified. Limitations: - Unverified parts: release_lag_days, version_pinning. - Read each atomic answer for its plan, access and feature limits. - release_lag_days — What was the lag for each of the last three major releases, per provider? [unknown]: What was the lag for each of the last three major releases, per provider? Unverified after checking release notes and Haiku notice; three provider/product release-date pairs and persistent enterprise model pinning not verified. - changelog — Is there a dated public model changelog? [supported]: Claude publishes dated model and product release notes. Sources: claude:cl-release. - deprecation_notice — How much notice is given before a model is removed? [partial]: Haiku 4.5 consumer removal has October 15-to-29 notice, explicitly excluding Team/Enterprise. A general commercial-model notice period was not established. Sources: claude:cl-haiku-notice. - version_pinning — Can an admin keep an older model version? [unknown]: Can an admin keep an older model version? Unverified after checking release notes and Haiku notice; three provider/product release-date pairs and persistent enterprise model pinning not verified. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: claude:cl-release, claude:cl-haiku-notice ### MOD-03: Bring-your-own keys and provider contracts Judgment rule: Record customer-held API keys, customer cloud accounts (Azure OpenAI, Bedrock, Vertex), and aggregator routes (OpenRouter, LiteLLM) as separate routes. Record what still works without a vendor-provided model, whether prices change with BYO, and documented restrictions. API-key support does not imply support for the customer's own Azure contract. #### ChatGPT Business / Enterprise Verification status: No public information found (not-published) Support: not-published We found no public information on this. A missing finding is not evidence that the product lacks the capability. #### Claude Team / Enterprise Verification status: Agent cross-checked (agent-cross-checked) Support: partial Office add-ins advertise customer cloud credentials; that does not establish BYO inference in regular Claude chat. Availability: generally-available Delivery: native Scope: surfaces=Claude for Microsoft 365 official add-ins, Claude Team and Enterprise web workspaces; version=Continuously updated commercial service, retrieved 2026-10-21; plan=Paid Office add-ins; regular Team/Enterprise chat only as an explicit gap; add_ons=Enterprise token usage at API rates, Optional US-only inference surcharge, External provider/app subscriptions and Office deployment approval where applicable, CMEK and compliance only on eligible Enterprise configurations; deployment_mode=multi-tenant-saas; region=Commercial supported regions; default global inference and US storage where documented; no EU/Swiss-only residency assumption; os=not specified. Limitations: - Unverified parts: own_api_keys, custom_endpoint, byo_pricing, byo_restrictions. - Read each atomic answer for its plan, access and feature limits. - own_api_keys — Can the customer use its own provider API keys? [unknown]: Can the customer use its own provider API keys? Unverified after checking Office cloud-credential FAQ, regular chat model settings and commercial pricing; arbitrary API keys/endpoints, BYO price changes and feature parity not verified. - own_cloud_contract — Can it use its own Azure OpenAI, Bedrock or Vertex deployment? [partial]: Claude for Microsoft 365 advertises Foundry, Bedrock and Gemini Enterprise Agent Platform credentials. Regular Claude chat BYO cloud-account support remains unverified. Sources: claude:cl-office. - custom_endpoint — Can an admin add any OpenAI-compatible endpoint? [unknown]: Can an admin add any OpenAI-compatible endpoint? Unverified after checking Office cloud-credential FAQ, regular chat model settings and commercial pricing; arbitrary API keys/endpoints, BYO price changes and feature parity not verified. - byo_pricing — Does BYO change the licence price? [unknown]: Does BYO change the licence price? Unverified after checking Office cloud-credential FAQ, regular chat model settings and commercial pricing; arbitrary API keys/endpoints, BYO price changes and feature parity not verified. - byo_restrictions — Which features stop working with BYO? [unknown]: Which features stop working with BYO? Unverified after checking Office cloud-credential FAQ, regular chat model settings and commercial pricing; arbitrary API keys/endpoints, BYO price changes and feature parity not verified. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: claude:cl-office ### MOD-04: Local and self-hosted models Judgment rule: Record support for models running in the customer's environment (vLLM, Ollama, TGI or similar) and which features work with them: chat, RAG, tools, embeddings. Distinguish a documented, supported route from a generic endpoint that happens to work. #### ChatGPT Business / Enterprise Verification status: No public information found (not-published) Support: not-published We found no public information on this. A missing finding is not evidence that the product lacks the capability. #### Claude Team / Enterprise Verification status: No public information found (not-published) Support: not-published We found no public information on this. A missing finding is not evidence that the product lacks the capability. ### MOD-05: Model control and usage limits Judgment rule: Record admin allow-lists per group, default models, restrictions on which models may see which data, and per-user rate or fair-use limits. Test one restriction with two users in different groups. Record limits as enforced stops, warnings or undocumented fair use. #### ChatGPT Business / Enterprise Verification status: Agent cross-checked (agent-cross-checked) Support: partial Enterprise model and default controls are documented; Business allowances depend on seat type. Availability: generally-available Delivery: native Scope: surfaces=ChatGPT Business and Enterprise web workspaces, ChatGPT desktop and mobile clients, ChatGPT connected apps and custom MCP apps; version=Continuously updated hosted service, retrieved 2026-10-21; plan=ChatGPT Business Standard/Premium versus Enterprise; Edu only where explicitly named for eligibility differences; add_ons=Purchased workspace credits or contracted token billing where stated, External app/provider subscriptions and Microsoft add-in approval where required, Enterprise residency, EKM and compliance entitlements only where stated; deployment_mode=multi-tenant-saas; region=Supported commercial regions; Europe means EEA + Switzerland when explicitly configured; app/client availability varies; os=not specified. Limitations: - No two-group model or data-bound-model test was run. Virtually unlimited Enterprise messages do not imply zero-dollar usage under token-billed contracts. - model_allowlist_by_group — Can admins limit models per group? [supported]: Enterprise/Edu model access uses workspace settings and RBAC; groups can receive roles. Sources: chatgpt:oa-models, chatgpt:oa-admin-quickstart. - data_bound_models — Can admins restrict which models receive connector or knowledge content? [unknown]: Can admins restrict which models receive connector or knowledge content? Unverified after checking OpenAI Business/Enterprise documentation, current model and app pages, service agreement and release notes retrieved 2026-10-21; no paid workspace or shared fixture. - default_model — Can admins set the default model? [supported]: Enterprise admins choose separate Chat and Work starting models/effort; defaults do not grant access. Sources: chatgpt:oa-admin-settings. - user_limits — What per-user message or token limits apply, and are they published? [partial]: Business Premium includes five times Standard usage and no five-hour cap; exact prompt count depends on task/model. Sources: chatgpt:oa-business. - limit_behaviour — What happens when a limit is reached? [partial]: Eligible work can draw workspace credits after included allowance; insufficient credits can stop credit-backed features. Sources: chatgpt:oa-credit-controls. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: chatgpt:oa-models, chatgpt:oa-admin-quickstart, chatgpt:oa-admin-settings, chatgpt:oa-business, chatgpt:oa-credit-controls #### Claude Team / Enterprise Verification status: Agent cross-checked (agent-cross-checked) Support: partial Enterprise has model/effort ceilings and ordinary defaults; always-start enforcement is a separate beta with project exceptions. Availability: beta Delivery: native Scope: surfaces=Claude Team and Enterprise web workspaces, Claude desktop and mobile clients, Claude for Microsoft 365 official add-ins, Claude Cowork cloud and desktop task execution; version=Continuously updated commercial service, retrieved 2026-10-21; plan=Enterprise organization/custom-role model access and defaults; Always start with the default model and effort level is beta; add_ons=Enterprise token usage at API rates, Optional US-only inference surcharge, External provider/app subscriptions and Office deployment approval where applicable, CMEK and compliance only on eligible Enterprise configurations; deployment_mode=multi-tenant-saas; region=Commercial supported regions; default global inference and US storage where documented; no EU/Swiss-only residency assumption; os=not specified. Limitations: - Beta applies specifically to forced starting model/effort; ordinary model ceilings and defaults are documented separately. Team entitlement is not inferred. - Existing chat-project selection is an explicit exception. No two-group/model restriction fixture; Chrome/Security and client-version coverage limits still apply. - model_allowlist_by_group — Can admins limit models per group? [partial]: Enterprise organization model/effort ceilings constrain custom roles; Haiku cannot be disabled. Per-source data-binding rules remain unverified. Sources: claude:cl-model-control-r2. - data_bound_models — Can admins restrict which models receive connector or knowledge content? [unknown]: Can admins restrict which models receive connector or knowledge content? Unverified after checking Claude Team/Enterprise pricing, identity, connector, privacy and release documentation retrieved 2026-10-21; no paid organization or shared fixture. - default_model — Can admins set the default model? [partial]: Enterprise can choose an ordinary organization/role default. The Always start switch is beta, still permits in-chat switching, and does not override remembered choices in existing chat projects. New projects and new project Cowork tasks use the default; unavailable product models fall back to Anthropic's recommendation. Sources: claude:cl-default-r2. - user_limits — What per-user message or token limits apply, and are they published? [supported]: Current usage-based Enterprise has no included token allowance or seat usage cap; Team/legacy plans differ. Sources: claude:cl-enterprise. - limit_behaviour — What happens when a limit is reached? [partial]: Disabling an enabled Enterprise model can require fallback or explicit switching; default selection is not permission to access a disabled model. Spend-limit enforcement remains separate. Sources: claude:cl-model-control-r2. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: claude:cl-model-control-r2, claude:cl-default-r2, claude:cl-enterprise ## Company knowledge ### KNOW-01: Files in chat Judgment rule: Record supported formats, size and count limits, scanned-PDF OCR, tables and spreadsheets, images inside documents, and whether a file is read in full or retrieved in chunks. Upload the shared fixture set (long German PDF, scanned contract, Excel with formulas, PowerPoint) and record failures. #### ChatGPT Business / Enterprise Verification status: Agent cross-checked (agent-cross-checked) Support: partial Formats and upload limits are documented; shared-fixture fidelity is untested. Availability: generally-available Delivery: native Scope: surfaces=ChatGPT Business and Enterprise web workspaces, ChatGPT desktop and mobile clients, ChatGPT connected apps and custom MCP apps; version=Continuously updated hosted service, retrieved 2026-10-21; plan=ChatGPT Business Standard/Premium versus Enterprise; Edu only where explicitly named for eligibility differences; add_ons=Purchased workspace credits or contracted token billing where stated, External app/provider subscriptions and Microsoft add-in approval where required, Enterprise residency, EKM and compliance entitlements only where stated; deployment_mode=multi-tenant-saas; region=Supported commercial regions; Europe means EEA + Switzerland when explicitly configured; app/client availability varies; os=not specified. Limitations: - Unverified parts: full_vs_chunked. - Read each atomic answer for its plan, access and feature limits. - formats — Which formats are accepted? [supported]: DOCX/PDF/TXT, XLS/XLSX/CSV/TSV, PPTX and supported image/audio uploads. Sources: chatgpt:oa-files. - limits — What size and count limits apply per file and chat? [supported]: Documents 512 MB/2M tokens; spreadsheets about 50 MB; images 20 MB; up to 80 uploads/3 hours, subject to peak reductions. Sources: chatgpt:oa-files. - ocr — Are scanned PDFs read? [partial]: Enterprise PDF visual retrieval can process embedded visual content; other plans use text-based retrieval. A scanned-contract OCR test was not run. Sources: chatgpt:oa-files. - spreadsheets — Are Excel tables read with structure intact? [partial]: Python analysis accepts structured sheets; formula/structure fidelity was not tested. Sources: chatgpt:oa-analysis. - full_vs_chunked — Is the whole file used or only retrieved parts, and does the user see which? [unknown]: Is the whole file used or only retrieved parts, and does the user see which? Unverified after checking upload and analysis documentation; full/chunk selection and the long-PDF/scanned-contract/formula/PPT fixture were not observed. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: chatgpt:oa-files, chatgpt:oa-analysis #### Claude Team / Enterprise Verification status: Agent cross-checked (agent-cross-checked) Support: partial Chat attachments, project knowledge files and code/file tools have separate published limits. Availability: generally-available Delivery: native Scope: surfaces=Claude Team and Enterprise web workspaces, Claude desktop and mobile clients; version=Continuously updated commercial service, retrieved 2026-10-21; plan=Claude Team/Enterprise Chat attachments and project Files; enabled Chat code/file path only where explicitly named; add_ons=Code execution/file creation must be enabled for XLSX and the computing/file-tool route; deployment_mode=multi-tenant-saas; region=Commercial supported regions; default global inference and US storage where documented; no EU/Swiss-only residency assumption; os=not specified. Limitations: - Limits are assigned to the named UI/repository/tool path rather than treated as conflicting universal maxima. Exact large-attachment transfer into the computing environment remains untested. - Office/Cowork paths are excluded. No long PDF, scan, formula workbook or PowerPoint fixture. - formats — Which formats are accepted? [supported]: Chat attachments support PDF/DOCX/CSV/TXT/HTML/ODT/RTF/EPUB/JSON and XLSX with code execution; JPEG/PNG/GIF/WebP images. This is not an Office/Cowork format matrix. Sources: claude:cl-upload-r2. - limits — What size and count limits apply per file and chat? [partial]: Chat Add files/photo attachments:500 MB/file,20/chat, PDF 1000-page maximum. Project Files:30 MB/file. The separate code/file-creation guide specifies30 MB per upload/download in its computing/file-tool path, with a separate larger-PDF processing caveat. A500 MB attachment is not promised to work in that30 MB tool path. Sources: claude:cl-upload-r2, claude:cl-code-files-r2. - ocr — Are scanned PDFs read? [partial]: For Chat PDF processing, up to 100 pages receive visual/text analysis;101–1000 pages text only. Scanned-contract OCR accuracy was not tested. Sources: claude:cl-upload-r2. - spreadsheets — Are Excel tables read with structure intact? [partial]: Chat XLSX uploads require code/file creation; its file-tool guide has a30 MB upload/download limit. Formula/table preservation was not fixture-tested. Sources: claude:cl-upload-r2, claude:cl-code-files-r2. - full_vs_chunked — Is the whole file used or only retrieved parts, and does the user see which? [partial]: Paid projects switch to search-based RAG near context limits and show an indicator; this does not establish every chat-file reading path. Sources: claude:cl-rag. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: claude:cl-upload-r2, claude:cl-code-files-r2, claude:cl-rag ### KNOW-02: Knowledge bases and shared collections Judgment rule: Record curated document collections that persist across chats, who can create and share them, size limits, and how they attach to assistants. Distinguish personal, group and organisation-wide scope. #### ChatGPT Business / Enterprise Verification status: Agent cross-checked (agent-cross-checked) Support: partial Projects and GPT knowledge persist curated content with sharing and file limits. Availability: generally-available Delivery: native Scope: surfaces=ChatGPT Business and Enterprise web workspaces, ChatGPT desktop and mobile clients, ChatGPT connected apps and custom MCP apps; version=Continuously updated hosted service, retrieved 2026-10-21; plan=ChatGPT Business Standard/Premium versus Enterprise; Edu only where explicitly named for eligibility differences; add_ons=Purchased workspace credits or contracted token billing where stated, External app/provider subscriptions and Microsoft add-in approval where required, Enterprise residency, EKM and compliance entitlements only where stated; deployment_mode=multi-tenant-saas; region=Supported commercial regions; Europe means EEA + Switzerland when explicitly configured; app/client availability varies; os=not specified. Limitations: - Custom GPT retirement is planned for affected Enterprise workspaces; the dates are in the roadmap review. - persistent_collections — Can users keep document collections across chats? [supported]: Projects retain chats, files and instructions across related work. Sources: chatgpt:oa-projects. - sharing_scope — Can collections be shared with users, groups or the whole organisation? [partial]: Shared projects expose project contents to admitted members and support group invitations where permitted; full entitlement matrix was not tested. Sources: chatgpt:oa-projects. - size_limits — What are the collection limits? [supported]: Business/Enterprise/Edu projects allow 40 files; a GPT can have up to 20 knowledge files. Sources: chatgpt:oa-files. - assistant_binding — Can collections be bound to an assistant? [supported]: GPTs can bind knowledge files; project chats can use GPTs under documented constraints. Sources: chatgpt:oa-files, chatgpt:oa-projects. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: chatgpt:oa-projects, chatgpt:oa-files #### Claude Team / Enterprise Verification status: Agent cross-checked (agent-cross-checked) Support: partial Projects persist curated knowledge and instructions and support organizational sharing. Availability: generally-available Delivery: native Scope: surfaces=Claude Team and Enterprise web workspaces, Claude desktop and mobile clients, Claude connectors and remote MCP integrations, Claude for Microsoft 365 official add-ins, Claude Cowork cloud and desktop task execution; version=Continuously updated commercial service, retrieved 2026-10-21; plan=Claude Team Standard/Premium versus current usage-based Enterprise; legacy Enterprise only when explicitly named; add_ons=Enterprise token usage at API rates, Optional US-only inference surcharge, External provider/app subscriptions and Office deployment approval where applicable, CMEK and compliance only on eligible Enterprise configurations; deployment_mode=multi-tenant-saas; region=Commercial supported regions; default global inference and US storage where documented; no EU/Swiss-only residency assumption; os=not specified. Limitations: - Read each atomic answer for its plan, access and feature limits. - persistent_collections — Can users keep document collections across chats? [supported]: Projects retain a knowledge base and instructions for related chats. Sources: claude:cl-projects. - sharing_scope — Can collections be shared with users, groups or the whole organisation? [supported]: Team/Enterprise share projects with organization members; Enterprise groups can receive shared resources. Sources: claude:cl-projects, claude:cl-groups. - size_limits — What are the collection limits? [partial]: Project files have a 30 MB limit; paid RAG expands effective knowledge capacity, with no fixed total capacity verified. Sources: claude:cl-upload, claude:cl-rag. - assistant_binding — Can collections be bound to an assistant? [partial]: Project instructions and knowledge provide persistent task context; binding tools/model into a separately versioned assistant was not fully verified. Sources: claude:cl-projects. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: claude:cl-projects, claude:cl-groups, claude:cl-upload, claude:cl-rag ### KNOW-03: Enterprise connectors Judgment rule: List each connector separately with plan, availability and setup owner: SharePoint, OneDrive, Outlook, Teams, Google Drive, Gmail, Confluence, Jira, Notion, Box, Salesforce, ServiceNow, file shares. Record whether the vendor or a third party (or the customer via MCP) provides it, and whether it needs admin consent. A connector listed on a roadmap or partner page is `announced`. An on-prem connector or gateway proves access to local data, not a self-hosted platform (DATA-02). #### ChatGPT Business / Enterprise Verification status: Agent cross-checked (agent-cross-checked) Support: partial Live apps and custom MCP connect business data; individual app entitlement and permission scope matter. Availability: generally-available Delivery: native Scope: surfaces=ChatGPT Business and Enterprise web workspaces, ChatGPT desktop and mobile clients, ChatGPT connected apps and custom MCP apps; version=Continuously updated hosted service, retrieved 2026-10-21; plan=ChatGPT Business Standard/Premium versus Enterprise; Edu only where explicitly named for eligibility differences; add_ons=Purchased workspace credits or contracted token billing where stated, External app/provider subscriptions and Microsoft add-in approval where required, Enterprise residency, EKM and compliance entitlements only where stated; deployment_mode=multi-tenant-saas; region=Supported commercial regions; Europe means EEA + Switzerland when explicitly configured; app/client availability varies; os=not specified. Limitations: - Microsoft Entra consent and ChatGPT app/action enablement are distinct. No connector list is treated as a passed retrieval test. - microsoft_365 — Which M365 sources (SharePoint, OneDrive, Outlook, Teams) are connected? [supported]: SharePoint covers supported SharePoint/OneDrive work content. Current Enterprise notes describe Teams and Outlook live-app controls. Sources: chatgpt:oa-sharepoint, chatgpt:oa-enterprise-notes. - google_workspace — Which Google sources are connected? [partial]: Current app/release documentation includes Google Drive and Gmail event connections; permissions and region depend on the app. Sources: chatgpt:oa-apps, chatgpt:oa-team-tasks. - atlassian — Confluence and Jira? [partial]: Business release notes list the Atlassian Rovo MCP connection for Jira, Confluence and Compass; current per-region rollout was not trialled. Sources: chatgpt:oa-business-notes. - other_systems — Which other business systems? [partial]: Slack is documented; Business app templates include GitHub Enterprise, Snowflake and Databricks. Box, Salesforce and ServiceNow details remain unverified. Sources: chatgpt:oa-business-notes. - on_prem_sources — Can on-prem file shares or databases be connected? [partial]: Custom remote MCP can reach private systems through a secure tunnel; named file-share/database coverage and deployment entitlement were not tested. Sources: chatgpt:oa-mcp. - connector_provider — Who builds and maintains each connector? [partial]: OpenAI-built, partner and customer MCP apps coexist; the responsible publisher must be checked per app. Sources: chatgpt:oa-mcp. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: chatgpt:oa-sharepoint, chatgpt:oa-enterprise-notes, chatgpt:oa-apps, chatgpt:oa-team-tasks, chatgpt:oa-business-notes, chatgpt:oa-mcp #### Claude Team / Enterprise Verification status: Agent cross-checked (agent-cross-checked) Support: partial First-party Microsoft/Google connectors and custom MCP provide distinct enterprise-data routes. Availability: generally-available Delivery: native Scope: surfaces=Claude Team and Enterprise web workspaces, Claude desktop and mobile clients, Claude connectors and remote MCP integrations, Claude for Microsoft 365 official add-ins, Claude Cowork cloud and desktop task execution; version=Continuously updated commercial service, retrieved 2026-10-21; plan=Claude Team Standard/Premium versus current usage-based Enterprise; legacy Enterprise only when explicitly named; add_ons=Enterprise token usage at API rates, Optional US-only inference surcharge, External provider/app subscriptions and Office deployment approval where applicable, CMEK and compliance only on eligible Enterprise configurations; deployment_mode=multi-tenant-saas; region=Commercial supported regions; default global inference and US storage where documented; no EU/Swiss-only residency assumption; os=not specified. Limitations: - atlassian: Claude Enterprise documents Atlassian Rovo MCP for Jira, Confluence and Teamwork Graph, including organization-managed authorization through Okta. This does not establish a native indexed Confluence connector, universal Team entitlement or observed ACL fidelity. - other_systems: Enterprise docs list GitHub and Slack; Salesforce is a separately approved paid-plan beta in release notes. Box/ServiceNow details remain unverified. - on_prem_sources: Remote MCP must be reachable from Anthropic cloud; Desktop-local MCP is separate and unavailable in cloud chat/Cowork. Named file-share/database connectors were not verified. - microsoft_365 — Which M365 sources (SharePoint, OneDrive, Outlook, Teams) are connected? [supported]: Anthropic-hosted Graph connector covers SharePoint, OneDrive, Outlook and Teams; Claude owner enablement and Entra consent are separate. Sources: claude:cl-m365-20261026. - google_workspace — Which Google sources are connected? [supported]: Gmail, Calendar and Drive are documented with owner enablement and user authorization; live Docs/Sheets/Slides are separate connectors. Sources: claude:cl-google-20261026. - atlassian — Confluence and Jira? [partial]: Claude Enterprise documents Atlassian Rovo MCP for Jira, Confluence and Teamwork Graph, including organization-managed authorization through Okta. This does not establish a native indexed Confluence connector, universal Team entitlement or observed ACL fidelity. Sources: claude:claude:atlassian-enterprise-20261026, claude:cl-mcp-20261026. - other_systems — Which other business systems? [partial]: Enterprise docs list GitHub and Slack; Salesforce is a separately approved paid-plan beta in release notes. Box/ServiceNow details remain unverified. Sources: claude:cl-enterprise-20261026, claude:cl-release-20261026. - on_prem_sources — Can on-prem file shares or databases be connected? [partial]: Remote MCP must be reachable from Anthropic cloud; Desktop-local MCP is separate and unavailable in cloud chat/Cowork. Named file-share/database connectors were not verified. Sources: claude:cl-mcp-20261026. - connector_provider — Who builds and maintains each connector? [supported]: Microsoft connector is Anthropic-hosted; custom MCP may be built/hosted by the customer or a third party. Sources: claude:cl-m365-20261026, claude:cl-mcp-20261026. Checked 2026-10-26; agent cross-checked 2026-10-26; check again by 2026-12-20. Sources: claude:cl-m365-20261026, claude:cl-google-20261026, claude:cl-enterprise-20261026, claude:cl-release-20261026, claude:cl-mcp-20261026, claude:claude:atlassian-enterprise-20261026 ### KNOW-04: Permission-aware retrieval Judgment rule: Using two test users, verify that a restricted document in the fixture tenant is never cited or summarised for the user without access, including after a permission change. Record whether permissions are enforced at query time by the source system, mirrored into an index, or not enforced. Record the propagation delay of a revocation. #### ChatGPT Business / Enterprise Verification status: Agent cross-checked (agent-cross-checked) Support: partial Connected sources inherit user permissions; plan entitlement for additional SharePoint site/label controls remains unverified. Availability: generally-available Delivery: native Scope: surfaces=ChatGPT Business and Enterprise web workspaces, ChatGPT connected apps and custom MCP apps; version=Continuously updated hosted service, retrieved 2026-10-21; plan=Business/Enterprise/Edu Company Knowledge source permissions and app enablement; SharePoint policy controls require separate workspace enablement with plan eligibility unverified; add_ons=Purchased workspace credits or contracted token billing where stated, External app/provider subscriptions and Microsoft add-in approval where required, Enterprise residency, EKM and compliance entitlements only where stated; deployment_mode=multi-tenant-saas; region=Supported commercial regions; Europe means EEA + Switzerland when explicitly configured; app/client availability varies; os=not specified. Limitations: - Positive plan-scoped findings cover source-account permissions and app availability controls. Optional SharePoint policies are recorded as conditional documentation and an explicit entitlement gap. - No two-user restricted-document, label-exclusion or revocation-latency test. - source_permissions_respected — Are source permissions enforced per user? [supported]: Company Knowledge is documented for Business/Enterprise/Edu and retrieves only content the connected source account permits. Sources: chatgpt:oa-company-r2. - enforcement_point — Does the source system, a mirrored index or nothing enforce them? [partial]: Live SharePoint checks authorized Microsoft-account access and requires delegated Sites.Read.All/Files.Read.All; setup availability remains workspace-dependent. Sources: chatgpt:oa-sharepoint-r2. - revocation_delay — How quickly does a removed permission take effect? [unknown]: How quickly does a removed permission take effect? Unverified after checking live SharePoint and Company Knowledge docs; no two-user/revocation fixture. - admin_scope_controls — Can admins exclude sites, folders or labels? [partial]: Owners/admins manage allowed apps/sources; Enterprise/Edu add RBAC/group controls. A separate enabled-workspace guide describes SharePoint site policies, but its complete plan matrix was not verified. Sources: chatgpt:oa-company-r2, chatgpt:oa-sharepoint-policy-r2. - sensitivity_labels — Are Microsoft Purview or similar labels respected? [unknown]: The SharePoint policy guide describes label-GUID exclusions only after workspace enablement and does not name a complete plan matrix. Availability for Business or a particular Enterprise configuration remains unverified; no fixture was run. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: chatgpt:oa-company-r2, chatgpt:oa-sharepoint-r2, chatgpt:oa-sharepoint-policy-r2 #### Claude Team / Enterprise Verification status: Agent cross-checked (agent-cross-checked) Support: partial Documented live-source permissions do not replace the required two-user test. Availability: generally-available Delivery: native Scope: surfaces=Claude Team and Enterprise web workspaces, Claude desktop and mobile clients, Claude connectors and remote MCP integrations, Claude for Microsoft 365 official add-ins, Claude Cowork cloud and desktop task execution; version=Continuously updated commercial service, retrieved 2026-10-21; plan=Claude Team Standard/Premium versus current usage-based Enterprise; legacy Enterprise only when explicitly named; add_ons=Enterprise token usage at API rates, Optional US-only inference surcharge, External provider/app subscriptions and Office deployment approval where applicable, CMEK and compliance only on eligible Enterprise configurations; deployment_mode=multi-tenant-saas; region=Commercial supported regions; default global inference and US storage where documented; no EU/Swiss-only residency assumption; os=not specified. Limitations: - No observed permission assurance or revocation SLA is established. Shared conversation output can reveal retrieved content to recipients. - source_permissions_respected — Are source permissions enforced per user? [supported]: Microsoft and Google connectors use the connected user account permissions. Sources: claude:cl-m365, claude:cl-google. - enforcement_point — Does the source system, a mirrored index or nothing enforce them? [supported]: Microsoft Graph delegated calls check source access; the connector is a proxy without a copied file-content cache. Sources: claude:cl-m365. - revocation_delay — How quickly does a removed permission take effect? [unknown]: How quickly does a removed permission take effect? Unverified after checking connector security and user docs; no restricted-document or revocation-latency fixture. - admin_scope_controls — Can admins exclude sites, folders or labels? [partial]: Owners control connectors/tools; Microsoft Sites.Selected and a SharePoint site allowlist are explicitly unavailable in this connector. Sources: claude:cl-m365-user. - sensitivity_labels — Are Microsoft Purview or similar labels respected? [partial]: The Microsoft security guide says delegated access respects M365 DLP; exact Purview label exclusion behavior was not tested. Sources: claude:cl-m365. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: claude:cl-m365, claude:cl-google, claude:cl-m365-user ### KNOW-05: Freshness and sync model Judgment rule: Record live (federated) search versus a copied index, sync interval, deletion propagation, and where the index is stored. Edit and delete one fixture document and record when answers change. A copied index adds storage location to DATA-01. #### ChatGPT Business / Enterprise Verification status: Agent cross-checked (agent-cross-checked) Support: partial Enterprise administrator-managed sync retired October16; supported real-time apps are the replacement route. Availability: generally-available Delivery: native Scope: surfaces=ChatGPT Business and Enterprise web workspaces, ChatGPT connected apps and custom MCP apps; version=Continuously updated hosted service, retrieved 2026-10-21; plan=Enterprise workspaces affected by the October16 administrator-managed sync retirement; no inferred Business retirement schedule; add_ons=Purchased workspace credits or contracted token billing where stated, External app/provider subscriptions and Microsoft add-in approval where required, Enterprise residency, EKM and compliance entitlements only where stated; deployment_mode=multi-tenant-saas; region=Supported commercial regions; Europe means EEA + Switzerland when explicitly configured; app/client availability varies; os=not specified. Limitations: - The earlier indexing conflict was stale context: the rechecked Company Knowledge/residency articles now describe current app-based access. Historical configurations are outside this current Enterprise finding. - Per-app synchronization, deletion timing and index geography remain unknown. No Business-wide retirement is inferred from Enterprise notes. - live_or_indexed — Is content searched live or copied into an index? [partial]: The Enterprise October16 notice retires administrator-managed sync and directs use of real-time GoogleDrive/SharePoint/Teams. Current Company Knowledge uses eligible apps; current residency guidance no longer specifies the older admin-indexing route. This does not prove every third-party app is index-free. Sources: chatgpt:oa-enterprise-notes-r2, chatgpt:oa-company-r2, chatgpt:oa-residency-r2. - sync_interval — How often does an index refresh? [unknown]: How often does an index refresh? Unverified after checking October 16 Enterprise notes and live SharePoint docs; app-specific refresh/deletion SLAs and index geography not verified. - deletion_propagation — How quickly does a deleted document disappear? [unknown]: How quickly does a deleted document disappear? Unverified after checking October 16 Enterprise notes and live SharePoint docs; app-specific refresh/deletion SLAs and index geography not verified. - index_location — Where is indexed content stored? [unknown]: Where is indexed content stored? Unverified after checking October 16 Enterprise notes and live SharePoint docs; app-specific refresh/deletion SLAs and index geography not verified. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: chatgpt:oa-enterprise-notes-r2, chatgpt:oa-company-r2, chatgpt:oa-residency-r2 #### Claude Team / Enterprise Verification status: Agent cross-checked (agent-cross-checked) Support: partial Microsoft content is fetched on demand; Google project references have a separate sync path. Availability: generally-available Delivery: native Scope: surfaces=Claude Team and Enterprise web workspaces, Claude desktop and mobile clients, Claude connectors and remote MCP integrations, Claude for Microsoft 365 official add-ins, Claude Cowork cloud and desktop task execution; version=Continuously updated commercial service, retrieved 2026-10-21; plan=Claude Team Standard/Premium versus current usage-based Enterprise; legacy Enterprise only when explicitly named; add_ons=Enterprise token usage at API rates, Optional US-only inference surcharge, External provider/app subscriptions and Office deployment approval where applicable, CMEK and compliance only on eligible Enterprise configurations; deployment_mode=multi-tenant-saas; region=Commercial supported regions; default global inference and US storage where documented; no EU/Swiss-only residency assumption; os=not specified. Limitations: - Unverified parts: sync_interval, deletion_propagation, index_location. - Read each atomic answer for its plan, access and feature limits. - live_or_indexed — Is content searched live or copied into an index? [partial]: Microsoft uses on-demand Graph access without caching file content. Google Docs attached to private projects sync from Drive. Sources: claude:cl-m365, claude:cl-google. - sync_interval — How often does an index refresh? [unknown]: How often does an index refresh? Unverified after checking Microsoft proxy and Google Workspace docs; full sync interval, deletion propagation and copied-index storage map not measured. - deletion_propagation — How quickly does a deleted document disappear? [unknown]: How quickly does a deleted document disappear? Unverified after checking Microsoft proxy and Google Workspace docs; full sync interval, deletion propagation and copied-index storage map not measured. - index_location — Where is indexed content stored? [unknown]: Where is indexed content stored? Unverified after checking Microsoft proxy and Google Workspace docs; full sync interval, deletion propagation and copied-index storage map not measured. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: claude:cl-m365, claude:cl-google ### KNOW-06: Grounding and retrieval quality Judgment rule: Run the shared question set over the fixture corpus: factual lookups, cross-document questions, German document with an English question, a question with no answer in the corpus. Record citation presence, link accuracy, correct answers and refusals to invent. Disclose model, settings, attempt count and failures. Single runs support a case study, not a ranking. #### ChatGPT Business / Enterprise Verification status: Agent cross-checked (agent-cross-checked) Support: partial Source links are documented; shared-corpus grounding accuracy remains unknown. Availability: generally-available Delivery: native Scope: surfaces=ChatGPT Business and Enterprise web workspaces, ChatGPT desktop and mobile clients, ChatGPT connected apps and custom MCP apps; version=Continuously updated hosted service, retrieved 2026-10-21; plan=ChatGPT Business Standard/Premium versus Enterprise; Edu only where explicitly named for eligibility differences; add_ons=Purchased workspace credits or contracted token billing where stated, External app/provider subscriptions and Microsoft add-in approval where required, Enterprise residency, EKM and compliance entitlements only where stated; deployment_mode=multi-tenant-saas; region=Supported commercial regions; Europe means EEA + Switzerland when explicitly configured; app/client availability varies; os=not specified. Limitations: - No answer accuracy, citation accuracy or refusal rate was measured. - citations — Are answers linked to specific sources? [partial]: Company Knowledge and SharePoint answers can include source links; presence is not guaranteed for every answer. Sources: chatgpt:oa-company, chatgpt:oa-sharepoint. - citation_accuracy — Do the cited passages support the answer? [unknown]: Do the cited passages support the answer? Unverified after checking Company Knowledge/source-link docs; no factual, cross-document, cross-language or unanswerable-question fixture. - cross_language — Does a question in one language find documents in another? [unknown]: Does a question in one language find documents in another? Unverified after checking Company Knowledge/source-link docs; no factual, cross-document, cross-language or unanswerable-question fixture. - no_answer_behaviour — Does it say when the corpus has no answer? [unknown]: Does it say when the corpus has no answer? Unverified after checking Company Knowledge/source-link docs; no factual, cross-document, cross-language or unanswerable-question fixture. - observed_accuracy — How many of the question set were answered correctly? [unknown]: How many of the question set were answered correctly? Unverified after checking Company Knowledge/source-link docs; no factual, cross-document, cross-language or unanswerable-question fixture. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: chatgpt:oa-company, chatgpt:oa-sharepoint #### Claude Team / Enterprise Verification status: Agent cross-checked (agent-cross-checked) Support: partial Google-source citations are documented; grounding accuracy remains unmeasured. Availability: generally-available Delivery: native Scope: surfaces=Claude Team and Enterprise web workspaces, Claude desktop and mobile clients, Claude connectors and remote MCP integrations, Claude for Microsoft 365 official add-ins, Claude Cowork cloud and desktop task execution; version=Continuously updated commercial service, retrieved 2026-10-21; plan=Claude Team Standard/Premium versus current usage-based Enterprise; legacy Enterprise only when explicitly named; add_ons=Enterprise token usage at API rates, Optional US-only inference surcharge, External provider/app subscriptions and Office deployment approval where applicable, CMEK and compliance only on eligible Enterprise configurations; deployment_mode=multi-tenant-saas; region=Commercial supported regions; default global inference and US storage where documented; no EU/Swiss-only residency assumption; os=not specified. Limitations: - No observed accuracy or cross-language retrieval ranking. - citations — Are answers linked to specific sources? [partial]: Google connector answers cite original email/calendar/document sources when available. Sources: claude:cl-google. - citation_accuracy — Do the cited passages support the answer? [unknown]: Do the cited passages support the answer? Unverified after checking Google connector citation docs; no multilingual shared corpus, cross-document, citation-accuracy or unanswerable-question test. - cross_language — Does a question in one language find documents in another? [unknown]: Does a question in one language find documents in another? Unverified after checking Google connector citation docs; no multilingual shared corpus, cross-document, citation-accuracy or unanswerable-question test. - no_answer_behaviour — Does it say when the corpus has no answer? [unknown]: Does it say when the corpus has no answer? Unverified after checking Google connector citation docs; no multilingual shared corpus, cross-document, citation-accuracy or unanswerable-question test. - observed_accuracy — How many of the question set were answered correctly? [unknown]: How many of the question set were answered correctly? Unverified after checking Google connector citation docs; no multilingual shared corpus, cross-document, citation-accuracy or unanswerable-question test. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: claude:cl-google ### KNOW-07: Memory and personal context Judgment rule: Record personal custom instructions, cross-chat memory, project or workspace context, and user controls to view, edit, delete or disable memory. Record whether admins can disable memory organisation-wide. #### ChatGPT Business / Enterprise Verification status: Agent cross-checked (agent-cross-checked) Support: supported Personal memory and project context have user and Enterprise role controls. Availability: generally-available Delivery: native Scope: surfaces=ChatGPT Business and Enterprise web workspaces, ChatGPT desktop and mobile clients, ChatGPT connected apps and custom MCP apps; version=Continuously updated hosted service, retrieved 2026-10-21; plan=ChatGPT Business Standard/Premium versus Enterprise; Edu only where explicitly named for eligibility differences; add_ons=Purchased workspace credits or contracted token billing where stated, External app/provider subscriptions and Microsoft add-in approval where required, Enterprise residency, EKM and compliance entitlements only where stated; deployment_mode=multi-tenant-saas; region=Supported commercial regions; Europe means EEA + Switzerland when explicitly configured; app/client availability varies; os=not specified. - custom_instructions — Can users set persistent instructions? [supported]: Custom instructions give persistent user guidance, separate from inferred memory. Sources: chatgpt:oa-memory. - cross_chat_memory — Does the product remember facts across chats? [supported]: Enabled memory can use remembered facts and prior-chat context; availability varies. Sources: chatgpt:oa-memory. - user_memory_controls — Can users view, edit and delete memories? [supported]: Users can inspect, correct or delete remembered information; source chats/files may need separate deletion. Sources: chatgpt:oa-memory. - admin_memory_controls — Can admins turn memory off? [supported]: Enterprise admins can manage supported shared/improved-memory permissions by role. Sources: chatgpt:oa-admin-settings. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: chatgpt:oa-memory, chatgpt:oa-admin-settings #### Claude Team / Enterprise Verification status: Agent cross-checked (agent-cross-checked) Support: partial Improved memory and legacy memory have different Team/Enterprise administration and Cowork behavior. Availability: generally-available Delivery: native Scope: surfaces=Claude Team and Enterprise web workspaces, Claude desktop and mobile clients, Claude Cowork cloud and desktop task execution; version=Continuously updated commercial service, retrieved 2026-10-21; plan=Team/Enterprise improved Settings>Memory experience; legacy Settings>Capabilities memory is separately qualified; project instructions are independent; add_ons=Enterprise token usage at API rates, Optional US-only inference surcharge, External provider/app subscriptions and Office deployment approval where applicable, CMEK and compliance only on eligible Enterprise configurations; deployment_mode=multi-tenant-saas; region=Commercial supported regions; default global inference and US storage where documented; no EU/Swiss-only residency assumption; os=not specified. Limitations: - Identify experience by Settings>Memory versus legacy Memory under Settings>Capabilities; neither control set is applied universally. - No organization memory fixture. Current page retains a legacy section for a small number of Team/Enterprise organizations. - custom_instructions — Can users set persistent instructions? [supported]: Projects have persistent instructions for context and style. Sources: claude:cl-projects. - cross_chat_memory — Does the product remember facts across chats? [partial]: Improved memory: owners enable availability and members opt in; cloud Cowork shares Chat memory, local Cowork does not. Legacy memory is chat-only and unavailable in Cowork. Sources: claude:cl-memory-r2. - user_memory_controls — Can users view, edit and delete memories? [partial]: Improved memory users inspect/delete topics, pause/reset and choose sensitive-topic opt-in. Incognito remains subject to organization export/retention. Legacy settings and summary-memory behavior differ. Sources: claude:cl-memory-r2. - admin_memory_controls — Can admins turn memory off? [partial]: Improved memory: Owners/Primary Owners control availability; disabling it deletes existing entries. Legacy Team explicitly lacks org-level memory controls. Improved memory is unavailable under the named HIPAA/public-sector/custom-retention agreements. Sources: claude:cl-memory-r2. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: claude:cl-projects, claude:cl-memory-r2 ## Assistants and agents ### AGT-01: Custom assistants Judgment rule: Record creation of assistants with instructions, model, knowledge and tools; who can create; sharing scope; versioning; and an internal catalogue or directory. Build one HR policy assistant on the fixture and share it with one group. Prompt templates and a prompt library are recorded here. #### ChatGPT Business / Enterprise Verification status: Agent cross-checked (agent-cross-checked) Support: partial GPTs, plugins and Workspace Agents offer reusable behavior; current notices plan custom-GPT retirement across plans. Availability: generally-available Delivery: native Scope: surfaces=ChatGPT Business and Enterprise web workspaces, ChatGPT desktop and mobile clients, ChatGPT connected apps and custom MCP apps, ChatGPT Work and team tasks, distinct from regular Chat and coding-only Codex; version=Current hosted commercial documentation checked 2026-10-26; plan=Business and Enterprise reusable workspace GPT/project/plugin behavior, subject to access controls; add_ons=Purchased workspace credits or contracted token billing where stated, External app/provider subscriptions and Microsoft add-in approval where required, Enterprise residency, EKM and compliance entitlements only where stated; deployment_mode=multi-tenant-saas; region=Supported commercial regions; Europe means EEA + Switzerland when explicitly configured; app/client availability varies; os=not specified. Limitations: - create_assistants: Business includes GPTs and Workspace Agents; projects/GPT knowledge provide instructions and files. Tools depend on app configuration. - creator_permissions: Workspace settings govern creation and sharing. The FAQ covers all-plan retirement on December 11, subject to account/workspace notices and approved Enterprise deferrals. In affected Enterprise workspaces, October 26 is the planned freeze on new GPT creation; publish drafts needed for migration before it. Existing unmigrated GPTs remain editable; migration makes the original read-only. Tenant state was not observed. - sharing_scope: Workspace GPT/project sharing is documented; exact user/group/public options depend on workspace policy and residency. - catalogue: The plugin directory and workspace GPT/agent discovery are documented. - prompt_library: The direct Plugins guide describes reusable skills/instructions and apps for Chat/Work, including workspace plugin sharing on Business/Enterprise. A dedicated prompt-library contract was not verified. Word has separate skills: plugins are unsupported there and ChatGPT skills do not carry over. - create_assistants — Can users create assistants with instructions, knowledge and tools? [partial]: Business includes GPTs and Workspace Agents; projects/GPT knowledge provide instructions and files. Tools depend on app configuration. Sources: chatgpt:oa-business-20261026, chatgpt:oa-files-20261026, chatgpt:oa-business-notes-20261026. - creator_permissions — Can admins limit who creates them? [partial]: Workspace settings govern creation and sharing. The FAQ covers all-plan retirement on December 11, subject to account/workspace notices and approved Enterprise deferrals. In affected Enterprise workspaces, October 26 is the planned freeze on new GPT creation; publish drafts needed for migration before it. Existing unmigrated GPTs remain editable; migration makes the original read-only. Tenant state was not observed. Sources: chatgpt:chatgpt:review-fix-gpt-creation-freeze-20261026, chatgpt:oa-admin-settings-20261026. - sharing_scope — Can assistants be shared with users, groups or everyone? [partial]: Workspace GPT/project sharing is documented; exact user/group/public options depend on workspace policy and residency. Sources: chatgpt:oa-projects, chatgpt:oa-residency-r2-20261026. - catalogue — Is there an internal assistant directory? [partial]: The plugin directory and workspace GPT/agent discovery are documented. Sources: chatgpt:oa-business-notes-20261026, chatgpt:oa-company-r2-20261026. - prompt_library — Are shared prompt templates available? [partial]: The direct Plugins guide describes reusable skills/instructions and apps for Chat/Work, including workspace plugin sharing on Business/Enterprise. A dedicated prompt-library contract was not verified. Word has separate skills: plugins are unsupported there and ChatGPT skills do not carry over. Sources: chatgpt:oa-plugins-r2-20261026, chatgpt:oa-word-r2-20261026. Checked 2026-10-26; agent cross-checked 2026-10-26; check again by 2026-12-20. Sources: chatgpt:oa-business-20261026, chatgpt:oa-files-20261026, chatgpt:oa-business-notes-20261026, chatgpt:oa-admin-settings-20261026, chatgpt:oa-projects, chatgpt:oa-residency-r2-20261026, chatgpt:oa-company-r2-20261026, chatgpt:oa-plugins-r2-20261026, chatgpt:oa-word-r2-20261026, chatgpt:oa-gpt-migration-r2-20261026, chatgpt:oa-enterprise-notes-20261026, chatgpt:chatgpt:review-fix-gpt-creation-freeze-20261026 #### Claude Team / Enterprise Verification status: Agent cross-checked (agent-cross-checked) Support: partial Projects, skills, plugins and artifacts provide reusable task context; full assistant governance remains partly unverified. Availability: generally-available Delivery: native Scope: surfaces=Claude Team and Enterprise web workspaces, Claude desktop and mobile clients, Claude connectors and remote MCP integrations, Claude for Microsoft 365 official add-ins, Claude Cowork cloud and desktop task execution; version=Continuously updated commercial service, retrieved 2026-10-21; plan=Claude Team Standard/Premium versus current usage-based Enterprise; legacy Enterprise only when explicitly named; add_ons=Enterprise token usage at API rates, Optional US-only inference surcharge, External provider/app subscriptions and Office deployment approval where applicable, CMEK and compliance only on eligible Enterprise configurations; deployment_mode=multi-tenant-saas; region=Commercial supported regions; default global inference and US storage where documented; no EU/Swiss-only residency assumption; os=not specified. Limitations: - No HR-policy assistant was built or shared with a test group. - create_assistants — Can users create assistants with instructions, knowledge and tools? [partial]: Projects pair instructions/knowledge; skills and plugins provide reusable task behavior, while custom agent model/tool binding was not fully audited. Sources: claude:cl-projects, claude:cl-academy. - creator_permissions — Can admins limit who creates them? [partial]: Enterprise groups/custom roles control plugin access and shared resources; a complete assistant-creator matrix was not verified. Sources: claude:cl-groups. - sharing_scope — Can assistants be shared with users, groups or everyone? [supported]: Team/Enterprise projects share with organization members; Enterprise groups can receive projects/skills/plugins. Sources: claude:cl-projects, claude:cl-groups. - catalogue — Is there an internal assistant directory? [partial]: Organization resources and plugins can be shared; a complete internal assistant directory was not inspected. Sources: claude:cl-groups. - prompt_library — Are shared prompt templates available? [partial]: Skills capture reusable instructions/processes across Office apps; plain prompt-template catalogue behavior was not verified. Sources: claude:cl-office. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: claude:cl-projects, claude:cl-academy, claude:cl-groups, claude:cl-office ### AGT-02: Tools, actions and MCP Judgment rule: Record built-in tools, custom actions (OpenAPI), MCP client support (local and remote servers), authentication model per tool (shared service account or per-user OAuth), and admin approval of tools. Verify one external-tool call and its access boundary. #### ChatGPT Business / Enterprise Verification status: Agent cross-checked (agent-cross-checked) Support: partial Current custom MCP connections use the web Plugins flow with plan-specific creator and publication permissions. Availability: generally-available Delivery: native Scope: surfaces=ChatGPT Business and Enterprise web workspaces, ChatGPT connected apps and custom MCP apps; version=Continuously updated hosted service, retrieved 2026-10-21; plan=Business and Enterprise/Edu custom remote MCP connections on ChatGPT web; Enterprise built-in tools only where explicitly named; add_ons=Purchased workspace credits or contracted token billing where stated, External app/provider subscriptions and Microsoft add-in approval where required, Enterprise residency, EKM and compliance entitlements only where stated; deployment_mode=multi-tenant-saas; region=Supported commercial regions; Europe means EEA + Switzerland when explicitly configured; app/client availability varies; os=not specified. Limitations: - Reconciliation: the rechecked MCP page redirects to Connecting custom MCP servers and replaces the old Developer Mode/search-only account with the current Plugins workflow. OpenAI-built apps are not assumed search-only. - Custom remote MCP scope is web. No tool/authentication/approval fixture or universal write permission is claimed. - builtin_tools — Which tools are built in? [supported]: Enterprise model documentation lists search/research/analysis/uploads/canvas/projects/voice/images; this inventory is Enterprise-specific. Sources: chatgpt:oa-enterprise-models-r2. - custom_actions — Can admins add API actions? [partial]: Custom MCP servers can expose read and write/modify tools. OpenAPI-action migration/parity is not established by this MCP finding. Sources: chatgpt:oa-mcp-r2. - mcp_client — Can it use remote MCP servers, and with what admin control? [supported]: Full MCP/custom remote connections are documented for Business/Enterprise/Edu web. Current Plugins creation does not require Developer Mode and the guide does not label this current flow beta. Sources: chatgpt:oa-mcp-r2. - tool_auth — Do tools act as the user or as a shared account? [supported]: Personal app authorization and designated team service-account connections are separate routes. Sources: chatgpt:oa-apps, chatgpt:oa-team-tasks. - tool_approval — Can admins approve or block tools, and can users confirm actions before they run? [partial]: Business admins/owners create/publish; Enterprise/Edu may delegate creation by RBAC but only admins/owners publish. Chat confirmations depend on app permissions/context; Workspace Agents use builder-specific controls. The live SharePoint app also documents separately enabled writes. Sources: chatgpt:oa-mcp-r2, chatgpt:oa-sharepoint-r2. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: chatgpt:oa-enterprise-models-r2, chatgpt:oa-mcp-r2, chatgpt:oa-apps, chatgpt:oa-team-tasks, chatgpt:oa-sharepoint-r2 #### Claude Team / Enterprise Verification status: Agent cross-checked (agent-cross-checked) Support: partial Claude supports remote and local MCP with different execution and identity boundaries. Availability: generally-available Delivery: native Scope: surfaces=Claude Team and Enterprise web workspaces, Claude desktop and mobile clients, Claude connectors and remote MCP integrations, Claude for Microsoft 365 official add-ins, Claude Cowork cloud and desktop task execution; version=Continuously updated commercial service, retrieved 2026-10-21; plan=Claude Team Standard/Premium versus current usage-based Enterprise; legacy Enterprise only when explicitly named; add_ons=Enterprise token usage at API rates, Optional US-only inference surcharge, External provider/app subscriptions and Office deployment approval where applicable, CMEK and compliance only on eligible Enterprise configurations; deployment_mode=multi-tenant-saas; region=Commercial supported regions; default global inference and US storage where documented; no EU/Swiss-only residency assumption; os=not specified. Limitations: - No external-tool call or fixture permission test was performed. - builtin_tools — Which tools are built in? [supported]: Code execution, web search, Research and connector tools are listed for commercial plans. Sources: claude:cl-pricing. - custom_actions — Can admins add API actions? [partial]: Custom remote MCP can expose action tools; OpenAPI-specific action configuration was not separately verified. Sources: claude:cl-mcp. - mcp_client — Can it use remote MCP servers, and with what admin control? [supported]: Remote MCP works through Anthropic cloud. Desktop-local MCP is a separate local-network mechanism; Cowork/cloud chat cannot use that local configuration. Sources: claude:cl-mcp. - tool_auth — Do tools act as the user or as a shared account? [supported]: Remote connectors can use per-user OAuth or fixed shared request-header credentials; the latter exposes that credential's access to users. Sources: claude:cl-mcp. - tool_approval — Can admins approve or block tools, and can users confirm actions before they run? [partial]: Owners enable connectors and tools; Microsoft Teams sends require Ask, while other tools have configurable permission behavior. Sources: claude:cl-m365, claude:cl-mcp. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: claude:cl-pricing, claude:cl-mcp, claude:cl-m365 ### AGT-03: Web search and deep research Judgment rule: Record web search on/off control per organisation and group, search provider, citation of web sources, deep or multi-step research, and whether queries leave the residency boundary. Admins of regulated companies often need web search off. #### ChatGPT Business / Enterprise Verification status: Agent cross-checked (agent-cross-checked) Support: partial Search, research and source links exist; external-provider and residency boundaries remain relevant. Availability: generally-available Delivery: native Scope: surfaces=ChatGPT Business and Enterprise web workspaces, ChatGPT desktop and mobile clients, ChatGPT connected apps and custom MCP apps; version=Continuously updated hosted service, retrieved 2026-10-21; plan=ChatGPT Business Standard/Premium versus Enterprise; Edu only where explicitly named for eligibility differences; add_ons=Purchased workspace credits or contracted token billing where stated, External app/provider subscriptions and Microsoft add-in approval where required, Enterprise residency, EKM and compliance entitlements only where stated; deployment_mode=multi-tenant-saas; region=Supported commercial regions; Europe means EEA + Switzerland when explicitly configured; app/client availability varies; os=not specified. Limitations: - Read each atomic answer for its plan, access and feature limits. - web_search — Is web search available? [supported]: Search is available on Business, Enterprise and Edu when permitted. Sources: chatgpt:oa-search. - admin_toggle — Can admins disable it per organisation or group? [partial]: Managed workspaces apply role/search controls; full Business-versus-Enterprise group policy was not verified. Sources: chatgpt:oa-search. - search_provider — Which search provider handles queries, and where? [partial]: Rewritten queries/general location can reach external search providers; external integrations are outside the ChatGPT residency guarantee. Sources: chatgpt:oa-search, chatgpt:oa-residency. - deep_research — Is multi-step research with a report available? [supported]: Business and Enterprise include Deep Research; shared-report outcomes were not tested. Sources: chatgpt:oa-business, chatgpt:oa-models. - web_citations — Are web sources cited? [supported]: Search responses provide source links/citations, with vendor warnings about correctness. Sources: chatgpt:oa-search. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: chatgpt:oa-search, chatgpt:oa-residency, chatgpt:oa-business, chatgpt:oa-models #### Claude Team / Enterprise Verification status: Agent cross-checked (agent-cross-checked) Support: partial Web search and Research are offered; detailed search-provider geography and group policy remain open. Availability: generally-available Delivery: native Scope: surfaces=Claude Team and Enterprise web workspaces, Claude desktop and mobile clients, Claude connectors and remote MCP integrations, Claude for Microsoft 365 official add-ins, Claude Cowork cloud and desktop task execution; version=Continuously updated commercial service, retrieved 2026-10-21; plan=Claude Team Standard/Premium versus current usage-based Enterprise; legacy Enterprise only when explicitly named; add_ons=Enterprise token usage at API rates, Optional US-only inference surcharge, External provider/app subscriptions and Office deployment approval where applicable, CMEK and compliance only on eligible Enterprise configurations; deployment_mode=multi-tenant-saas; region=Commercial supported regions; default global inference and US storage where documented; no EU/Swiss-only residency assumption; os=not specified. Limitations: - search_provider: Which search provider handles queries, and where? Unverified after checking commercial plan comparison, connector and release docs; current search provider, query location, web-specific citation behavior and full admin toggle matrix not established. Search on 2026-10-26: https://claude.com/pricing, https://support.claude.com/en/articles/13345190-get-started-with-claude-cowork, https://support.claude.com/en/articles/10684626-enable-and-use-web-search. No additional scoped evidence established this answer. - web_search — Is web search available? [supported]: Commercial plans include web search. Sources: claude:cl-pricing-20261026. - admin_toggle — Can admins disable it per organisation or group? [supported]: An Owner or Primary Owner enables web search for the Team/Enterprise workspace under Organization settings > Capabilities. Members then enable it in chat; the new unified experience can invoke search without a per-chat toggle. Sources: claude:claude:web-search-controls-20261026. - search_provider — Which search provider handles queries, and where? [unknown]: Which search provider handles queries, and where? Unverified after checking commercial plan comparison, connector and release docs; current search provider, query location, web-specific citation behavior and full admin toggle matrix not established. Search on 2026-10-26: https://claude.com/pricing, https://support.claude.com/en/articles/13345190-get-started-with-claude-cowork, https://support.claude.com/en/articles/10684626-enable-and-use-web-search. No additional scoped evidence established this answer. - deep_research — Is multi-step research with a report available? [supported]: Commercial plans list Research; no shared-corpus report was run. Sources: claude:cl-pricing-20261026. - web_citations — Are web sources cited? [supported]: The web-search guide documents direct citations and links to the sources used in searched answers. Citation correctness was not fixture-tested. Sources: claude:claude:web-search-controls-20261026. Checked 2026-10-26; agent cross-checked 2026-10-26; check again by 2026-12-20. Sources: claude:cl-pricing-20261026, claude:claude:web-search-controls-20261026 ### AGT-04: Workflows and automation Judgment rule: Record no-code or low-code workflows, scheduled prompts, triggers from email, forms or business systems, and multi-step chains. Name where they run and who can build them. A shared prompt template is not a workflow. #### ChatGPT Business / Enterprise Verification status: Agent cross-checked (agent-cross-checked) Support: partial Business/Enterprise team tasks support cloud schedules and app events. Availability: generally-available Delivery: native Scope: surfaces=ChatGPT Work and team tasks, distinct from regular Chat and coding-only Codex; version=Continuously updated hosted service, retrieved 2026-10-21; plan=Business and Enterprise team tasks, subject to workspace permissions; add_ons=Purchased workspace credits or contracted token billing where stated, External app/provider subscriptions and Microsoft add-in approval where required, Enterprise residency, EKM and compliance entitlements only where stated; deployment_mode=multi-tenant-saas; region=Supported commercial regions; Europe means EEA + Switzerland when explicitly configured; app/client availability varies; os=not specified. Limitations: - No event-trigger or multi-step fixture was run. - workflow_builder — Is there a workflow or chain builder? [supported]: Workspace Agents/team tasks use saved instructions, plugins and approved connections. Sources: chatgpt:oa-team-tasks. - scheduled_tasks — Can prompts or assistants run on a schedule? [supported]: Team tasks run on recurring schedules or one-time dates even while clients are closed. Sources: chatgpt:oa-team-tasks. - event_triggers — Can external events start a workflow? [supported]: Supported Gmail/Slack events can start a task under configured permissions. Sources: chatgpt:oa-team-tasks. - builder_audience — Is building aimed at business users, IT or developers? [supported]: Authorized members configure task instructions/triggers; admins and team owners manage connections. Sources: chatgpt:oa-team-tasks. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: chatgpt:oa-team-tasks #### Claude Team / Enterprise Verification status: Agent cross-checked (agent-cross-checked) Support: partial Cowork documents scheduled multi-step tasks; external-event triggers remain unverified. Availability: beta Delivery: native Scope: surfaces=Claude Cowork cloud and desktop task execution; version=Continuously updated commercial service, retrieved 2026-10-21; plan=Team and Enterprise Cowork; cloud execution in beta; add_ons=Enterprise token usage at API rates, Optional US-only inference surcharge, External provider/app subscriptions and Office deployment approval where applicable, CMEK and compliance only on eligible Enterprise configurations; deployment_mode=multi-tenant-saas; region=Commercial supported regions; default global inference and US storage where documented; no EU/Swiss-only residency assumption; os=not specified. Limitations: - Unverified parts: event_triggers. - Read each atomic answer for its plan, access and feature limits. - workflow_builder — Is there a workflow or chain builder? [partial]: Cowork turns outcome instructions into multi-step tasks and reusable scheduled work; a separate no-code graph builder was not verified. Sources: claude:cl-cowork. - scheduled_tasks — Can prompts or assistants run on a schedule? [partial]: Scheduled Cowork tasks run in the cloud with no device online, subject to commercial beta and admin access. Sources: claude:cl-cowork. - event_triggers — Can external events start a workflow? [unknown]: Can external events start a workflow? Unverified after checking Cowork task/schedule and connector docs; no external-event trigger contract or event fixture. - builder_audience — Is building aimed at business users, IT or developers? [supported]: Cowork is aimed at knowledge work with no terminal required. Sources: claude:cl-cowork. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: claude:cl-cowork ### AGT-05: Agentic task execution Judgment rule: Record an agent mode that plans and carries out multi-step tasks with tools (browser, files, connectors), with visible steps, user confirmation of side effects and stop control. Run one fixture task (gather three documents, draft a summary, propose an email). Record interventions and what ran. A final claim of success is not proof. #### ChatGPT Business / Enterprise Verification status: Agent cross-checked (agent-cross-checked) Support: partial ChatGPT Work is the current multi-step task experience; legacy agent limits are historical. Availability: generally-available Delivery: native Scope: surfaces=ChatGPT Work and team tasks, distinct from regular Chat and coding-only Codex; version=Continuously updated hosted service, retrieved 2026-10-21; plan=Eligible Business and Enterprise Work access; add_ons=Purchased workspace credits or contracted token billing where stated, External app/provider subscriptions and Microsoft add-in approval where required, Enterprise residency, EKM and compliance entitlements only where stated; deployment_mode=multi-tenant-saas; region=Supported commercial regions; Europe means EEA + Switzerland when explicitly configured; app/client availability varies; os=not specified. Limitations: - Reconciliation: the legacy agent page's current Overview explicitly says it is unavailable and directs users to Work. The older body's plan list/40-request quotas describe the retired experience and are excluded from this Work finding. - Current Work is the sole source for positive execution/approval behavior; no gather-three-documents/draft-email fixture was run. - agent_mode — Is there an agent mode for multi-step tasks? [supported]: Current Work documentation describes longer multi-step tasks and finished document/spreadsheet/presentation deliverables on eligible paid workspaces. Sources: chatgpt:oa-work-r2. - visible_steps — Are steps and tool calls shown? [partial]: Work documents reviewing progress and directing task execution; full tool-step visibility was not observed. Sources: chatgpt:oa-work-r2. - side_effect_confirmation — Must the user confirm actions with side effects? [partial]: Work uses applicable permissions and approval requirements; precise app-by-app side-effect confirmations were not fixture-tested. Sources: chatgpt:oa-work-r2. - stop_control — Can the user stop a running task? [unknown]: A concrete stop-control workflow for a running Work task was not established from current Work documentation; no running-task fixture was executed. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: chatgpt:oa-work-r2 #### Claude Team / Enterprise Verification status: Agent cross-checked (agent-cross-checked) Support: partial Cowork documents multi-step execution; broad action and stop-control behavior remains untested. Availability: beta Delivery: native Scope: surfaces=Claude Cowork cloud and desktop task execution, Claude connectors and remote MCP integrations; version=Continuously updated commercial service, retrieved 2026-10-21; plan=Team/Enterprise Cowork; cloud beta where stated; add_ons=Enterprise token usage at API rates, Optional US-only inference surcharge, External provider/app subscriptions and Office deployment approval where applicable, CMEK and compliance only on eligible Enterprise configurations; deployment_mode=multi-tenant-saas; region=Commercial supported regions; default global inference and US storage where documented; no EU/Swiss-only residency assumption; os=not specified. Limitations: - visible_steps: The documented task flow includes planning and subtasks; complete tool-step visibility was not independently observed. - side_effect_confirmation: Microsoft connector has required confirmations for specified email/calendar/Teams actions; this does not establish mandatory confirmation for every Cowork side effect. - stop_control: The paid-plan Cowork safety guide documents user stopping/monitoring of tasks. It does not guarantee that stopping reverses a completed write or cancels every submitted external action. - agent_mode — Is there an agent mode for multi-step tasks? [supported]: Paid Cowork plans and executes multi-step tasks with code, files and browser access where permitted. Sources: claude:cl-cowork-20261026. - visible_steps — Are steps and tool calls shown? [partial]: The documented task flow includes planning and subtasks; complete tool-step visibility was not independently observed. Sources: claude:cl-cowork-20261026. - side_effect_confirmation — Must the user confirm actions with side effects? [partial]: Microsoft connector has required confirmations for specified email/calendar/Teams actions; this does not establish mandatory confirmation for every Cowork side effect. Sources: claude:cl-m365-20261026. - stop_control — Can the user stop a running task? [partial]: The paid-plan Cowork safety guide documents user stopping/monitoring of tasks. It does not guarantee that stopping reverses a completed write or cancels every submitted external action. Sources: claude:claude:cowork-stop-20261026, claude:cl-cowork-20261026. Checked 2026-10-26; agent cross-checked 2026-10-26; check again by 2026-12-20. Sources: claude:cl-cowork-20261026, claude:cl-m365-20261026, claude:claude:cowork-stop-20261026 ### AGT-06: Programmable access Judgment rule: Record a public API for chat, assistants and knowledge, SDKs, API authentication, rate limits and whether API use counts against the same governance (audit, budgets, model restrictions). Being an MCP client is different from exposing the product over MCP. #### ChatGPT Business / Enterprise Verification status: Agent cross-checked (agent-cross-checked) Support: partial The separate API platform is distinct from the governed ChatGPT workspace. Availability: generally-available Delivery: native Scope: surfaces=ChatGPT Business and Enterprise web workspaces, ChatGPT desktop and mobile clients, ChatGPT connected apps and custom MCP apps; version=Continuously updated hosted service, retrieved 2026-10-21; plan=ChatGPT Business Standard/Premium versus Enterprise; Edu only where explicitly named for eligibility differences; add_ons=Purchased workspace credits or contracted token billing where stated, External app/provider subscriptions and Microsoft add-in approval where required, Enterprise residency, EKM and compliance entitlements only where stated; deployment_mode=multi-tenant-saas; region=Supported commercial regions; Europe means EEA + Switzerland when explicitly configured; app/client availability varies; os=not specified. Limitations: - Unverified parts: knowledge_api, mcp_server. - Read each atomic answer for its plan, access and feature limits. - chat_api — Is there an API for chat and assistants? [partial]: API usage is separate from Business subscription billing. A supported API for the same ChatGPT workspace conversations/assistants was not established. Sources: chatgpt:oa-business-faq. - knowledge_api — Can documents be loaded through an API? [unknown]: Can documents be loaded through an API? Unverified after checking Business/API separation and Compliance Platform docs; no general ChatGPT knowledge-ingestion API or product MCP-server contract verified. - api_governance — Do audit, budgets and model rules apply to API use? [partial]: API credits/rate limits do not transfer to Business workspace allowances; unified audit/budget/model policy was not established. Sources: chatgpt:oa-business-faq. - mcp_server — Does the product expose itself to other agents over MCP? [unknown]: Does the product expose itself to other agents over MCP? Unverified after checking Business/API separation and Compliance Platform docs; no general ChatGPT knowledge-ingestion API or product MCP-server contract verified. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: chatgpt:oa-business-faq #### Claude Team / Enterprise Verification status: Agent cross-checked (agent-cross-checked) Support: partial A public model API and separate compliance/analytics interfaces exist; workspace feature parity is unverified. Availability: generally-available Delivery: native Scope: surfaces=Claude Team and Enterprise web workspaces, Claude desktop and mobile clients, Claude connectors and remote MCP integrations, Claude for Microsoft 365 official add-ins, Claude Cowork cloud and desktop task execution; version=Continuously updated commercial service, retrieved 2026-10-21; plan=Claude Team Standard/Premium versus current usage-based Enterprise; legacy Enterprise only when explicitly named; add_ons=Enterprise token usage at API rates, Optional US-only inference surcharge, External provider/app subscriptions and Office deployment approval where applicable, CMEK and compliance only on eligible Enterprise configurations; deployment_mode=multi-tenant-saas; region=Commercial supported regions; default global inference and US storage where documented; no EU/Swiss-only residency assumption; os=not specified. Limitations: - Unverified parts: knowledge_api, mcp_server. - Read each atomic answer for its plan, access and feature limits. - chat_api — Is there an API for chat and assistants? [partial]: Claude Platform has a public separately priced model API; this does not establish API access to the same Claude Team/Enterprise assistant conversations. Sources: claude:cl-api-prices. - knowledge_api — Can documents be loaded through an API? [unknown]: Can documents be loaded through an API? Unverified after checking Claude Platform pricing and commercial Compliance API docs; workspace knowledge ingestion and product MCP-server exposure not verified. - api_governance — Do audit, budgets and model rules apply to API use? [partial]: Enterprise Compliance API covers eligible deployments; automatic parity of model, budget and audit policy with separately purchased API usage was not established. Sources: claude:cl-compliance. - mcp_server — Does the product expose itself to other agents over MCP? [unknown]: Does the product expose itself to other agents over MCP? Unverified after checking Claude Platform pricing and commercial Compliance API docs; workspace knowledge ingestion and product MCP-server exposure not verified. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: claude:cl-api-prices, claude:cl-compliance ## Daily work ### WORK-01: Clients and access points Judgment rule: List web, desktop (Windows, macOS), iOS, Android, mobile browser and browser extension separately. For each, record login with company SSO, feature gaps against web, and MDM/Intune deployability. An installable app is different from a mobile website. #### ChatGPT Business / Enterprise Verification status: Agent cross-checked (agent-cross-checked) Support: partial Web, mobile and desktop clients exist, with plan-specific managed deployment. Availability: generally-available Delivery: native Scope: surfaces=ChatGPT Business and Enterprise web workspaces, ChatGPT desktop and mobile clients, ChatGPT connected apps and custom MCP apps; version=Continuously updated hosted service, retrieved 2026-10-21; plan=ChatGPT Business Standard/Premium versus Enterprise; Edu only where explicitly named for eligibility differences; add_ons=Purchased workspace credits or contracted token billing where stated, External app/provider subscriptions and Microsoft add-in approval where required, Enterprise residency, EKM and compliance entitlements only where stated; deployment_mode=multi-tenant-saas; region=Supported commercial regions; Europe means EEA + Switzerland when explicitly configured; app/client availability varies; os=not specified. Limitations: - Read each atomic answer for its plan, access and feature limits. - web — Is a full web client available? [supported]: ChatGPT and Company Knowledge have web interfaces. Sources: chatgpt:oa-company. - desktop_apps — Windows and macOS apps? [supported]: The current ChatGPT desktop app supports macOS and Windows. Sources: chatgpt:oa-work. - mobile_apps — iOS and Android apps with SSO? [partial]: Business is available on iPhone/Android; enterprise SSO app login was not trialled. Sources: chatgpt:oa-business-faq. - browser_extension — Is there a browser extension or sidebar? [supported]: An official Chrome extension sets ChatGPT as the address-bar search destination. Sources: chatgpt:oa-search. - managed_deployment — Can IT deploy and configure clients through MDM? [partial]: Enterprise-only ChatGPT for Intune on iOS/iPadOS requires organizational onboarding; it supports Intune protection and Entra Conditional Access. Sources: chatgpt:oa-enterprise-notes. - client_feature_gaps — Which features are missing on mobile? [partial]: Developer-mode MCP apps are documented as web-only; other tool/client gaps vary by feature. Sources: chatgpt:oa-mcp. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: chatgpt:oa-company, chatgpt:oa-work, chatgpt:oa-business-faq, chatgpt:oa-search, chatgpt:oa-enterprise-notes, chatgpt:oa-mcp #### Claude Team / Enterprise Verification status: Agent cross-checked (agent-cross-checked) Support: partial Web, native clients and Chrome access are documented, with distinct admin and beta eligibility. Availability: generally-available Delivery: native Scope: surfaces=Claude Team and Enterprise web workspaces, Claude desktop and mobile clients, Claude connectors and remote MCP integrations, Claude for Microsoft 365 official add-ins, Claude Cowork cloud and desktop task execution; version=Continuously updated commercial service, retrieved 2026-10-21; plan=Claude Team Standard/Premium versus current usage-based Enterprise; legacy Enterprise only when explicitly named; add_ons=Enterprise token usage at API rates, Optional US-only inference surcharge, External provider/app subscriptions and Office deployment approval where applicable, CMEK and compliance only on eligible Enterprise configurations; deployment_mode=multi-tenant-saas; region=Commercial supported regions; default global inference and US storage where documented; no EU/Swiss-only residency assumption; os=not specified. Limitations: - Read each atomic answer for its plan, access and feature limits. - web — Is a full web client available? [supported]: Commercial Claude is available on the web. Sources: claude:cl-enterprise. - desktop_apps — Windows and macOS apps? [supported]: Cowork supports macOS and Windows desktop clients on paid plans. Sources: claude:cl-cowork. - mobile_apps — iOS and Android apps with SSO? [partial]: iOS/Android clients support commercial accounts; SSO mobile login was not tested. Sources: claude:cl-cowork, claude:cl-m365-user. - browser_extension — Is there a browser extension or sidebar? [partial]: Claude in Chrome is available with plan/Enterprise admin eligibility. Sources: claude:cl-cowork. - managed_deployment — Can IT deploy and configure clients through MDM? [partial]: Team and Enterprise plan comparisons list enterprise desktop deployment; exact MDM packages/policies were not reviewed. Sources: claude:cl-pricing. - client_feature_gaps — Which features are missing on mobile? [partial]: Exports require web/Desktop; cloud Cowork rollout and admin enablement differ from local desktop execution. Sources: claude:cl-export-user, claude:cl-cowork. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: claude:cl-enterprise, claude:cl-cowork, claude:cl-m365-user, claude:cl-pricing, claude:cl-export-user ### WORK-02: Office suite and Teams integration Judgment rule: Record presence inside Word, Excel, PowerPoint, Outlook and Teams (and Google Docs, Gmail), with what the assistant can do in each: read the open document, write into it, act on mail. Record extra licences and admin consent needed. A connector that searches Office files is KNOW-03, not WORK-02. #### ChatGPT Business / Enterprise Verification status: Agent cross-checked (agent-cross-checked) Support: partial Official Office/Sheets add-ins and an Enterprise Teams entry point are documented. Availability: generally-available Delivery: native Scope: surfaces=Official Microsoft Office and Google Sheets add-ins where stated, ChatGPT connected apps and custom MCP apps; version=Continuously updated hosted service, retrieved 2026-10-21; plan=Business Office/Sheets; Enterprise @ChatGPT Teams where explicitly stated; add_ons=Purchased workspace credits or contracted token billing where stated, External app/provider subscriptions and Microsoft add-in approval where required, Enterprise residency, EKM and compliance entitlements only where stated; deployment_mode=multi-tenant-saas; region=Supported commercial regions; Europe means EEA + Switzerland when explicitly configured; app/client availability varies; os=not specified. Limitations: - Read each atomic answer for its plan, access and feature limits. - word_excel_powerpoint — Does it work inside Word, Excel and PowerPoint? [supported]: Word uses the same Microsoft add-in as Excel and PowerPoint; Word reads/edits the open document with formatting limits. Sources: chatgpt:oa-word. - outlook — Does it work inside Outlook? [partial]: An Outlook connected app is documented; a native Outlook add-in was not established. Sources: chatgpt:oa-enterprise-notes. - teams — Is there a Teams app or bot? [supported]: Enterprise @ChatGPT in Microsoft Teams can receive DMs/channel mentions after admin setup. Sources: chatgpt:oa-enterprise-notes. - google_workspace_apps — Does it work inside Docs, Sheets or Gmail? [partial]: Business release notes document the native Google Sheets sidebar; Docs and Gmail-native assistant UI were not verified. Sources: chatgpt:oa-business-notes. - licence_prerequisites — Which licences or consents are needed? [supported]: Microsoft admins must allow the add-in and ChatGPT admins manage access; applicable token/credit allowances apply. Sources: chatgpt:oa-word. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: chatgpt:oa-word, chatgpt:oa-enterprise-notes, chatgpt:oa-business-notes #### Claude Team / Enterprise Verification status: Agent cross-checked (agent-cross-checked) Support: partial Native Microsoft add-ins and a separate Google Workspace beta have different approval and data paths. Availability: generally-available Delivery: native Scope: surfaces=Claude for Microsoft 365 official add-ins, Claude connectors and remote MCP integrations, Claude native Google Workspace sidebar beta; version=Continuously updated commercial service, retrieved 2026-10-21; plan=Team/Enterprise Office; Outlook beta; Google Workspace native beta; add_ons=Microsoft/Google subscriptions and administrator deployment approval where required; deployment_mode=multi-tenant-saas; region=Commercial supported regions; default global inference and US storage where documented; no EU/Swiss-only residency assumption; os=not specified. Limitations: - No deployment or native-edit fixture. Google extension retains its own local per-file history and does not inherit custom organization retention. - word_excel_powerpoint — Does it work inside Word, Excel and PowerPoint? [supported]: Claude advertises native Excel/PowerPoint/Word add-ins as generally available on paid plans. Sources: claude:cl-office. - outlook — Does it work inside Outlook? [supported]: Outlook add-in is beta and opens drafts in the native composer for user sending. Sources: claude:cl-office. - teams — Is there a Teams app or bot? [partial]: Teams read/write is through the separate Microsoft connector; a native Teams app was not established. Sources: claude:cl-m365. - google_workspace_apps — Does it work inside Docs, Sheets or Gmail? [supported]: Native Google Docs/Sheets/Slides sidebar is beta for Team/Enterprise, installed via Google Marketplace. It edits the open file under the user identity with ask-before-edits by default; connectors are a separate feature. Sources: claude:cl-google-addon. - licence_prerequisites — Which licences or consents are needed? [partial]: Paid Claude or supported cloud credentials are advertised for Office; Google add-in needs a paid supported plan and Marketplace approval. Microsoft source connector needs work-account/Entra consent. Sources: claude:cl-office, claude:cl-google-addon, claude:cl-m365-user. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: claude:cl-office, claude:cl-m365, claude:cl-google-addon, claude:cl-m365-user ### WORK-03: Translation and writing Judgment rule: Record document translation preserving layout, the translation engine (LLM or dedicated such as DeepL), glossaries, formality control, supported languages including Swiss German conventions (no ß), and rewriting/proofreading tools. Translate the shared German contract into French and Italian and record layout and glossary results. #### ChatGPT Business / Enterprise Verification status: Agent cross-checked (agent-cross-checked) Support: partial Document rewriting is documented; translation layout, glossaries and Swiss variants remain untested. Availability: generally-available Delivery: native Scope: surfaces=Official Microsoft Office and Google Sheets add-ins where stated; version=Continuously updated hosted service, retrieved 2026-10-21; plan=ChatGPT for Word native add-in under Business/Enterprise/Edu workspace controls; availability guide says all ChatGPT plans; add_ons=Microsoft Word and administrator-approved ChatGPT Microsoft add-in, Applicable usage allowance/credits and workspace feature access; deployment_mode=multi-tenant-saas; region=Supported commercial regions; Europe means EEA + Switzerland when explicitly configured; app/client availability varies; os=not specified. Limitations: - This positive writing finding concerns the native Word add-in, not every chat/client surface. - Translation layout, terminology/glossary behavior and Swiss variants remain untested. - document_translation — Can whole documents be translated with formatting kept? [unknown]: Can whole documents be translated with formatting kept? Unverified after checking Word, upload and language docs; no DE-to-FR/IT contract translation, terminology or de-CH fixture. - translation_engine — Which engine translates? [unknown]: Which engine translates? Unverified after checking Word, upload and language docs; no DE-to-FR/IT contract translation, terminology or de-CH fixture. - glossaries — Are company glossaries supported? [unknown]: Are company glossaries supported? Unverified after checking Word, upload and language docs; no DE-to-FR/IT contract translation, terminology or de-CH fixture. - formality_and_variants — Can formality and regional variants (de-CH) be set? [unknown]: Can formality and regional variants (de-CH) be set? Unverified after checking Word, upload and language docs; no DE-to-FR/IT contract translation, terminology or de-CH fixture. - writing_tools — Are dedicated rewrite and proofreading tools available? [partial]: Native ChatGPT for Word drafts, revises, reorganizes and checks clarity/terminology in the open document. Complex formatting/tables/charts can need manual adjustments. Sources: chatgpt:oa-word-r2. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: chatgpt:oa-word-r2 #### Claude Team / Enterprise Verification status: Agent cross-checked (agent-cross-checked) Support: partial Office rewriting/review is documented; translation fidelity and glossary controls remain unverified. Availability: generally-available Delivery: native Scope: surfaces=Claude Team and Enterprise web workspaces, Claude desktop and mobile clients, Claude connectors and remote MCP integrations, Claude for Microsoft 365 official add-ins, Claude Cowork cloud and desktop task execution; version=Continuously updated commercial service, retrieved 2026-10-21; plan=Claude Team Standard/Premium versus current usage-based Enterprise; legacy Enterprise only when explicitly named; add_ons=Enterprise token usage at API rates, Optional US-only inference surcharge, External provider/app subscriptions and Office deployment approval where applicable, CMEK and compliance only on eligible Enterprise configurations; deployment_mode=multi-tenant-saas; region=Commercial supported regions; default global inference and US storage where documented; no EU/Swiss-only residency assumption; os=not specified. Limitations: - Unverified parts: document_translation, translation_engine, glossaries, formality_and_variants. - Read each atomic answer for its plan, access and feature limits. - document_translation — Can whole documents be translated with formatting kept? [unknown]: Can whole documents be translated with formatting kept? Unverified after checking Office and project-instruction docs; layout-preserving DE-to-FR/IT translation, dedicated engine, glossary and Swiss-language controls not established. - translation_engine — Which engine translates? [unknown]: Which engine translates? Unverified after checking Office and project-instruction docs; layout-preserving DE-to-FR/IT translation, dedicated engine, glossary and Swiss-language controls not established. - glossaries — Are company glossaries supported? [unknown]: Are company glossaries supported? Unverified after checking Office and project-instruction docs; layout-preserving DE-to-FR/IT translation, dedicated engine, glossary and Swiss-language controls not established. - formality_and_variants — Can formality and regional variants (de-CH) be set? [unknown]: Can formality and regional variants (de-CH) be set? Unverified after checking Office and project-instruction docs; layout-preserving DE-to-FR/IT translation, dedicated engine, glossary and Swiss-language controls not established. - writing_tools — Are dedicated rewrite and proofreading tools available? [partial]: Word add-in advertises tracked revisions, comments and company styles; no proofreading/translation fixture was run. Sources: claude:cl-office. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: claude:cl-office ### WORK-04: Image generation and editing Judgment rule: Record available image models, editing (inpainting, reference images), admin control and per-image cost visibility, and licence or usage terms for generated images. #### ChatGPT Business / Enterprise Verification status: Agent cross-checked (agent-cross-checked) Support: partial Native ChatGPT Images supports editing uploaded images; administrator restrictions remain a named gap. Availability: generally-available Delivery: native Scope: surfaces=ChatGPT Business and Enterprise web workspaces, ChatGPT desktop and mobile clients; version=Continuously updated hosted service, retrieved 2026-10-21; plan=ChatGPT Enterprise native image generation; output rights under the business Services Agreement; add_ons=Purchased workspace credits or contracted token billing where stated, External app/provider subscriptions and Microsoft add-in approval where required, Enterprise residency, EKM and compliance entitlements only where stated; deployment_mode=multi-tenant-saas; region=Supported commercial regions; Europe means EEA + Switzerland when explicitly configured; app/client availability varies; os=not specified. Limitations: - image_generation: Enterprise's current native-tool inventory includes image generation; exact image-model naming and individual client/group entitlement were not verified. - admin_control: Can admins restrict image generation? Unverified after checking current model/tool inventory and Services Agreement; image editing, group controls and per-image rates not verified. Search on 2026-10-26: https://help.openai.com/en/articles/11165333-chatgpt-enterprise-and-edu-models-and-limits, https://openai.com/policies/services-agreement/, https://help.openai.com/en/articles/8555545-uploading-files-and-audio-to-chatgpt. No additional scoped evidence established this answer. - usage_terms: The business agreement assigns output rights to the customer to the extent permitted by law, with customer responsibility for use. - image_generation — Can users generate images, with which models? [partial]: Enterprise's current native-tool inventory includes image generation; exact image-model naming and individual client/group entitlement were not verified. Sources: chatgpt:oa-enterprise-models-r2-20261026. - image_editing — Can users edit uploaded images? [supported]: Users can upload an existing image and request edits or edit a generated image with text or the selection editor. The guide says Images is available on all tiers; the separate Images with thinking mode is not yet asserted for Enterprise/Edu. Sources: chatgpt:chatgpt:images-editing-20261026. - admin_control — Can admins restrict image generation? [unknown]: Can admins restrict image generation? Unverified after checking current model/tool inventory and Services Agreement; image editing, group controls and per-image rates not verified. Search on 2026-10-26: https://help.openai.com/en/articles/11165333-chatgpt-enterprise-and-edu-models-and-limits, https://openai.com/policies/services-agreement/, https://help.openai.com/en/articles/8555545-uploading-files-and-audio-to-chatgpt. No additional scoped evidence established this answer. - usage_terms — What usage rights apply to output? [partial]: The business agreement assigns output rights to the customer to the extent permitted by law, with customer responsibility for use. Sources: chatgpt:oa-services-20261026. Checked 2026-10-26; agent cross-checked 2026-10-26; check again by 2026-12-20. Sources: chatgpt:oa-enterprise-models-r2-20261026, chatgpt:oa-services-20261026, chatgpt:chatgpt:images-editing-20261026 #### Claude Team / Enterprise Verification status: Agent cross-checked (agent-cross-checked) Support: partial Claude explicitly excludes native photo/illustration generation; HTML/SVG visuals and uploaded-image analysis are separate capabilities. Availability: unknown Delivery: unknown Scope: surfaces=Claude Team and Enterprise web workspaces, Claude desktop and mobile clients; version=Public help checked 2026-10-26; plan=Team/Enterprise native Claude web and desktop; third-party image tools excluded; add_ons=none stated; deployment_mode=multi-tenant-saas; region=Supported commercial regions; os=not specified. Limitations: - image_editing: Can users edit uploaded images? Unverified after checking Claude pricing, artifacts and code/file-creation docs; design/artifact creation does not establish a native raster image model, uploaded-image editing, per-image controls or image-specific licence terms. Search on 2026-10-26: https://support.claude.com/en/articles/9002504-can-claude-produce-images, https://support.claude.com/en/articles/12111783-create-and-edit-files-with-claude, https://support.claude.com/en/articles/10769299-how-to-use-claude-in-your-preferred-language. No additional scoped evidence established this answer. - admin_control: Can admins restrict image generation? Unverified after checking Claude pricing, artifacts and code/file-creation docs; design/artifact creation does not establish a native raster image model, uploaded-image editing, per-image controls or image-specific licence terms. Search on 2026-10-26: https://support.claude.com/en/articles/9002504-can-claude-produce-images, https://support.claude.com/en/articles/12111783-create-and-edit-files-with-claude, https://support.claude.com/en/articles/10769299-how-to-use-claude-in-your-preferred-language. No additional scoped evidence established this answer. - usage_terms: What usage rights apply to output? Unverified after checking Claude pricing, artifacts and code/file-creation docs; design/artifact creation does not establish a native raster image model, uploaded-image editing, per-image controls or image-specific licence terms. Search on 2026-10-26: https://support.claude.com/en/articles/9002504-can-claude-produce-images, https://support.claude.com/en/articles/12111783-create-and-edit-files-with-claude, https://support.claude.com/en/articles/10769299-how-to-use-claude-in-your-preferred-language. No additional scoped evidence established this answer. - image_generation — Can users generate images, with which models? [unsupported]: The official image FAQ explicitly says Claude does not generate photos or illustrations like dedicated image-generation tools. Its beta HTML/SVG diagrams/charts are not a native raster image-generation model. Sources: claude:claude:image-generation-boundary-20261026. - image_editing — Can users edit uploaded images? [unknown]: Can users edit uploaded images? Unverified after checking Claude pricing, artifacts and code/file-creation docs; design/artifact creation does not establish a native raster image model, uploaded-image editing, per-image controls or image-specific licence terms. Search on 2026-10-26: https://support.claude.com/en/articles/9002504-can-claude-produce-images, https://support.claude.com/en/articles/12111783-create-and-edit-files-with-claude, https://support.claude.com/en/articles/10769299-how-to-use-claude-in-your-preferred-language. No additional scoped evidence established this answer. - admin_control — Can admins restrict image generation? [unknown]: Can admins restrict image generation? Unverified after checking Claude pricing, artifacts and code/file-creation docs; design/artifact creation does not establish a native raster image model, uploaded-image editing, per-image controls or image-specific licence terms. Search on 2026-10-26: https://support.claude.com/en/articles/9002504-can-claude-produce-images, https://support.claude.com/en/articles/12111783-create-and-edit-files-with-claude, https://support.claude.com/en/articles/10769299-how-to-use-claude-in-your-preferred-language. No additional scoped evidence established this answer. - usage_terms — What usage rights apply to output? [unknown]: What usage rights apply to output? Unverified after checking Claude pricing, artifacts and code/file-creation docs; design/artifact creation does not establish a native raster image model, uploaded-image editing, per-image controls or image-specific licence terms. Search on 2026-10-26: https://support.claude.com/en/articles/9002504-can-claude-produce-images, https://support.claude.com/en/articles/12111783-create-and-edit-files-with-claude, https://support.claude.com/en/articles/10769299-how-to-use-claude-in-your-preferred-language. No additional scoped evidence established this answer. Checked 2026-10-26; agent cross-checked 2026-10-26; check again by 2026-12-20. Sources: claude:claude:image-generation-boundary-20261026 ### WORK-05: Voice and meetings Judgment rule: Record dictation, read-aloud, live voice conversation, meeting transcription and summarisation, supported languages including Swiss German speech, and where audio is processed. #### ChatGPT Business / Enterprise Verification status: Agent cross-checked (agent-cross-checked) Support: partial Live Voice and recording uploads are documented with seat- and billing-specific rules. Availability: generally-available Delivery: native Scope: surfaces=ChatGPT Business and Enterprise web workspaces, ChatGPT desktop and mobile clients, ChatGPT connected apps and custom MCP apps; version=Continuously updated hosted service, retrieved 2026-10-21; plan=ChatGPT Business Standard/Premium versus Enterprise; Edu only where explicitly named for eligibility differences; add_ons=Purchased workspace credits or contracted token billing where stated, External app/provider subscriptions and Microsoft add-in approval where required, Enterprise residency, EKM and compliance entitlements only where stated; deployment_mode=multi-tenant-saas; region=Supported commercial regions; Europe means EEA + Switzerland when explicitly configured; app/client availability varies; os=not specified. Limitations: - dictation: Voice documentation links a distinct dictation feature; its exact work-account processing path was not separately reviewed. - read_aloud: The iOS/Android FAQ lists Read aloud among response actions, with available actions varying by message. This documents response playback without establishing uniform client/message coverage or a Swiss German quality guarantee. - voice_conversation: Business Standard has 3 hours and Premium 15 hours on a rolling daily window; additional Live use is credit-billed. Enterprise pricing differs by contract. - meeting_summaries: Paid audio uploads can be transcribed and turned into meeting summaries; this does not establish an automatic live meeting bot. - swiss_german_speech: Is Swiss German speech recognised? Unverified after checking Voice and audio-upload documentation; standalone read-aloud and Swiss German recognition not tested. Search on 2026-10-26: https://help.openai.com/en/articles/20001274-chatgpt-voice, https://help.openai.com/en/articles/8555545-uploading-files-and-audio-to-chatgpt, https://help.openai.com/en/articles/8357869-how-to-change-your-language-setting-in-chatgpt. No additional scoped evidence established this answer. - dictation — Can users dictate prompts? [partial]: Voice documentation links a distinct dictation feature; its exact work-account processing path was not separately reviewed. Sources: chatgpt:oa-voice. - read_aloud — Can answers be read aloud? [partial]: The iOS/Android FAQ lists Read aloud among response actions, with available actions varying by message. This documents response playback without establishing uniform client/message coverage or a Swiss German quality guarantee. Sources: chatgpt:chatgpt:mobile-read-aloud-20261026. - voice_conversation — Is a live voice mode available? [partial]: Business Standard has 3 hours and Premium 15 hours on a rolling daily window; additional Live use is credit-billed. Enterprise pricing differs by contract. Sources: chatgpt:oa-voice. - meeting_summaries — Are meetings transcribed and summarised? [partial]: Paid audio uploads can be transcribed and turned into meeting summaries; this does not establish an automatic live meeting bot. Sources: chatgpt:oa-files-20261026. - swiss_german_speech — Is Swiss German speech recognised? [unknown]: Is Swiss German speech recognised? Unverified after checking Voice and audio-upload documentation; standalone read-aloud and Swiss German recognition not tested. Search on 2026-10-26: https://help.openai.com/en/articles/20001274-chatgpt-voice, https://help.openai.com/en/articles/8555545-uploading-files-and-audio-to-chatgpt, https://help.openai.com/en/articles/8357869-how-to-change-your-language-setting-in-chatgpt. No additional scoped evidence established this answer. Checked 2026-10-26; agent cross-checked 2026-10-26; check again by 2026-12-20. Sources: chatgpt:oa-voice, chatgpt:oa-files-20261026, chatgpt:chatgpt:mobile-read-aloud-20261026 #### Claude Team / Enterprise Verification status: Agent cross-checked (agent-cross-checked) Support: partial Voice and Office dictation are listed; meeting and dialect details need evidence. Availability: generally-available Delivery: native Scope: surfaces=Claude Team and Enterprise web workspaces, Claude desktop and mobile clients, Claude connectors and remote MCP integrations, Claude for Microsoft 365 official add-ins, Claude Cowork cloud and desktop task execution; version=Continuously updated commercial service, retrieved 2026-10-21; plan=Claude Team Standard/Premium versus current usage-based Enterprise; legacy Enterprise only when explicitly named; add_ons=Enterprise token usage at API rates, Optional US-only inference surcharge, External provider/app subscriptions and Office deployment approval where applicable, CMEK and compliance only on eligible Enterprise configurations; deployment_mode=multi-tenant-saas; region=Commercial supported regions; default global inference and US storage where documented; no EU/Swiss-only residency assumption; os=not specified. Limitations: - Unverified parts: read_aloud, meeting_summaries, swiss_german_speech. - Read each atomic answer for its plan, access and feature limits. - dictation — Can users dictate prompts? [supported]: Claude for Microsoft 365 advertises dictation in its sidebar. Sources: claude:cl-office. - read_aloud — Can answers be read aloud? [unknown]: Can answers be read aloud? Unverified after checking commercial Voice listing, Office and connector docs; standalone read-aloud, live meeting transcription and Swiss German accuracy not verified. - voice_conversation — Is a live voice mode available? [partial]: Team/Enterprise feature comparison lists Voice mode; exact client/language/audio-processing scope was not fully verified. Sources: claude:cl-pricing. - meeting_summaries — Are meetings transcribed and summarised? [unknown]: Are meetings transcribed and summarised? Unverified after checking commercial Voice listing, Office and connector docs; standalone read-aloud, live meeting transcription and Swiss German accuracy not verified. - swiss_german_speech — Is Swiss German speech recognised? [unknown]: Is Swiss German speech recognised? Unverified after checking commercial Voice listing, Office and connector docs; standalone read-aloud, live meeting transcription and Swiss German accuracy not verified. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: claude:cl-office, claude:cl-pricing ### WORK-06: Data analysis and document output Judgment rule: Record code execution for data analysis, charts, and generation of downloadable Word, Excel, PowerPoint and PDF files. Analyse the fixture Excel and request a PowerPoint summary. Record where code runs and whether files are editable. #### ChatGPT Business / Enterprise Verification status: Agent cross-checked (agent-cross-checked) Support: partial Code-backed analysis and generated documents are documented. Availability: generally-available Delivery: native Scope: surfaces=ChatGPT Business and Enterprise web workspaces, ChatGPT desktop and mobile clients, ChatGPT Work and team tasks, distinct from regular Chat and coding-only Codex; version=Continuously updated hosted service, retrieved 2026-10-21; plan=Enterprise Chat analysis/canvas; Business and Enterprise Work deliverables where Work is enabled; add_ons=Purchased workspace credits or contracted token billing where stated, External app/provider subscriptions and Microsoft add-in approval where required, Enterprise residency, EKM and compliance entitlements only where stated; deployment_mode=multi-tenant-saas; region=Supported commercial regions; Europe means EEA + Switzerland when explicitly configured; app/client availability varies; os=not specified. Limitations: - Each atom distinguishes Enterprise Chat tools from Business/Enterprise Work output. Work is explicitly included as a surface. - No formula workbook, downloadable Office/PDF fidelity or canvas-editing fixture was run. - data_analysis — Can it analyse spreadsheets with executed code? [supported]: Enterprise lists data analysis; its documented code path uses a stateful Jupyter/Python environment without external network access. Sources: chatgpt:oa-enterprise-models-r2, chatgpt:oa-analysis-r2. - charts — Can it produce charts? [supported]: For the Enterprise analysis path, the direct guide documents static charts and selected interactive bar/line/pie/scatter charts. Sources: chatgpt:oa-enterprise-models-r2, chatgpt:oa-analysis-r2. - office_file_output — Can it create Word, Excel or PowerPoint files? [partial]: Eligible Business and Enterprise Work creates documents, spreadsheets and presentations. Exact download-format/editability fidelity was not fixture-tested. Sources: chatgpt:oa-work-r2. - canvas_editing — Is there a document or canvas editor for iterating on output? [partial]: Enterprise model/tool inventory lists canvas and Enterprise settings govern role access. This does not establish canvas on every Business seat/client. Sources: chatgpt:oa-enterprise-models-r2, chatgpt:oa-admin-settings. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: chatgpt:oa-enterprise-models-r2, chatgpt:oa-analysis-r2, chatgpt:oa-work-r2, chatgpt:oa-admin-settings #### Claude Team / Enterprise Verification status: Agent cross-checked (agent-cross-checked) Support: partial Enabled Chat code/file tools provide sandboxed analysis and Office/PDF output; Team egress defaults are not established by this finding. Availability: generally-available Delivery: native Scope: surfaces=Claude Team and Enterprise web workspaces, Claude desktop and mobile clients; version=Continuously updated commercial service, retrieved 2026-10-21; plan=Team/Enterprise Chat code execution, file creation and artifact editing where enabled; excludes native Office and Cowork execution defaults; add_ons=Enterprise token usage at API rates, Optional US-only inference surcharge, External provider/app subscriptions and Office deployment approval where applicable, CMEK and compliance only on eligible Enterprise configurations; deployment_mode=multi-tenant-saas; region=Commercial supported regions; default global inference and US storage where documented; no EU/Swiss-only residency assumption; os=not specified. Limitations: - Narrowed to verified file creation/execution. The guide's conflicting Team default is retained as a named configuration gap, not a claim about an enabled tenant. - No formula/PPT/PDF output fixture. Separate enabled MCP routes are not controlled by the code-sandbox egress setting. - data_analysis — Can it analyse spreadsheets with executed code? [supported]: Enabled Chat code/file creation runs code in a sandboxed container and can create Python analysis scripts. This does not establish a particular Team egress default. Sources: claude:cl-code-files-r2. - charts — Can it produce charts? [supported]: The Chat computing path can create PNG data visualizations; native Office add-in charts are outside this narrowed scope. Sources: claude:cl-code-files-r2. - office_file_output — Can it create Word, Excel or PowerPoint files? [supported]: Enabled Chat file creation produces downloadable XLSX/PPTX/DOCX/PDF, subject to the file-tool guide's30 MB upload/download path. Sources: claude:cl-code-files-r2. - canvas_editing — Is there a document or canvas editor for iterating on output? [partial]: Docs/Design/Slides artifact templates support editing; template availability differs by type and plan. Sources: claude:cl-artifacts-admin. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: claude:cl-code-files-r2, claude:cl-artifacts-admin ### WORK-07: Sharing and team spaces Judgment rule: Record chat sharing (link, user, group), shared projects or team spaces, channels or group chat with AI, and commenting. Test sharing a chat with a colleague in another group and record what the recipient sees, including knowledge they lack access to. #### ChatGPT Business / Enterprise Verification status: Agent cross-checked (agent-cross-checked) Support: partial Shared projects and team resources support collaboration with explicit visibility limits. Availability: generally-available Delivery: native Scope: surfaces=ChatGPT Business and Enterprise web workspaces, ChatGPT desktop and mobile clients, ChatGPT connected apps and custom MCP apps; version=Continuously updated hosted service, retrieved 2026-10-21; plan=ChatGPT Business Standard/Premium versus Enterprise; Edu only where explicitly named for eligibility differences; add_ons=Purchased workspace credits or contracted token billing where stated, External app/provider subscriptions and Microsoft add-in approval where required, Enterprise residency, EKM and compliance entitlements only where stated; deployment_mode=multi-tenant-saas; region=Supported commercial regions; Europe means EEA + Switzerland when explicitly configured; app/client availability varies; os=not specified. Limitations: - No cross-group sharing or restricted-source leakage test was performed. - share_chats — Can chats be shared inside the organisation? [supported]: Managed-workspace sharing is controlled by permissions; shared-project chats require project membership. Sources: chatgpt:oa-projects, chatgpt:oa-admin-settings. - team_spaces — Are shared projects or workspaces available? [supported]: Shared projects and Enterprise team Pages/Spaces are documented. Sources: chatgpt:oa-projects, chatgpt:oa-enterprise-notes. - group_chat — Can several people chat together with the AI? [partial]: Shared-project chats support branching rather than synchronous collaboration on the same chat. Enterprise Teams conversations can use @ChatGPT. Sources: chatgpt:oa-projects, chatgpt:oa-enterprise-notes. - share_permission_boundary — Does sharing respect the recipient's access to sources? [partial]: Project members can view/download added files; uploading information into a shared project can expose it to other members. This is different from rechecking original source ACLs. Sources: chatgpt:oa-projects. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: chatgpt:oa-projects, chatgpt:oa-admin-settings, chatgpt:oa-enterprise-notes #### Claude Team / Enterprise Verification status: Agent cross-checked (agent-cross-checked) Support: partial Commercial projects and artifacts support shared work; recipient source boundaries need tests. Availability: generally-available Delivery: native Scope: surfaces=Claude Team and Enterprise web workspaces, Claude desktop and mobile clients, Claude connectors and remote MCP integrations, Claude for Microsoft 365 official add-ins, Claude Cowork cloud and desktop task execution; version=Continuously updated commercial service, retrieved 2026-10-21; plan=Claude Team Standard/Premium versus current usage-based Enterprise; legacy Enterprise only when explicitly named; add_ons=Enterprise token usage at API rates, Optional US-only inference surcharge, External provider/app subscriptions and Office deployment approval where applicable, CMEK and compliance only on eligible Enterprise configurations; deployment_mode=multi-tenant-saas; region=Commercial supported regions; default global inference and US storage where documented; no EU/Swiss-only residency assumption; os=not specified. Limitations: - Unverified parts: group_chat. - Read each atomic answer for its plan, access and feature limits. - share_chats — Can chats be shared inside the organisation? [partial]: Shared project members can see project content and chat within it; a full chat-link audience matrix was not verified. Sources: claude:cl-projects. - team_spaces — Are shared projects or workspaces available? [supported]: Team/Enterprise have shared projects; Enterprise groups receive shared projects/skills/plugins. Sources: claude:cl-projects, claude:cl-groups. - group_chat — Can several people chat together with the AI? [unknown]: Can several people chat together with the AI? Unverified after checking project sharing, group controls and connector security; synchronous group AI chat and cross-group sharing fixture not verified. - share_permission_boundary — Does sharing respect the recipient's access to sources? [partial]: Microsoft connector guide says shared-chat recipients see the response incorporating tool data; original source authorization does not prove recipient-safe output sharing. Sources: claude:cl-m365. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: claude:cl-projects, claude:cl-groups, claude:cl-m365 ### WORK-08: Interface languages and accessibility Judgment rule: Record UI languages, focusing on German, French, Italian and English, with translation quality observed (complete, partial, machine-translated). Record response language handling and WCAG conformance statements. #### ChatGPT Business / Enterprise Verification status: Agent cross-checked (agent-cross-checked) Support: partial German, French and Italian UI settings are documented; quality was not observed. Availability: generally-available Delivery: native Scope: surfaces=ChatGPT Business and Enterprise web workspaces, ChatGPT desktop and mobile clients, ChatGPT connected apps and custom MCP apps; version=Continuously updated hosted service, retrieved 2026-10-21; plan=ChatGPT Business Standard/Premium versus Enterprise; Edu only where explicitly named for eligibility differences; add_ons=Purchased workspace credits or contracted token billing where stated, External app/provider subscriptions and Microsoft add-in approval where required, Enterprise residency, EKM and compliance entitlements only where stated; deployment_mode=multi-tenant-saas; region=Supported commercial regions; Europe means EEA + Switzerland when explicitly configured; app/client availability varies; os=not specified. Limitations: - Unverified parts: dach_language_quality, admin_ui_languages. - Read each atomic answer for its plan, access and feature limits. - ui_languages — Which UI languages are offered? [supported]: Browser and mobile language settings include German, French and Italian. Sources: chatgpt:oa-language. - dach_language_quality — Are German, French and Italian UIs complete and natural? [unknown]: Are German, French and Italian UIs complete and natural? Unverified after checking language settings and Trust Portal; no localized UI/admin inspection or WCAG conformance report download. - accessibility_statement — Is there a WCAG conformance statement? [partial]: The Trust Portal lists a VPAT document; its conformance level, version and scope were not inspected. Sources: chatgpt:oa-trust. - admin_ui_languages — Is the admin interface available in German? [unknown]: Is the admin interface available in German? Unverified after checking language settings and Trust Portal; no localized UI/admin inspection or WCAG conformance report download. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: chatgpt:oa-language, chatgpt:oa-trust #### Claude Team / Enterprise Verification status: Agent cross-checked (agent-cross-checked) Support: partial Web and desktop interface languages include German, French and Italian; UI quality, complete admin localization and WCAG conformance remain unverified. Availability: unknown Delivery: unknown Scope: surfaces=Claude Team and Enterprise web workspaces, Claude desktop and mobile clients; version=Continuously updated commercial service, retrieved 2026-10-21; plan=Team and Enterprise using the documented web/desktop language setting; add_ons=Enterprise token usage at API rates, Optional US-only inference surcharge, External provider/app subscriptions and Office deployment approval where applicable, CMEK and compliance only on eligible Enterprise configurations; deployment_mode=multi-tenant-saas; region=Commercial supported regions; default global inference and US storage where documented; no EU/Swiss-only residency assumption; os=not specified. Limitations: - dach_language_quality: Are German, French and Italian UIs complete and natural? Unverified after checking Claude support/pricing/client documentation and language-setting searches; no plan-specific German/French/Italian UI inventory, linguistic inspection, localized admin inspection or WCAG conformance report retrieved. Search on 2026-10-26: https://support.claude.com/en/articles/12111783-create-and-edit-files-with-claude, https://support.claude.com/en/articles/10769299-how-to-use-claude-in-your-preferred-language, https://support.claude.com/en/articles/9002504-can-claude-produce-images. No additional scoped evidence established this answer. - accessibility_statement: Is there a WCAG conformance statement? Unverified after checking Claude support/pricing/client documentation and language-setting searches; no plan-specific German/French/Italian UI inventory, linguistic inspection, localized admin inspection or WCAG conformance report retrieved. Search on 2026-10-26: https://support.claude.com/en/articles/12111783-create-and-edit-files-with-claude, https://support.claude.com/en/articles/10769299-how-to-use-claude-in-your-preferred-language, https://support.claude.com/en/articles/9002504-can-claude-produce-images. No additional scoped evidence established this answer. - admin_ui_languages: Is the admin interface available in German? Unverified after checking Claude support/pricing/client documentation and language-setting searches; no plan-specific German/French/Italian UI inventory, linguistic inspection, localized admin inspection or WCAG conformance report retrieved. Search on 2026-10-26: https://support.claude.com/en/articles/12111783-create-and-edit-files-with-claude, https://support.claude.com/en/articles/10769299-how-to-use-claude-in-your-preferred-language, https://support.claude.com/en/articles/9002504-can-claude-produce-images. No additional scoped evidence established this answer. - ui_languages — Which UI languages are offered? [supported]: The public display-language guide lists German, French and Italian, alongside English, Hindi, Indonesian, Japanese, Korean, Brazilian Portuguese and two Spanish variants, for web and desktop. Sources: claude:claude:display-languages-20261026. - dach_language_quality — Are German, French and Italian UIs complete and natural? [unknown]: Are German, French and Italian UIs complete and natural? Unverified after checking Claude support/pricing/client documentation and language-setting searches; no plan-specific German/French/Italian UI inventory, linguistic inspection, localized admin inspection or WCAG conformance report retrieved. Search on 2026-10-26: https://support.claude.com/en/articles/12111783-create-and-edit-files-with-claude, https://support.claude.com/en/articles/10769299-how-to-use-claude-in-your-preferred-language, https://support.claude.com/en/articles/9002504-can-claude-produce-images. No additional scoped evidence established this answer. - accessibility_statement — Is there a WCAG conformance statement? [unknown]: Is there a WCAG conformance statement? Unverified after checking Claude support/pricing/client documentation and language-setting searches; no plan-specific German/French/Italian UI inventory, linguistic inspection, localized admin inspection or WCAG conformance report retrieved. Search on 2026-10-26: https://support.claude.com/en/articles/12111783-create-and-edit-files-with-claude, https://support.claude.com/en/articles/10769299-how-to-use-claude-in-your-preferred-language, https://support.claude.com/en/articles/9002504-can-claude-produce-images. No additional scoped evidence established this answer. - admin_ui_languages — Is the admin interface available in German? [unknown]: Is the admin interface available in German? Unverified after checking Claude support/pricing/client documentation and language-setting searches; no plan-specific German/French/Italian UI inventory, linguistic inspection, localized admin inspection or WCAG conformance report retrieved. Search on 2026-10-26: https://support.claude.com/en/articles/12111783-create-and-edit-files-with-claude, https://support.claude.com/en/articles/10769299-how-to-use-claude-in-your-preferred-language, https://support.claude.com/en/articles/9002504-can-claude-produce-images. No additional scoped evidence established this answer. Checked 2026-10-26; agent cross-checked 2026-10-26; check again by 2026-12-20. Sources: claude:claude:display-languages-20261026 ## Administration and governance ### ADM-01: Single sign-on and authentication Judgment rule: Record SAML, OIDC, Microsoft Entra ID, Google, LDAP, MFA enforcement, conditional-access compatibility, domain verification and plan restrictions. Test one SSO login on a trial where possible. #### ChatGPT Business / Enterprise Verification status: Agent cross-checked (agent-cross-checked) Support: partial Business SAML/OIDC is distinct from Enterprise directory lifecycle controls. Availability: generally-available Delivery: native Scope: surfaces=ChatGPT Business and Enterprise web workspaces, ChatGPT desktop and mobile clients, ChatGPT connected apps and custom MCP apps; version=Continuously updated hosted service, retrieved 2026-10-21; plan=ChatGPT Business Standard/Premium versus Enterprise; Edu only where explicitly named for eligibility differences; add_ons=Purchased workspace credits or contracted token billing where stated, External app/provider subscriptions and Microsoft add-in approval where required, Enterprise residency, EKM and compliance entitlements only where stated; deployment_mode=multi-tenant-saas; region=Supported commercial regions; Europe means EEA + Switzerland when explicitly configured; app/client availability varies; os=not specified. Limitations: - mfa: Individuals can configure supported MFA methods. The official guide explicitly says MFA cannot currently be enforced at ChatGPT workspace or API organization level. This native control restriction is separate from any customer IdP authentication policy. - conditional_access: Enterprise Intune iOS deployment supports Entra Conditional Access; general client/IdP enforcement was not tested. - domain_capture: Business can verify more than one domain; verification does not automatically merge personal accounts. - sso_protocols — Which SSO protocols and identity providers work? [supported]: Business supports SAML and OIDC identity-provider connections. Sources: chatgpt:oa-business-sso. - sso_plan — Which plan includes SSO? [supported]: Business includes SSO and domain verification; Enterprise uses its managed identity setup. Sources: chatgpt:oa-business-sso, chatgpt:oa-admin-quickstart. - mfa — Can MFA be enforced? [partial]: Individuals can configure supported MFA methods. The official guide explicitly says MFA cannot currently be enforced at ChatGPT workspace or API organization level. This native control restriction is separate from any customer IdP authentication policy. Sources: chatgpt:chatgpt:native-mfa-enforcement-20261026. - conditional_access — Do Entra conditional-access policies apply? [partial]: Enterprise Intune iOS deployment supports Entra Conditional Access; general client/IdP enforcement was not tested. Sources: chatgpt:oa-enterprise-notes-20261026. - domain_capture — Can the company claim its email domain? [partial]: Business can verify more than one domain; verification does not automatically merge personal accounts. Sources: chatgpt:oa-business-sso. Checked 2026-10-26; agent cross-checked 2026-10-26; check again by 2026-12-20. Sources: chatgpt:oa-business-sso, chatgpt:oa-admin-quickstart, chatgpt:oa-enterprise-notes-20261026, chatgpt:chatgpt:native-mfa-enforcement-20261026 #### Claude Team / Enterprise Verification status: Agent cross-checked (agent-cross-checked) Support: partial Commercial SSO and domain controls are documented; exact client MFA/Conditional Access coverage remains open. Availability: generally-available Delivery: native Scope: surfaces=Claude Team and Enterprise web workspaces, Claude desktop and mobile clients, Claude connectors and remote MCP integrations, Claude for Microsoft 365 official add-ins, Claude Cowork cloud and desktop task execution; version=Continuously updated commercial service, retrieved 2026-10-21; plan=Claude Team Standard/Premium versus current usage-based Enterprise; legacy Enterprise only when explicitly named; add_ons=Enterprise token usage at API rates, Optional US-only inference surcharge, External provider/app subscriptions and Office deployment approval where applicable, CMEK and compliance only on eligible Enterprise configurations; deployment_mode=multi-tenant-saas; region=Commercial supported regions; default global inference and US storage where documented; no EU/Swiss-only residency assumption; os=not specified. Limitations: - Connector token/device policy caveats must not be generalized to Claude SSO itself. No trial login was performed. - sso_protocols — Which SSO protocols and identity providers work? [partial]: The SSO/provisioning guides document SAML IdPs including Entra, Okta, Google and others; full OIDC/direct-LDAP matrix was not established. Sources: claude:cl-sso, claude:cl-provision. - sso_plan — Which plan includes SSO? [supported]: SSO is available on Team and Enterprise. Sources: claude:cl-sso. - mfa — Can MFA be enforced? [unknown]: Can MFA be enforced? Unverified after checking SSO/provisioning and Microsoft connector security docs; direct MFA policy enforcement and client Conditional Access compatibility not tested. - conditional_access — Do Entra conditional-access policies apply? [unknown]: Do Entra conditional-access policies apply? Unverified after checking SSO/provisioning and Microsoft connector security docs; direct MFA policy enforcement and client Conditional Access compatibility not tested. - domain_capture — Can the company claim its email domain? [partial]: SSO requires domain verification; Enterprise account claiming and Team migration differ. Sources: claude:cl-sso, claude:cl-pricing. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: claude:cl-sso, claude:cl-provision, claude:cl-pricing ### ADM-02: User provisioning and lifecycle Judgment rule: Record SCIM, just-in-time provisioning, group sync from the identity provider, deprovisioning effects (chats, assistants, knowledge ownership transfer) and licence assignment. Deprovision a test user and record what happens to their content. #### ChatGPT Business / Enterprise Verification status: Agent cross-checked (agent-cross-checked) Support: partial Standalone Business and Enterprise differ materially in provisioning and leaver behavior. Availability: generally-available Delivery: native Scope: surfaces=ChatGPT Business and Enterprise web workspaces, ChatGPT desktop and mobile clients, ChatGPT connected apps and custom MCP apps; version=Continuously updated hosted service, retrieved 2026-10-21; plan=ChatGPT Business Standard/Premium versus Enterprise; Edu only where explicitly named for eligibility differences; add_ons=Purchased workspace credits or contracted token billing where stated, External app/provider subscriptions and Microsoft add-in approval where required, Enterprise residency, EKM and compliance entitlements only where stated; deployment_mode=multi-tenant-saas; region=Supported commercial regions; Europe means EEA + Switzerland when explicitly configured; app/client availability varies; os=not specified. Limitations: - No SCIM or leaver fixture was performed. - scim — Is SCIM provisioning supported? [supported]: Standalone Business excludes SCIM. Enterprise supports directory sync; tenant sync alone does not grant workspace access. Sources: chatgpt:oa-business-sso, chatgpt:oa-admin-quickstart. - group_sync — Are identity-provider groups synced? [supported]: Business standalone excludes synchronized groups. Enterprise directory groups can receive separate workspace assignments. Sources: chatgpt:oa-business-sso, chatgpt:oa-admin-quickstart. - jit_provisioning — Are users created at first login? [partial]: Business automatic account creation can add eligible verified-domain sign-ins where available; this is distinct from SCIM. Sources: chatgpt:oa-business-sso. - deprovisioning — What happens to a removed user's data and shared assets? [supported]: Removal revokes access immediately. Business data remains indefinitely; Enterprise/Edu follow retention. GPT/project ownership transfers without private chat/file visibility. Sources: chatgpt:oa-leavers. - seat_assignment — Can admins assign and reclaim seats? [supported]: Business owners buy and reassign Standard/Premium seats; Enterprise separates roles, seats and access. Sources: chatgpt:oa-billing, chatgpt:oa-members. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: chatgpt:oa-business-sso, chatgpt:oa-admin-quickstart, chatgpt:oa-leavers, chatgpt:oa-billing, chatgpt:oa-members #### Claude Team / Enterprise Verification status: Agent cross-checked (agent-cross-checked) Support: partial Team JIT and Enterprise SCIM have different synchronization and removal behavior. Availability: generally-available Delivery: native Scope: surfaces=Claude Team and Enterprise web workspaces, Claude desktop and mobile clients, Claude connectors and remote MCP integrations, Claude for Microsoft 365 official add-ins, Claude Cowork cloud and desktop task execution; version=Continuously updated commercial service, retrieved 2026-10-21; plan=Claude Team Standard/Premium versus current usage-based Enterprise; legacy Enterprise only when explicitly named; add_ons=Enterprise token usage at API rates, Optional US-only inference surcharge, External provider/app subscriptions and Office deployment approval where applicable, CMEK and compliance only on eligible Enterprise configurations; deployment_mode=multi-tenant-saas; region=Commercial supported regions; default global inference and US storage where documented; no EU/Swiss-only residency assumption; os=not specified. Limitations: - No leaver fixture or asset transfer test was performed. - scim — Is SCIM provisioning supported? [supported]: SCIM is available on Enterprise and explicitly unavailable on Team. Sources: claude:cl-provision. - group_sync — Are identity-provider groups synced? [partial]: Enterprise SCIM can synchronize groups; JIT group mappings change role/seat at login and do not synchronize custom-role groups. Sources: claude:cl-provision. - jit_provisioning — Are users created at first login? [supported]: Team/Enterprise JIT can provision at first SSO login; unassigned JIT users can retain their seat until manual removal. Sources: claude:cl-provision. - deprovisioning — What happens to a removed user's data and shared assets? [partial]: Enterprise SCIM automatically removes users when IdP access is revoked; underlying chat/project ownership and retention were not fixture-tested. Sources: claude:cl-provision. - seat_assignment — Can admins assign and reclaim seats? [supported]: Admins/owners manage standard/premium or current Enterprise access seats; group mappings can assign role/tier on supported plans. Sources: claude:cl-provision. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: claude:cl-provision ### ADM-03: Roles, groups and feature permissions Judgment rule: Record admin roles, delegated admins, groups, per-feature permissions (web search, image generation, connectors, file upload, agents), separation of subsidiaries or departments, and enforcement. Test one disabled feature for one group. #### ChatGPT Business / Enterprise Verification status: Agent cross-checked (agent-cross-checked) Support: partial Enterprise groups/RBAC and delegated roles differ from Business administration. Availability: generally-available Delivery: native Scope: surfaces=ChatGPT Business and Enterprise web workspaces, ChatGPT desktop and mobile clients, ChatGPT connected apps and custom MCP apps; version=Continuously updated hosted service, retrieved 2026-10-21; plan=ChatGPT Business Standard/Premium versus Enterprise; Edu only where explicitly named for eligibility differences; add_ons=Purchased workspace credits or contracted token billing where stated, External app/provider subscriptions and Microsoft add-in approval where required, Enterprise residency, EKM and compliance entitlements only where stated; deployment_mode=multi-tenant-saas; region=Supported commercial regions; Europe means EEA + Switzerland when explicitly configured; app/client availability varies; os=not specified. Limitations: - No disabled-feature test with two users was performed. - admin_roles — Which admin roles exist, and can admin rights be delegated? [supported]: Enterprise/Edu roles include member, analytics viewer, admin and owner; Enterprise can delegate group tasks. Sources: chatgpt:oa-members. - groups — Can permissions be set per group? [supported]: Enterprise sync/manual groups can receive roles; standalone Business synchronized groups are excluded. Sources: chatgpt:oa-admin-quickstart, chatgpt:oa-business-sso. - feature_toggles — Which features can be switched on or off per group? [partial]: Enterprise controls models, GPTs, canvas, projects, memory and Work by workspace/role; exact per-group feature matrix was not tested. Sources: chatgpt:oa-admin-settings. - multi_entity — Can subsidiaries or departments be separated within one contract? [partial]: The Services Agreement allows affiliates within one workspace or separate affiliate orders/workspaces. It does not prove an arbitrary subsidiary-isolation console. Sources: chatgpt:oa-services. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: chatgpt:oa-members, chatgpt:oa-admin-quickstart, chatgpt:oa-business-sso, chatgpt:oa-admin-settings, chatgpt:oa-services #### Claude Team / Enterprise Verification status: Agent cross-checked (agent-cross-checked) Support: partial Enterprise custom roles/groups add granular controls beyond Team owner/admin roles. Availability: generally-available Delivery: native Scope: surfaces=Claude Team and Enterprise web workspaces, Claude desktop and mobile clients, Claude connectors and remote MCP integrations, Claude for Microsoft 365 official add-ins, Claude Cowork cloud and desktop task execution; version=Continuously updated commercial service, retrieved 2026-10-21; plan=Claude Team Standard/Premium versus current usage-based Enterprise; legacy Enterprise only when explicitly named; add_ons=Enterprise token usage at API rates, Optional US-only inference surcharge, External provider/app subscriptions and Office deployment approval where applicable, CMEK and compliance only on eligible Enterprise configurations; deployment_mode=multi-tenant-saas; region=Commercial supported regions; default global inference and US storage where documented; no EU/Swiss-only residency assumption; os=not specified. Limitations: - Read each atomic answer for its plan, access and feature limits. - admin_roles — Which admin roles exist, and can admin rights be delegated? [supported]: Team has Owner/Admin/User; Enterprise also has custom roles and Primary Owner responsibilities. Sources: claude:cl-provision, claude:cl-compliance. - groups — Can permissions be set per group? [supported]: Enterprise groups can be manual or SCIM-synchronized and receive roles/resources. Sources: claude:cl-groups. - feature_toggles — Which features can be switched on or off per group? [partial]: Enterprise roles control model/effort and plugin access; owners manage connectors, artifacts and egress. A full feature-by-group matrix was not tested. Sources: claude:cl-model-control, claude:cl-groups, claude:cl-artifacts-admin. - multi_entity — Can subsidiaries or departments be separated within one contract? [partial]: Parent/linked organization identity and compliance are documented, but full subsidiary data-isolation behavior was not verified. Sources: claude:cl-compliance. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: claude:cl-provision, claude:cl-compliance, claude:cl-groups, claude:cl-model-control, claude:cl-artifacts-admin ### ADM-04: Usage and adoption analytics Judgment rule: Record dashboards for active users, usage by feature, model, group and assistant, export, and privacy controls (aggregation, pseudonymisation, works-council-friendly settings). Distinguish aggregate adoption metrics from per-person monitoring. #### ChatGPT Business / Enterprise Verification status: Agent cross-checked (agent-cross-checked) Support: partial Business documents adoption/member analytics; Enterprise/Edu now documents CSV exports and specific aggregate-report privacy controls. Availability: generally-available Delivery: native Scope: surfaces=ChatGPT Business and Enterprise web workspaces, ChatGPT desktop and mobile clients, ChatGPT connected apps and custom MCP apps; version=Continuously updated hosted service, retrieved 2026-10-21; plan=Business workspace analytics; Enterprise/Edu export and Task insights controls only where explicitly identified; add_ons=Purchased workspace credits or contracted token billing where stated, External app/provider subscriptions and Microsoft add-in approval where required, Enterprise residency, EKM and compliance entitlements only where stated; deployment_mode=multi-tenant-saas; region=Supported commercial regions; Europe means EEA + Switzerland when explicitly configured; app/client availability varies; os=not specified. Limitations: - breakdowns: Member-level usage and seat-type metrics are documented; full model/group/assistant views were not all verified. - export: Enterprise/Edu can export a by-user Workspace report and GPT/project reports as CSV, plus survey and benchmark data. The October 23 release confirms the updated flow. A complete equivalent Business export entitlement was not established. - privacy_modes: Enterprise/Edu Task insights reports aggregate categories without individual conversation content and can be disabled; survey export names/emails depend on Include user identifiers. This is not a universal pseudonymization switch for the ordinary per-user usage report or a verified Business setting. - adoption_dashboard — Is there an adoption dashboard? [supported]: Business has workspace analytics with active users, messages and credits. Sources: chatgpt:oa-business-notes-20261026. - breakdowns — Can usage be broken down by group, model, feature and assistant? [partial]: Member-level usage and seat-type metrics are documented; full model/group/assistant views were not all verified. Sources: chatgpt:oa-business-notes-20261026. - export — Can usage data be exported? [partial]: Enterprise/Edu can export a by-user Workspace report and GPT/project reports as CSV, plus survey and benchmark data. The October 23 release confirms the updated flow. A complete equivalent Business export entitlement was not established. Sources: chatgpt:chatgpt:enterprise-analytics-export-20261026, chatgpt:oa-enterprise-notes-20261026. - privacy_modes — Can per-person reporting be limited or pseudonymised? [partial]: Enterprise/Edu Task insights reports aggregate categories without individual conversation content and can be disabled; survey export names/emails depend on Include user identifiers. This is not a universal pseudonymization switch for the ordinary per-user usage report or a verified Business setting. Sources: chatgpt:chatgpt:enterprise-analytics-export-20261026. Checked 2026-10-26; agent cross-checked 2026-10-26; check again by 2026-12-20. Sources: chatgpt:oa-business-notes-20261026, chatgpt:chatgpt:enterprise-analytics-export-20261026, chatgpt:oa-enterprise-notes-20261026 #### Claude Team / Enterprise Verification status: Agent cross-checked (agent-cross-checked) Support: partial Commercial analytics expose adoption and spend with plan-specific roles and CSV exports. Availability: generally-available Delivery: native Scope: surfaces=Claude Team and Enterprise web workspaces, Claude desktop and mobile clients, Claude connectors and remote MCP integrations, Claude for Microsoft 365 official add-ins, Claude Cowork cloud and desktop task execution; version=Continuously updated commercial service, retrieved 2026-10-21; plan=Claude Team Standard/Premium versus current usage-based Enterprise; legacy Enterprise only when explicitly named; add_ons=Enterprise token usage at API rates, Optional US-only inference surcharge, External provider/app subscriptions and Office deployment approval where applicable, CMEK and compliance only on eligible Enterprise configurations; deployment_mode=multi-tenant-saas; region=Commercial supported regions; default global inference and US storage where documented; no EU/Swiss-only residency assumption; os=not specified. Limitations: - Unverified parts: privacy_modes. - Read each atomic answer for its plan, access and feature limits. - adoption_dashboard — Is there an adoption dashboard? [supported]: Team owners and Enterprise owners/admins have usage analytics; Enterprise admins cannot see Spend. Sources: claude:cl-analytics. - breakdowns — Can usage be broken down by group, model, feature and assistant? [partial]: Product, group, member, model, skill and connector read/write activity are documented; availability varies by billing mode. Sources: claude:cl-analytics. - export — Can usage data be exported? [supported]: CSV spend reports include user/model token and estimated-spend fields, updated daily, with up to 90-day selectable history. Sources: claude:cl-analytics. - privacy_modes — Can per-person reporting be limited or pseudonymised? [unknown]: Can per-person reporting be limited or pseudonymised? Unverified after checking analytics and role docs; organization-wide pseudonymization/works-council reporting settings not established. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: claude:cl-analytics ### ADM-05: Spend controls and cost allocation Judgment rule: Record cost visibility per user, group and cost centre, budgets and their behaviour (alert, block, downgrade model), pooled credits, and chargeback exports. Test a small budget on a trial where possible. Distinguish billed amounts, estimates and unavailable amounts. #### ChatGPT Business / Enterprise Verification status: Agent cross-checked (agent-cross-checked) Support: partial Business has credit and recharge limits; these do not equate to a full cost-centre system. Availability: generally-available Delivery: native Scope: surfaces=ChatGPT Business and Enterprise web workspaces, ChatGPT desktop and mobile clients, ChatGPT connected apps and custom MCP apps; version=Continuously updated hosted service, retrieved 2026-10-21; plan=ChatGPT Business Standard/Premium versus Enterprise; Edu only where explicitly named for eligibility differences; add_ons=Purchased workspace credits or contracted token billing where stated, External app/provider subscriptions and Microsoft add-in approval where required, Enterprise residency, EKM and compliance entitlements only where stated; deployment_mode=multi-tenant-saas; region=Supported commercial regions; Europe means EEA + Switzerland when explicitly configured; app/client availability varies; os=not specified. Limitations: - Unverified parts: chargeback. - Read each atomic answer for its plan, access and feature limits. - cost_visibility — Can admins see cost or consumption per user and group? [supported]: Business analytics show member seat types, credits and messages. Sources: chatgpt:oa-business-notes. - budgets — Can budgets be set per user or group? [supported]: Business permits seat-type monthly credit limits and per-user overrides; defaults have no specified limits. Sources: chatgpt:oa-credit-controls. - budget_enforcement — Does reaching a budget alert, block or downgrade? [partial]: Credit-backed features can become unavailable when credits are insufficient; exact monthly-limit overshoot/stop timing was not tested. Sources: chatgpt:oa-credit-controls. - chargeback — Can costs be exported per cost centre? [unknown]: Can costs be exported per cost centre? Unverified after checking Business spend-control docs; group/cost-centre allocation and chargeback export not established. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: chatgpt:oa-business-notes, chatgpt:oa-credit-controls #### Claude Team / Enterprise Verification status: Agent cross-checked (agent-cross-checked) Support: partial Enterprise has user/group limits, with pooled group budgets in beta. Availability: generally-available Delivery: native Scope: surfaces=Claude Team and Enterprise web workspaces, Claude desktop and mobile clients, Claude connectors and remote MCP integrations, Claude for Microsoft 365 official add-ins, Claude Cowork cloud and desktop task execution; version=Continuously updated commercial service, retrieved 2026-10-21; plan=Claude Team Standard/Premium versus current usage-based Enterprise; legacy Enterprise only when explicitly named; add_ons=Enterprise token usage at API rates, Optional US-only inference surcharge, External provider/app subscriptions and Office deployment approval where applicable, CMEK and compliance only on eligible Enterprise configurations; deployment_mode=multi-tenant-saas; region=Commercial supported regions; default global inference and US storage where documented; no EU/Swiss-only residency assumption; os=not specified. Limitations: - No small-budget enforced-stop fixture was run. - cost_visibility — Can admins see cost or consumption per user and group? [supported]: Enterprise analytics show model/member spend; legacy seat-based reports cover overage only. Sources: claude:cl-analytics. - budgets — Can budgets be set per user or group? [partial]: Enterprise supports organization/user limits and group per-user limits; shared monthly group budgets are beta. Sources: claude:cl-enterprise, claude:cl-groups. - budget_enforcement — Does reaching a budget alert, block or downgrade? [partial]: Docs expose blocked-by-limit behavior and individual/group resolution order; exact overshoot/timing was not tested. Sources: claude:cl-groups. - chargeback — Can costs be exported per cost centre? [partial]: Per-user/model CSVs can inform allocation; a native cost-centre chargeback export was not established. Sources: claude:cl-analytics. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: claude:cl-analytics, claude:cl-enterprise, claude:cl-groups ### ADM-06: Audit logs and compliance export Judgment rule: Record which events are logged (logins, admin changes, prompts, responses, file access, connector queries), retention, export or SIEM streaming, and eDiscovery/legal hold. Use the word audit only with a defined retention and integrity model. #### ChatGPT Business / Enterprise Verification status: Agent cross-checked (agent-cross-checked) Support: partial Enterprise/Edu compliance access is owner-granted; Business documents conditional owner exports for individual members. Availability: generally-available Delivery: native Scope: surfaces=ChatGPT Business and Enterprise web workspaces, ChatGPT connected apps and custom MCP apps; version=Continuously updated hosted service, retrieved 2026-10-21; plan=Enterprise/Edu Compliance Platform and role permissions; Business default private-history/analytics boundaries and conditional owner per-member export; add_ons=Purchased workspace credits or contracted token billing where stated, External app/provider subscriptions and Microsoft add-in approval where required, Enterprise residency, EKM and compliance entitlements only where stated; deployment_mode=multi-tenant-saas; region=Supported commercial regions; Europe means EEA + Switzerland when explicitly configured; app/client availability varies; os=not specified. Limitations: - Business routine visibility, conditional owner per-member export and Enterprise/Edu Compliance access are separate operations. No audit or archive fixture was run. - No blanket Business no-admin-access guarantee. No Enterprise/Edu compliance entitlement is transferred to Business. - admin_events — Are admin and security events logged? [supported]: Enterprise/Edu Compliance Platform exposes append-only audit/authentication/app events, with category-scoped Admin keys. Sources: chatgpt:oa-compliance-r2. - content_logging — Can prompts and answers be retained for compliance, and is it configurable? [partial]: Enterprise/Edu: only an owner grants broad compliance or Conversation messages access, including locked-chat messages. Business: default history and routine analytics do not expose all private chats. Owners can export an individual member via the Business workspace > Members > member three-dot menu > Export data, if available. Bulk all-chat coverage is unverified. Sources: chatgpt:oa-compliance-r2, chatgpt:oa-business-faq-r2, chatgpt:oa-business-privacy-r2, chatgpt:oa-business-owner-export-r3. - siem_export — Can logs stream to a SIEM or be exported? [supported]: Enterprise/Edu can export eligible compliance logs into SIEM/data-lake/partner systems. Business eligibility is not inferred. Sources: chatgpt:oa-compliance-r2. - ediscovery — Are eDiscovery and legal hold supported? [partial]: Enterprise/Edu Compliance Platform documents eDiscovery integrations; native legal-hold operation was not verified. Sources: chatgpt:oa-compliance-r2. - log_retention — How long are logs kept? [supported]: Enterprise/Edu Compliance Logs Platform gives30-day availability; longer retention requires continuous external downloads. Sources: chatgpt:oa-compliance-r2. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: chatgpt:oa-compliance-r2, chatgpt:oa-business-faq-r2, chatgpt:oa-business-privacy-r2, chatgpt:oa-business-owner-export-r3 #### Claude Team / Enterprise Verification status: Agent cross-checked (agent-cross-checked) Support: partial Enterprise audit metadata and content/compliance exports are distinct. Availability: generally-available Delivery: native Scope: surfaces=Claude Team and Enterprise web workspaces, Claude desktop and mobile clients, Claude connectors and remote MCP integrations, Claude for Microsoft 365 official add-ins, Claude Cowork cloud and desktop task execution; version=Continuously updated commercial service, retrieved 2026-10-21; plan=Claude Team Standard/Premium versus current usage-based Enterprise; legacy Enterprise only when explicitly named; add_ons=Enterprise token usage at API rates, Optional US-only inference surcharge, External provider/app subscriptions and Office deployment approval where applicable, CMEK and compliance only on eligible Enterprise configurations; deployment_mode=multi-tenant-saas; region=Commercial supported regions; default global inference and US storage where documented; no EU/Swiss-only residency assumption; os=not specified. Limitations: - CMEK disables the UI Export logs route; audit events remain accessible through Compliance API. No export or integrity fixture was run. - admin_events — Are admin and security events logged? [supported]: Enterprise audit events cover member, SSO, configuration, file and conversation metadata; exported fields include actor/device/IP. Sources: claude:cl-audit. - content_logging — Can prompts and answers be retained for compliance, and is it configurable? [supported]: Audit export excludes chat titles/content; organization data exports or Compliance API provide eligible content. Sources: claude:cl-audit, claude:cl-compliance. - siem_export — Can logs stream to a SIEM or be exported? [supported]: Enterprise Compliance API and partner integrations provide event/chat/file access for security tools. Sources: claude:cl-compliance, claude:cl-compliance-partners. - ediscovery — Are eDiscovery and legal hold supported? [partial]: Partner integrations include preservation/eDiscovery workflows; a native legal-hold setting was not verified. Sources: claude:cl-compliance-partners. - log_retention — How long are logs kept? [partial]: UI audit export aggregates the past 180 days; its download link lasts 24 hours. API retention/integrity guarantees were not fully inspected. Sources: claude:cl-audit. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: claude:cl-audit, claude:cl-compliance, claude:cl-compliance-partners ### ADM-07: Data loss prevention and personal data Judgment rule: Record detection and handling of personal and confidential data before it reaches a model: redaction, masking, blocking, warning. Record integration with Purview, Netskope or similar, and whether filtering runs locally or at a third party. Send a fixture prompt with a Swiss AHV number and IBAN and record the outcome. #### ChatGPT Business / Enterprise Verification status: Agent cross-checked (agent-cross-checked) Support: partial Enterprise/Edu can integrate compliance data with DLP; inline redaction was not established. Availability: generally-available Delivery: native Scope: surfaces=ChatGPT Business and Enterprise web workspaces, ChatGPT desktop and mobile clients, ChatGPT connected apps and custom MCP apps; version=Continuously updated hosted service, retrieved 2026-10-21; plan=ChatGPT Business Standard/Premium versus Enterprise; Edu only where explicitly named for eligibility differences; add_ons=Purchased workspace credits or contracted token billing where stated, External app/provider subscriptions and Microsoft add-in approval where required, Enterprise residency, EKM and compliance entitlements only where stated; deployment_mode=multi-tenant-saas; region=Supported commercial regions; Europe means EEA + Switzerland when explicitly configured; app/client availability varies; os=not specified. Limitations: - Unverified parts: pii_detection, pii_action, custom_patterns, filter_location. - Read each atomic answer for its plan, access and feature limits. - pii_detection — Is personal data detected in prompts and files? [unknown]: Is personal data detected in prompts and files? Unverified after checking Compliance Platform, app controls and security documentation; no inline PII action, custom AHV/IBAN pattern or filter-location evidence/test. - pii_action — Is it redacted, masked, blocked or only warned? [unknown]: Is it redacted, masked, blocked or only warned? Unverified after checking Compliance Platform, app controls and security documentation; no inline PII action, custom AHV/IBAN pattern or filter-location evidence/test. - custom_patterns — Can admins add custom patterns or terms? [unknown]: Can admins add custom patterns or terms? Unverified after checking Compliance Platform, app controls and security documentation; no inline PII action, custom AHV/IBAN pattern or filter-location evidence/test. - dlp_integration — Does it integrate with an existing DLP product? [partial]: Compliance Platform lists DLP partners including Purview and Netskope. This does not establish pre-model prompt redaction. Sources: chatgpt:oa-compliance. - filter_location — Where does filtering run? [unknown]: Where does filtering run? Unverified after checking Compliance Platform, app controls and security documentation; no inline PII action, custom AHV/IBAN pattern or filter-location evidence/test. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: chatgpt:oa-compliance #### Claude Team / Enterprise Verification status: Agent cross-checked (agent-cross-checked) Support: partial Eligible Enterprise organizations can use Compliance API partner monitoring; native inline PII handling remains unverified. Availability: generally-available Delivery: native Scope: surfaces=Claude Team and Enterprise web workspaces, Claude connectors and remote MCP integrations; version=Continuously updated commercial service, retrieved 2026-10-21; plan=Claude Enterprise with Primary-Owner-enabled Compliance API and separately configured partner integration; no Team entitlement; add_ons=Enterprise plan, Compliance API activation by Primary Owner, Applicable partner subscription and configuration; deployment_mode=multi-tenant-saas; region=Commercial supported regions; default global inference and US storage where documented; no EU/Swiss-only residency assumption; os=not specified. Limitations: - The positive integration statement is Enterprise-only. Team integration support remains unverified. - No Swiss AHV/IBAN fixture, custom-pattern behavior, pre-model blocking/redaction or filter geography verified. - pii_detection — Is personal data detected in prompts and files? [unknown]: Is personal data detected in prompts and files? Unverified after checking Compliance API integration, connector and security docs; no Swiss AHV/IBAN test, native PII action/custom patterns or filter geography verified. - pii_action — Is it redacted, masked, blocked or only warned? [unknown]: Is it redacted, masked, blocked or only warned? Unverified after checking Compliance API integration, connector and security docs; no Swiss AHV/IBAN test, native PII action/custom patterns or filter geography verified. - custom_patterns — Can admins add custom patterns or terms? [unknown]: Can admins add custom patterns or terms? Unverified after checking Compliance API integration, connector and security docs; no Swiss AHV/IBAN test, native PII action/custom patterns or filter geography verified. - dlp_integration — Does it integrate with an existing DLP product? [partial]: Enterprise Compliance API partners offer monitoring/security/DLP integrations after Primary Owner activation. Claude Platform is a separate scope, and these integrations do not prove native inline pre-model redaction. Sources: claude:cl-compliance-partners-r2. - filter_location — Where does filtering run? [unknown]: Where does filtering run? Unverified after checking Compliance API integration, connector and security docs; no Swiss AHV/IBAN test, native PII action/custom patterns or filter geography verified. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: claude:cl-compliance-partners-r2 ### ADM-08: AI policy and guardrails Judgment rule: Record organisation-wide system instructions, acceptable-use notices and acknowledgement, content filters, topic restrictions, AI-output labelling, and admin visibility of policy violations. Separate enforced policy from instructions the model is expected to follow. #### ChatGPT Business / Enterprise Verification status: Agent cross-checked (agent-cross-checked) Support: partial Enterprise has policy reminders and workspace controls; enforcement coverage remains partly unverified. Availability: generally-available Delivery: native Scope: surfaces=ChatGPT Business and Enterprise web workspaces, ChatGPT desktop and mobile clients, ChatGPT connected apps and custom MCP apps; version=Continuously updated hosted service, retrieved 2026-10-21; plan=ChatGPT Business Standard/Premium versus Enterprise; Edu only where explicitly named for eligibility differences; add_ons=Purchased workspace credits or contracted token billing where stated, External app/provider subscriptions and Microsoft add-in approval where required, Enterprise residency, EKM and compliance entitlements only where stated; deployment_mode=multi-tenant-saas; region=Supported commercial regions; Europe means EEA + Switzerland when explicitly configured; app/client availability varies; os=not specified. Limitations: - Unverified parts: org_instructions. - Read each atomic answer for its plan, access and feature limits. - org_instructions — Can admins set organisation-wide instructions? [unknown]: Can admins set organisation-wide instructions? Unverified after checking Enterprise settings, Services Agreement and compliance docs; an enforced organization system prompt was not established. - usage_notice — Can users be required to accept a usage policy? [partial]: The Enterprise AI policy modal appears every 30 days and after updates; mandatory acknowledgment behavior was not established. Sources: chatgpt:oa-admin-settings. - content_filters — Are content filters configurable? [partial]: Service usage restrictions apply; customer-configurable topic filters were not established. Sources: chatgpt:oa-services. - violation_reporting — Are policy hits visible to admins? [partial]: Compliance app/audit events are available; complete policy-violation coverage was not verified. Sources: chatgpt:oa-compliance. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: chatgpt:oa-admin-settings, chatgpt:oa-services, chatgpt:oa-compliance #### Claude Team / Enterprise Verification status: Agent cross-checked (agent-cross-checked) Support: partial Enterprise has feature/model and plugin safeguards; broader policy enforcement remains partly unverified. Availability: generally-available Delivery: native Scope: surfaces=Claude Team and Enterprise web workspaces, Claude desktop and mobile clients, Claude connectors and remote MCP integrations, Claude for Microsoft 365 official add-ins, Claude Cowork cloud and desktop task execution; version=Continuously updated commercial service, retrieved 2026-10-21; plan=Claude Team Standard/Premium versus current usage-based Enterprise; legacy Enterprise only when explicitly named; add_ons=Enterprise token usage at API rates, Optional US-only inference surcharge, External provider/app subscriptions and Office deployment approval where applicable, CMEK and compliance only on eligible Enterprise configurations; deployment_mode=multi-tenant-saas; region=Commercial supported regions; default global inference and US storage where documented; no EU/Swiss-only residency assumption; os=not specified. Limitations: - Unverified parts: org_instructions, usage_notice. - Read each atomic answer for its plan, access and feature limits. - org_instructions — Can admins set organisation-wide instructions? [unknown]: Can admins set organisation-wide instructions? Unverified after checking commercial terms, Enterprise controls and security scanning releases; organization-wide enforced instructions and mandatory AUP acknowledgment not established. - usage_notice — Can users be required to accept a usage policy? [unknown]: Can users be required to accept a usage policy? Unverified after checking commercial terms, Enterprise controls and security scanning releases; organization-wide enforced instructions and mandatory AUP acknowledgment not established. - content_filters — Are content filters configurable? [partial]: Enterprise release notes announce skill/plugin security scanning beta; it does not establish a configurable prompt/topic content-filter system. Sources: claude:cl-release. - violation_reporting — Are policy hits visible to admins? [partial]: Security/compliance integrations can analyze events; a complete native policy-violation dashboard was not verified. Sources: claude:cl-compliance-partners. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: claude:cl-release, claude:cl-compliance-partners ## Data protection and sovereignty ### DATA-01: Hosting location and data residency Judgment rule: Record country or region separately for chat storage, files and indexes, model inference, backups, logs and telemetry, and support access. Name the cloud provider. Record whether residency is default, a paid option or plan-dependent. "EU data boundary" programmes are recorded with their documented exceptions. #### ChatGPT Business / Enterprise Verification status: Agent cross-checked (agent-cross-checked) Support: partial Enterprise/Edu residency separates regional content storage from GPU execution and global operations. Availability: generally-available Delivery: native Scope: surfaces=ChatGPT Business and Enterprise web workspaces, ChatGPT desktop and mobile clients, ChatGPT connected apps and custom MCP apps; version=Continuously updated hosted service, retrieved 2026-10-21; plan=ChatGPT Business Standard/Premium versus Enterprise; Edu only where explicitly named for eligibility differences; add_ons=Purchased workspace credits or contracted token billing where stated, External app/provider subscriptions and Microsoft add-in approval where required, Enterprise residency, EKM and compliance entitlements only where stated; deployment_mode=multi-tenant-saas; region=Supported commercial regions; Europe means EEA + Switzerland when explicitly configured; app/client availability varies; os=not specified. Limitations: - Cloud infrastructure subprocessors include multiple providers. Exact placement per workspace, support geography and CPU processing remain separate questions. - storage_region — Where are chats, files and indexes stored? [partial]: Eligible new Enterprise/Edu workspaces can select Europe, EEA + Switzerland, for in-scope content at rest. Standalone Business eligibility is not established. Sources: chatgpt:oa-residency. - inference_region — Where do model calls run, per provider? [partial]: Eligible Enterprise/Edu can configure same-region European GPU inference; CPU tasks and external apps/search can process elsewhere. Sources: chatgpt:oa-residency. - backups_logs_region — Where are backups, logs and telemetry? [partial]: In-scope content backups/replicas stay in-region; system metadata and non-content logs are outside the general residency commitment. Sources: chatgpt:oa-residency. - support_access_region — From where can vendor staff access data? [partial]: Authorized staff access has purpose restrictions; an EU/Swiss-only support-access region was not established. Sources: chatgpt:oa-privacy. - swiss_hosting — Is Swiss hosting available? [partial]: Europe includes Switzerland as a region grouping; this is not a Switzerland-only storage/inference/support commitment. Sources: chatgpt:oa-residency. - residency_plan — Which plan or option provides residency? [partial]: Residency is documented for eligible Enterprise/Edu, with storage included at no extra charge; inference has separate eligibility. Sources: chatgpt:oa-residency. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: chatgpt:oa-residency, chatgpt:oa-privacy #### Claude Team / Enterprise Verification status: Agent cross-checked (agent-cross-checked) Support: partial Commercial privacy documentation describes US storage and global inference; US-only Enterprise inference is a separate option. Availability: generally-available Delivery: native Scope: surfaces=Claude Team and Enterprise web workspaces, Claude desktop and mobile clients, Claude connectors and remote MCP integrations, Claude for Microsoft 365 official add-ins, Claude Cowork cloud and desktop task execution; version=Continuously updated commercial service, retrieved 2026-10-21; plan=Claude Team Standard/Premium versus current usage-based Enterprise; legacy Enterprise only when explicitly named; add_ons=Enterprise token usage at API rates, Optional US-only inference surcharge, External provider/app subscriptions and Office deployment approval where applicable, CMEK and compliance only on eligible Enterprise configurations; deployment_mode=multi-tenant-saas; region=Commercial supported regions; default global inference and US storage where documented; no EU/Swiss-only residency assumption; os=not specified. Limitations: - Do not substitute cloud-provider model availability for residency of the hosted Claude workspace. Design and Google add-in retention have separate rules. - storage_region — Where are chats, files and indexes stored? [partial]: The commercial server-location article specifies US storage for Enterprise/API; exact Team and per-feature chat/file/index mapping was not established. Sources: claude:cl-servers. - inference_region — Where do model calls run, per provider? [supported]: Default commercial inference may run in the US, Europe, Asia or Australia; usage-based Enterprise can select US-only inference. Sources: claude:cl-servers, claude:cl-us-only. - backups_logs_region — Where are backups, logs and telemetry? [unknown]: Where are backups, logs and telemetry? Unverified after checking commercial location and US-only inference guides; no EU/Swiss-only hosting guarantee or backup/log/telemetry country matrix retrieved. - support_access_region — From where can vendor staff access data? [partial]: Internal support/safety processing can take place in countries with Anthropic affiliates; the full personnel/country/access map is not enumerated here. Sources: claude:cl-servers. - swiss_hosting — Is Swiss hosting available? [unknown]: Is Swiss hosting available? Unverified after checking commercial location and US-only inference guides; no EU/Swiss-only hosting guarantee or backup/log/telemetry country matrix retrieved. - residency_plan — Which plan or option provides residency? [supported]: US-only inference is limited to usage-based Enterprise, excludes Team and legacy seat-based Enterprise, and has model-specific 1.1x pricing. It does not control storage or third-party services. Sources: claude:cl-us-only. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: claude:cl-servers, claude:cl-us-only ### DATA-02: Deployment options Judgment rule: Record multi-tenant SaaS, dedicated single-tenant instance, deployment in the customer's cloud account, on-premise and air-gapped as separate options with plan and availability. Record which features are missing in each mode, who operates it, and the documented seat or contract threshold for each mode, which can differ from the enterprise plan threshold (e.g. dedicated SaaS from 2,000 seats, own cloud from 5,000). A local-network connector or gateway that reaches on-prem data from a vendor-hosted platform is KNOW-03, not on-premise deployment. #### ChatGPT Business / Enterprise Verification status: Agent cross-checked (agent-cross-checked) Support: partial ChatGPT is a hosted workspace; customer-hosted deployment contracts remain unverified. Availability: generally-available Delivery: native Scope: surfaces=ChatGPT Business and Enterprise web workspaces, ChatGPT desktop and mobile clients, ChatGPT connected apps and custom MCP apps; version=Continuously updated hosted service, retrieved 2026-10-21; plan=ChatGPT Business Standard/Premium versus Enterprise; Edu only where explicitly named for eligibility differences; add_ons=Purchased workspace credits or contracted token billing where stated, External app/provider subscriptions and Microsoft add-in approval where required, Enterprise residency, EKM and compliance entitlements only where stated; deployment_mode=multi-tenant-saas; region=Supported commercial regions; Europe means EEA + Switzerland when explicitly configured; app/client availability varies; os=not specified. Limitations: - Unverified parts: dedicated_instance, customer_cloud, on_premise, air_gapped, mode_feature_gaps. - Read each atomic answer for its plan, access and feature limits. - multi_tenant_saas — Is a shared SaaS offered? [partial]: Business and Enterprise are hosted, separately administered workspaces; implementation isolation was not tested. Sources: chatgpt:oa-business. - dedicated_instance — Is a dedicated single-tenant instance offered, from what size? [unknown]: Is a dedicated single-tenant instance offered, from what size? Unverified after checking ChatGPT Business/Enterprise plans, Work and residency documentation; dedicated instance, customer-cloud, full on-premises and air-gap thresholds not established. - customer_cloud — Can it run in the customer's own cloud account, from what size? [unknown]: Can it run in the customer's own cloud account, from what size? Unverified after checking ChatGPT Business/Enterprise plans, Work and residency documentation; dedicated instance, customer-cloud, full on-premises and air-gap thresholds not established. - on_premise — Can the whole platform run on customer infrastructure, from what size? [unknown]: Can the whole platform run on customer infrastructure, from what size? Unverified after checking ChatGPT Business/Enterprise plans, Work and residency documentation; dedicated instance, customer-cloud, full on-premises and air-gap thresholds not established. - air_gapped — Can it run without internet access? [unknown]: Can it run without internet access? Unverified after checking ChatGPT Business/Enterprise plans, Work and residency documentation; dedicated instance, customer-cloud, full on-premises and air-gap thresholds not established. - mode_feature_gaps — Which features are missing outside SaaS? [unknown]: Which features are missing outside SaaS? Unverified after checking ChatGPT Business/Enterprise plans, Work and residency documentation; dedicated instance, customer-cloud, full on-premises and air-gap thresholds not established. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: chatgpt:oa-business #### Claude Team / Enterprise Verification status: Agent cross-checked (agent-cross-checked) Support: partial Team/Enterprise are vendor-hosted workspaces; whole-platform private deployment is unverified. Availability: generally-available Delivery: native Scope: surfaces=Claude Team and Enterprise web workspaces, Claude desktop and mobile clients, Claude connectors and remote MCP integrations, Claude for Microsoft 365 official add-ins, Claude Cowork cloud and desktop task execution; version=Continuously updated commercial service, retrieved 2026-10-21; plan=Claude Team Standard/Premium versus current usage-based Enterprise; legacy Enterprise only when explicitly named; add_ons=Enterprise token usage at API rates, Optional US-only inference surcharge, External provider/app subscriptions and Office deployment approval where applicable, CMEK and compliance only on eligible Enterprise configurations; deployment_mode=multi-tenant-saas; region=Commercial supported regions; default global inference and US storage where documented; no EU/Swiss-only residency assumption; os=not specified. Limitations: - Local Cowork tasks, Desktop MCP and Office cloud credentials do not establish deployment of the whole hosted workspace. - multi_tenant_saas — Is a shared SaaS offered? [supported]: Team/Enterprise provide Anthropic-operated commercial SaaS; the DPA specifies logical separation of customer data. Sources: claude:cl-enterprise, claude:cl-dpa. - dedicated_instance — Is a dedicated single-tenant instance offered, from what size? [unknown]: Is a dedicated single-tenant instance offered, from what size? Unverified after checking commercial plans, DPA, remote MCP and Office cloud-credential documentation; dedicated instance, whole-platform customer cloud/on-premises, air-gap and feature/seat thresholds not verified. - customer_cloud — Can it run in the customer's own cloud account, from what size? [unknown]: Can it run in the customer's own cloud account, from what size? Unverified after checking commercial plans, DPA, remote MCP and Office cloud-credential documentation; dedicated instance, whole-platform customer cloud/on-premises, air-gap and feature/seat thresholds not verified. - on_premise — Can the whole platform run on customer infrastructure, from what size? [unknown]: Can the whole platform run on customer infrastructure, from what size? Unverified after checking commercial plans, DPA, remote MCP and Office cloud-credential documentation; dedicated instance, whole-platform customer cloud/on-premises, air-gap and feature/seat thresholds not verified. - air_gapped — Can it run without internet access? [unknown]: Can it run without internet access? Unverified after checking commercial plans, DPA, remote MCP and Office cloud-credential documentation; dedicated instance, whole-platform customer cloud/on-premises, air-gap and feature/seat thresholds not verified. - mode_feature_gaps — Which features are missing outside SaaS? [unknown]: Which features are missing outside SaaS? Unverified after checking commercial plans, DPA, remote MCP and Office cloud-credential documentation; dedicated instance, whole-platform customer cloud/on-premises, air-gap and feature/seat thresholds not verified. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: claude:cl-enterprise, claude:cl-dpa ### DATA-03: Training use and provider retention Judgment rule: Record whether customer content trains vendor or provider models, by plan and default; zero-data-retention arrangements with model providers; abuse-monitoring retention and human review; and the model provider's terms that apply. A "no training" claim on a marketing page is `vendor-claimed` until the contract or DPA says so. #### ChatGPT Business / Enterprise Verification status: Agent cross-checked (agent-cross-checked) Support: partial The business contract restricts content reuse; retention and human access remain separate. Availability: generally-available Delivery: native Scope: surfaces=ChatGPT Business and Enterprise web workspaces, ChatGPT desktop and mobile clients, ChatGPT connected apps and custom MCP apps; version=Continuously updated hosted service, retrieved 2026-10-21; plan=ChatGPT Business Standard/Premium versus Enterprise; Edu only where explicitly named for eligibility differences; add_ons=Purchased workspace credits or contracted token billing where stated, External app/provider subscriptions and Microsoft add-in approval where required, Enterprise residency, EKM and compliance entitlements only where stated; deployment_mode=multi-tenant-saas; region=Supported commercial regions; Europe means EEA + Switzerland when explicitly configured; app/client availability varies; os=not specified. Limitations: - Read each atomic answer for its plan, access and feature limits. - vendor_training — Does the vendor train on customer content? [supported]: Services Agreement 4.2 prohibits using customer content to develop/improve services without explicit agreement. Sources: chatgpt:oa-services. - provider_training — Do model providers train on it under this product's contracts? [partial]: The same business protection covers OpenAI model use; third-party app data handling needs its own terms. Sources: chatgpt:oa-services, chatgpt:oa-apps. - provider_retention — How long do model providers keep prompts, including for abuse monitoring? [partial]: Chat/workspace retention is not API zero-retention. Provider abuse/security retention is not fully quantified for every plan. Sources: chatgpt:oa-privacy. - zero_retention — Is zero data retention available, and on which plan? [partial]: Self-serve Business documentation directs zero-retention requirements to contracted offerings; ChatGPT-specific eligibility/terms were not obtained. Sources: chatgpt:oa-business. - human_review — Can provider staff review content? [partial]: Enterprise privacy limits authorized staff access by purpose; the subprocessor list also describes review of flagged content. This is not a no-human-access guarantee. Sources: chatgpt:oa-privacy, chatgpt:oa-subprocessors. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: chatgpt:oa-services, chatgpt:oa-apps, chatgpt:oa-privacy, chatgpt:oa-business, chatgpt:oa-subprocessors #### Claude Team / Enterprise Verification status: Agent cross-checked (agent-cross-checked) Support: partial Hosted commercial Chat/Cowork retention is separate from API/Code/provider ZDR arrangements and limited Fable exceptions. Availability: generally-available Delivery: native Scope: surfaces=Claude Team and Enterprise web workspaces, Claude desktop and mobile clients, Claude Cowork cloud and desktop task execution; version=Continuously updated commercial service, retrieved 2026-10-21; plan=Direct hosted Claude Team/Enterprise Chat and Cowork under Commercial Terms; API/ClaudeCode/third-party-provider ZDR routes discussed only as separate exceptions; add_ons=Standard hosted commercial retention; no assumed special ZDR agreement; deployment_mode=multi-tenant-saas; region=Commercial supported regions; default global inference and US storage where documented; no EU/Swiss-only residency assumption; os=not specified. Limitations: - Reconciliation: the Covered Model minimum is a default rule; its temporary agreement-based exception is conditional. The current route guide expressly excludes notified exception customers from the general ZDR-transition instructions. - No-training, saved history, safety-monitoring copies and specialized ZDR agreements are distinct. No sales contact or agreement signing. - vendor_training — Does the vendor train on customer content? [supported]: Commercial Terms section B prohibits training on Customer Content; the privacy guide describes explicit feedback/bug submissions as an exception to default no-training. Sources: claude:cl-terms, claude:cl-training. - provider_training — Do model providers train on it under this product's contracts? [partial]: Direct hosted Claude uses Anthropic models under its commercial no-training terms. Separate API, Office BYO cloud or third-party integrations require their own contracts and are outside this hosted inference finding. Sources: claude:cl-terms. - provider_retention — How long do model providers keep prompts, including for abuse monitoring? [partial]: Hosted saved commercial chats persist until deletion; normal backend deletion is within 30 days with safety/legal exceptions. Covered Models have an additional default minimum 30-day safety-retention rule; ordinary saved-chat history is not thereby limited to30 days. Sources: claude:cl-retention-r2, claude:cl-covered-r2. - zero_retention — Is zero data retention available, and on which plan? [partial]: The route guide says hosted Enterprise Chat/Cowork already operate with standard retention. Separately, Console/API, Enterprise Code and provider ZDR configurations follow their own rules. The default Covered Model rule has a limited temporary Fable exception for eligible notified/agreement-based internal business applications; no general hosted Chat/Cowork ZDR entitlement is established. Sources: claude:cl-covered-r2, claude:cl-covered-routes-r2. - human_review — Can provider staff review content? [partial]: Commercial confidentiality/DPA measures permit authorized, least-privileged personnel processing. The detailed approved-reviewer path concerns the described Covered Model retained-monitoring configurations; it is not a complete hosted-chat human-access map. No no-human-access guarantee is made. Sources: claude:cl-terms, claude:cl-dpa, claude:cl-covered-routes-r2. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: claude:cl-terms, claude:cl-training, claude:cl-retention-r2, claude:cl-covered-r2, claude:cl-covered-routes-r2, claude:cl-dpa ### DATA-04: Retention and deletion Judgment rule: Record default retention for chats, files, indexes and logs; admin-configured retention; user deletion; deletion after contract end; and deletion confirmation. #### ChatGPT Business / Enterprise Verification status: Agent cross-checked (agent-cross-checked) Support: partial Retention differs by content and operation: Enterprise/Edu policy, Business member removal, user deletion and conditional admin controls. Availability: generally-available Delivery: native Scope: surfaces=ChatGPT Business and Enterprise web workspaces, ChatGPT desktop and mobile clients, ChatGPT connected apps and custom MCP apps; version=Continuously updated hosted service, retrieved 2026-10-21; plan=ChatGPT Business Standard/Premium versus Enterprise; Edu only where explicitly named for eligibility differences; add_ons=Purchased workspace credits or contracted token billing where stated, External app/provider subscriptions and Microsoft add-in approval where required, Enterprise residency, EKM and compliance entitlements only where stated; deployment_mode=multi-tenant-saas; region=Supported commercial regions; Europe means EEA + Switzerland when explicitly configured; app/client availability varies; os=not specified. Limitations: - Member removal is not content deletion: project/GPT ownership reassignment does not grant access to the removed member's private conversations. - The broader Business privacy retention statement is recorded alongside the detailed operational gaps instead of being discarded or treated as an Enterprise-equivalent setting. - default_retention — What is retained and for how long by default? [supported]: Saved chats remain until deletion/applicable policy. The leaver guide specifically retains removed Business members' chats/files/canvas indefinitely; Enterprise/Edu leavers follow configured retention. This is removal behavior, not a complete Business admin-settings specification. Sources: chatgpt:oa-retention-r2, chatgpt:oa-leavers-r2. - admin_retention — Can admins set retention periods? [partial]: Enterprise/Edu configuration is documented. The privacy page says Business admins can control retention, and the managed-account notice makes controls configuration-dependent; the exact standalone Business setting, role, supported periods and content coverage were not verified. Sources: chatgpt:oa-leavers-r2, chatgpt:oa-privacy-r2, chatgpt:oa-managed-access-r2. - user_deletion — Can users delete their chats and files permanently? [partial]: Users delete saved chats and Library files separately; deletion is normally scheduled within30 days, with de-identification/legal/security exceptions and separate Enterprise inactive-file backup handling. Sources: chatgpt:oa-retention-r2. - contract_end_deletion — What is deleted at contract end, and when? [partial]: DPA 2.11 provides return/deletion on customer instruction after contract expiry, subject to legal retention; no fixed retrieval/deletion deadline is stated there. Sources: chatgpt:oa-dpa. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: chatgpt:oa-retention-r2, chatgpt:oa-leavers-r2, chatgpt:oa-privacy-r2, chatgpt:oa-managed-access-r2, chatgpt:oa-dpa #### Claude Team / Enterprise Verification status: Agent cross-checked (agent-cross-checked) Support: partial Current Enterprise retention guidance schedules deletion on save and removes content through a daily process, with project precedence and feature exclusions. Availability: generally-available Delivery: native Scope: surfaces=Claude Team and Enterprise web workspaces, Claude desktop and mobile clients, Claude Cowork cloud and desktop task execution; version=Continuously updated commercial service, retrieved 2026-10-21; plan=Team/Enterprise saved commercial Chat; Enterprise owner-configured Chat/project retention. Cowork is included only for documented project-activity effects, not blanket cloud-Code retention; add_ons=Enterprise token usage at API rates, Optional US-only inference surcharge, External provider/app subscriptions and Office deployment approval where applicable, CMEK and compliance only on eligible Enterprise configurations; deployment_mode=multi-tenant-saas; region=Commercial supported regions; default global inference and US storage where documented; no EU/Swiss-only residency assumption; os=not specified. Limitations: - Reconciliation: current English text is authoritative for this snapshot; the earlier cached immediate-deletion wording is superseded and is not a current factual claim. Scheduling on save does not mean instant physical deletion. - No retention/deletion fixture. Google Workspace add-in and the named excluded cloud features have separate retention behavior. - default_retention — What is retained and for how long by default? [partial]: Saved commercial chats persist until deletion; Enterprise chats/projects default to indefinite retention without configured periods. Incognito normally deletes within 30 days. Other file/index/log schedules are not fully mapped. Sources: claude:cl-retention-r2, claude:cl-retention-admin-r2. - admin_retention — Can admins set retention periods? [supported]: Enterprise Owners/Primary Owners set a minimum 30-day Chat/project period. Project retention overrides contained chats, including indefinite projects. Shortening a period schedules over-age data on save; a daily process can take several days. Design/Tag/Managed Agents and other cloud-Code features are excluded. Sources: claude:cl-retention-admin-r2. - user_deletion — Can users delete their chats and files permanently? [partial]: User-deleted chats leave visible history immediately and normally delete from backend within 30 days, subject to legal/safety exceptions. This is different from the daily custom-retention job. Sources: claude:cl-retention-r2. - contract_end_deletion — What is deleted at contract end, and when? [partial]: DPA H requires return on request within 30 days and deletion within 30 days after expiry/termination, except legal requirements, disputes or combating harmful use. Confirmation/copy completeness were not tested. Sources: claude:cl-dpa. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: claude:cl-retention-r2, claude:cl-retention-admin-r2, claude:cl-dpa ### DATA-05: Sub-processors and foreign-law exposure Judgment rule: Record the published sub-processor list with countries, change-notification rules, the vendor's and parent company's jurisdiction, transfer mechanisms (EU-US Data Privacy Framework, Swiss-US DPF, SCCs) and the vendor's documented position on foreign government access requests (e.g. US CLOUD Act). Record facts, not a legal assessment. #### ChatGPT Business / Enterprise Verification status: Agent cross-checked (agent-cross-checked) Support: partial A dated processor list and contractual transfer/notice rules are public. Availability: generally-available Delivery: native Scope: surfaces=ChatGPT Business and Enterprise web workspaces, ChatGPT desktop and mobile clients, ChatGPT connected apps and custom MCP apps; version=Continuously updated hosted service, retrieved 2026-10-21; plan=ChatGPT Business Standard/Premium versus Enterprise; Edu only where explicitly named for eligibility differences; add_ons=Purchased workspace credits or contracted token billing where stated, External app/provider subscriptions and Microsoft add-in approval where required, Enterprise residency, EKM and compliance entitlements only where stated; deployment_mode=multi-tenant-saas; region=Supported commercial regions; Europe means EEA + Switzerland when explicitly configured; app/client availability varies; os=not specified. Limitations: - subprocessor_countries: Examples include multi-country Microsoft/CoreWeave/Oracle/GCP infrastructure and US AWS; support/moderation processors have separate scopes. The list is not a workspace location guarantee. - parent_jurisdiction: EEA/Swiss customers contract with OpenAI Ireland Ltd; the list identifies US OpenAI affiliates. A complete current parent-entity chain was not independently verified. - subprocessor_list — Is a dated sub-processor list published? [supported]: OpenAI publishes a product-scoped list updated 2026-10-14. Sources: chatgpt:oa-subprocessors-20261026. - subprocessor_countries — Which countries do sub-processors operate in? [partial]: Examples include multi-country Microsoft/CoreWeave/Oracle/GCP infrastructure and US AWS; support/moderation processors have separate scopes. The list is not a workspace location guarantee. Sources: chatgpt:oa-subprocessors-20261026. - change_notification — Are customers notified of sub-processor changes? [supported]: DPA 2.9 gives notification and a 30-day objection period; subscribers can receive email. Sources: chatgpt:oa-dpa-20261026. - parent_jurisdiction — Which jurisdiction governs the vendor and its parent? [partial]: EEA/Swiss customers contract with OpenAI Ireland Ltd; the list identifies US OpenAI affiliates. A complete current parent-entity chain was not independently verified. Sources: chatgpt:oa-services-20261026, chatgpt:oa-subprocessors-20261026. - transfer_mechanism — Which transfer mechanism applies to non-EU/CH processing? [supported]: DPA 4.1 uses SCC safeguards or an applicable adequacy decision for transfers of EEA/Swiss data. Sources: chatgpt:oa-dpa-20261026. - government_access_policy — Is there a published government-access or transparency policy? [supported]: OpenAI publishes a Government User Data Request Policy and semiannual transparency reports from its official Trust and transparency page. Current listed reporting includes January–June 2026. Sources: chatgpt:chatgpt:government-transparency-20261026. Checked 2026-10-26; agent cross-checked 2026-10-26; check again by 2026-12-20. Sources: chatgpt:oa-subprocessors-20261026, chatgpt:oa-dpa-20261026, chatgpt:oa-services-20261026, chatgpt:chatgpt:government-transparency-20261026 #### Claude Team / Enterprise Verification status: Agent cross-checked (agent-cross-checked) Support: partial The DPA provides subprocessor and transfer rules; the current country list remains inaccessible in this pass. Availability: generally-available Delivery: native Scope: surfaces=Claude Team and Enterprise web workspaces, Claude desktop and mobile clients, Claude connectors and remote MCP integrations, Claude for Microsoft 365 official add-ins, Claude Cowork cloud and desktop task execution; version=Continuously updated commercial service, retrieved 2026-10-21; plan=Claude Team Standard/Premium versus current usage-based Enterprise; legacy Enterprise only when explicitly named; add_ons=Enterprise token usage at API rates, Optional US-only inference surcharge, External provider/app subscriptions and Office deployment approval where applicable, CMEK and compliance only on eligible Enterprise configurations; deployment_mode=multi-tenant-saas; region=Commercial supported regions; default global inference and US storage where documented; no EU/Swiss-only residency assumption; os=not specified. Limitations: - Unverified parts: subprocessor_countries. - Read each atomic answer for its plan, access and feature limits. - subprocessor_list — Is a dated sub-processor list published? [partial]: DPA Schedule 4 links to a published trust-portal list; its entries and revision were not extractable during retrieval. Sources: claude:cl-dpa, claude:cl-trust-route. - subprocessor_countries — Which countries do sub-processors operate in? [unknown]: Which countries do sub-processors operate in? Unverified after checking DPA Schedule 4, trust redirect and commercial terms; full current subprocessor countries, list date and ownership chain not retrieved. - change_notification — Are customers notified of sub-processor changes? [supported]: DPA C.3 provides notice before a new subprocessor gains data access and a 15-day objection window on reasonable privacy/security concerns. Sources: claude:cl-dpa. - parent_jurisdiction — Which jurisdiction governs the vendor and its parent? [partial]: Commercial Terms contract with Anthropic Ireland Limited for EEA/Swiss/UK customers and Anthropic PBC elsewhere; the ultimate ownership/entity chain was not independently established. Sources: claude:cl-terms. - transfer_mechanism — Which transfer mechanism applies to non-EU/CH processing? [supported]: DPA incorporates controller-to-processor/processor-to-processor SCCs and UK/Swiss schedules where applicable. Sources: claude:cl-dpa. - government_access_policy — Is there a published government-access or transparency policy? [supported]: Published policy requires valid process with emergency exceptions, reviews deficient requests, usually redirects enterprise requests to the customer and provides notice subject to exceptions. Sources: claude:cl-gov. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: claude:cl-dpa, claude:cl-trust-route, claude:cl-terms, claude:cl-gov ### DATA-06: Contracts and regulatory coverage Judgment rule: Record DPA availability and form (click-through, negotiable), reference to Swiss revDSG and GDPR, governing law and court, EU AI Act documentation (provider or deployer role, transparency materials), and sector-specific materials (FINMA outsourcing, banking secrecy, public sector). No compliance verdict. #### ChatGPT Business / Enterprise Verification status: Agent cross-checked (agent-cross-checked) Support: partial Business contracts and DPA are public; sector/legal conclusions remain outside this pass. Availability: generally-available Delivery: native Scope: surfaces=ChatGPT Business and Enterprise web workspaces, ChatGPT desktop and mobile clients, ChatGPT connected apps and custom MCP apps; version=Continuously updated hosted service, retrieved 2026-10-21; plan=ChatGPT Business Standard/Premium versus Enterprise; Edu only where explicitly named for eligibility differences; add_ons=Purchased workspace credits or contracted token billing where stated, External app/provider subscriptions and Microsoft add-in approval where required, Enterprise residency, EKM and compliance entitlements only where stated; deployment_mode=multi-tenant-saas; region=Supported commercial regions; Europe means EEA + Switzerland when explicitly configured; app/client availability varies; os=not specified. Limitations: - dpa: The Services Agreement incorporates the public DPA; negotiability is not established. - revdsg_gdpr: The DPA covers EEA and Swiss data and GDPR transfer provisions; a detailed revDSG obligation map was not performed. - ai_act_materials: A public customer AI Act guide links OpenAI’s governance framework, Codes of Practice approach and provenance material, and describes a request route for relevant model documentation. No gated materials were requested, and these resources do not establish a legal compliance verdict for a customer deployment. - sector_materials: The Services Agreement requires a healthcare addendum for protected health data. FINMA/banking-secrecy materials were not retrieved. - dpa — Is a DPA available, and is it negotiable? [partial]: The Services Agreement incorporates the public DPA; negotiability is not established. Sources: chatgpt:oa-services-20261026, chatgpt:oa-dpa-20261026. - revdsg_gdpr — Does the DPA cover revDSG and GDPR? [partial]: The DPA covers EEA and Swiss data and GDPR transfer provisions; a detailed revDSG obligation map was not performed. Sources: chatgpt:oa-dpa-20261026. - governing_law — Which law and court govern the contract? [supported]: For EEA/Swiss/UK customers, governing law is Ireland and venue Dublin under the standard agreement; contracting party differs for UK. Sources: chatgpt:oa-services-20261026. - ai_act_materials — Is EU AI Act documentation provided? [partial]: A public customer AI Act guide links OpenAI’s governance framework, Codes of Practice approach and provenance material, and describes a request route for relevant model documentation. No gated materials were requested, and these resources do not establish a legal compliance verdict for a customer deployment. Sources: chatgpt:chatgpt:eu-ai-act-resources-20261026. - sector_materials — Are FINMA or other sector materials provided? [partial]: The Services Agreement requires a healthcare addendum for protected health data. FINMA/banking-secrecy materials were not retrieved. Sources: chatgpt:oa-services-20261026. Checked 2026-10-26; agent cross-checked 2026-10-26; check again by 2026-12-20. Sources: chatgpt:oa-services-20261026, chatgpt:oa-dpa-20261026, chatgpt:chatgpt:eu-ai-act-resources-20261026 #### Claude Team / Enterprise Verification status: Agent cross-checked (agent-cross-checked) Support: partial Public commercial contracts include a DPA and Swiss transfer terms; this is not a regulatory suitability verdict. Availability: generally-available Delivery: native Scope: surfaces=Claude Team and Enterprise web workspaces, Claude desktop and mobile clients, Claude connectors and remote MCP integrations, Claude for Microsoft 365 official add-ins, Claude Cowork cloud and desktop task execution; version=Continuously updated commercial service, retrieved 2026-10-21; plan=Claude Team Standard/Premium versus current usage-based Enterprise; legacy Enterprise only when explicitly named; add_ons=Enterprise token usage at API rates, Optional US-only inference surcharge, External provider/app subscriptions and Office deployment approval where applicable, CMEK and compliance only on eligible Enterprise configurations; deployment_mode=multi-tenant-saas; region=Commercial supported regions; default global inference and US storage where documented; no EU/Swiss-only residency assumption; os=not specified. Limitations: - Generic confidentiality/DPA language does not establish a German section 203 or Swiss article 321 professional-secrecy undertaking. - dpa — Is a DPA available, and is it negotiable? [partial]: Commercial Terms incorporate the public DPA; standard acceptance is documented, while negotiability for this account was not verified. Sources: claude:cl-terms, claude:cl-dpa. - revdsg_gdpr — Does the DPA cover revDSG and GDPR? [supported]: DPA defines GDPR and includes a Swiss Addendum covering Swiss data protection laws and new/revised versions. Sources: claude:cl-dpa. - governing_law — Which law and court govern the contract? [supported]: For EEA/Swiss/UK customers, Terms M.7 specify Irish law and Irish courts for proceedings not subject to section J arbitration; specific orders may differ. Sources: claude:cl-terms. - ai_act_materials — Is EU AI Act documentation provided? [partial]: Provider materials describe transparency-code commitments, text watermarking and an eligible-organization detection API private preview. A complete deployer compliance pack was not inspected. Sources: claude:cl-ai-act. - sector_materials — Are FINMA or other sector materials provided? [partial]: Enterprise plan documentation lists HIPAA-ready configurations; scope/BAA conditions and FINMA/banking/public-sector materials were not fully retrieved. Sources: claude:cl-enterprise. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: claude:cl-terms, claude:cl-dpa, claude:cl-ai-act, claude:cl-enterprise ### DATA-07: Certifications and attestations Judgment rule: Record each certificate or report separately: ISO 27001, 27017, 27018, 27701, 42001; SOC 2 Type I/II with period; BSI C5; TISAX; national schemes. Record issuer, scope (which product and entity), validity and access route. A cloud provider's certificate does not certify the product. #### ChatGPT Business / Enterprise Verification status: Agent cross-checked (agent-cross-checked) Support: partial Trust-portal claims remain unverified certificate assertions. Availability: generally-available Delivery: native Scope: surfaces=ChatGPT Business and Enterprise web workspaces, ChatGPT desktop and mobile clients, ChatGPT connected apps and custom MCP apps; version=Continuously updated hosted service, retrieved 2026-10-21; plan=ChatGPT Business Standard/Premium versus Enterprise; Edu only where explicitly named for eligibility differences; add_ons=Purchased workspace credits or contracted token billing where stated, External app/provider subscriptions and Microsoft add-in approval where required, Enterprise residency, EKM and compliance entitlements only where stated; deployment_mode=multi-tenant-saas; region=Supported commercial regions; Europe means EEA + Switzerland when explicitly configured; app/client availability varies; os=not specified. Limitations: - All certification assertions use vendor-claimed evidence, never certificate-verified. - iso_27001 — ISO 27001 with scope and validity? [partial]: The portal lists ISO/IEC 27001:2022; issuer, precise certified scope and expiry were not inspected. Sources: chatgpt:oa-trust. - soc2 — SOC 2 type, period and covered service? [partial]: The portal claims SOC 2 Type 2; the actual report and reporting period were not reviewed. Sources: chatgpt:oa-trust. - c5 — BSI C5 attestation? [unknown]: BSI C5 attestation? Unverified after checking Trust Portal public index; no C5 attestation or certificate issuer/validity/period evidence. - other_certifications — Which other certificates (27701, 42001, TISAX)? [partial]: The portal lists 27017, 27018, 27701 and 42001; none is certificate-verified here. Sources: chatgpt:oa-trust. - report_access — How can customers obtain reports? [supported]: The public Trust Portal lists public/private documents and an access-request route; no access request was made. Sources: chatgpt:oa-trust. - pentest — Are independent penetration test summaries available? [partial]: A Pentest Report entry exists; the report scope and results were not retrieved. Sources: chatgpt:oa-trust. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: chatgpt:oa-trust #### Claude Team / Enterprise Verification status: Agent cross-checked (agent-cross-checked) Support: partial The DPA documents report and penetration-test access; actual certification scope and validity remain open. Availability: generally-available Delivery: native Scope: surfaces=Claude Team and Enterprise web workspaces, Claude desktop and mobile clients, Claude connectors and remote MCP integrations, Claude for Microsoft 365 official add-ins, Claude Cowork cloud and desktop task execution; version=Continuously updated commercial service, retrieved 2026-10-21; plan=Claude Team Standard/Premium versus current usage-based Enterprise; legacy Enterprise only when explicitly named; add_ons=Enterprise token usage at API rates, Optional US-only inference surcharge, External provider/app subscriptions and Office deployment approval where applicable, CMEK and compliance only on eligible Enterprise configurations; deployment_mode=multi-tenant-saas; region=Commercial supported regions; default global inference and US storage where documented; no EU/Swiss-only residency assumption; os=not specified. Limitations: - iso_27001: Anthropic publicly claims ISO 27001:2022 for its commercial products. The issuing body, full certificate scope and validity dates were not inspected; this is vendor-claimed evidence. - soc2: The commercial privacy page lists SOC 2 Type I and Type II. The auditor, report period and detailed service scope were not inspected. - c5: BSI C5 attestation? Unverified after checking public DPA and Trust Center; issuer, covered entity/product, period and validity of ISO/SOC/C5/other attestations were not verified. Search on 2026-10-26: https://www.anthropic.com/legal/data-processing-addendum, https://www.anthropic.com/legal/commercial-terms, https://trust.anthropic.com/. No additional scoped evidence established this answer. - other_certifications: The commercial privacy page claims ISO/IEC 42001:2023. No issuing-body certificate, validity dates or TISAX/ISO 27701 scope was inspected. - pentest: DPA Schedule 2 G.2 commits to annual external penetration tests and a customer-request summary; no summary or testing period was inspected. - iso_27001 — ISO 27001 with scope and validity? [partial]: Anthropic publicly claims ISO 27001:2022 for its commercial products. The issuing body, full certificate scope and validity dates were not inspected; this is vendor-claimed evidence. Sources: claude:claude:commercial-certifications-20261026. - soc2 — SOC 2 type, period and covered service? [partial]: The commercial privacy page lists SOC 2 Type I and Type II. The auditor, report period and detailed service scope were not inspected. Sources: claude:claude:commercial-certifications-20261026. - c5 — BSI C5 attestation? [unknown]: BSI C5 attestation? Unverified after checking public DPA and Trust Center; issuer, covered entity/product, period and validity of ISO/SOC/C5/other attestations were not verified. Search on 2026-10-26: https://www.anthropic.com/legal/data-processing-addendum, https://www.anthropic.com/legal/commercial-terms, https://trust.anthropic.com/. No additional scoped evidence established this answer. - other_certifications — Which other certificates (27701, 42001, TISAX)? [partial]: The commercial privacy page claims ISO/IEC 42001:2023. No issuing-body certificate, validity dates or TISAX/ISO 27701 scope was inspected. Sources: claude:claude:commercial-certifications-20261026. - report_access — How can customers obtain reports? [supported]: DPA F and Schedule 2 direct customers to the Trust Center and offer applicable reports/certificates on written request under confidentiality. No protected report was requested or downloaded. Sources: claude:cl-dpa-20261026. - pentest — Are independent penetration test summaries available? [partial]: DPA Schedule 2 G.2 commits to annual external penetration tests and a customer-request summary; no summary or testing period was inspected. Sources: claude:cl-dpa-20261026. Checked 2026-10-26; agent cross-checked 2026-10-26; check again by 2026-12-20. Sources: claude:cl-dpa-20261026, claude:claude:commercial-certifications-20261026 ### DATA-08: Encryption and key control Judgment rule: Record encryption at rest and in transit, customer-managed keys (BYOK/HYOK), key location, and private networking (private link, IP allow-lists, VPN). #### ChatGPT Business / Enterprise Verification status: Agent cross-checked (agent-cross-checked) Support: partial Encryption, optional Enterprise key control and IP restrictions are documented separately. Availability: generally-available Delivery: native Scope: surfaces=ChatGPT Business and Enterprise web workspaces, ChatGPT desktop and mobile clients, ChatGPT connected apps and custom MCP apps; version=Continuously updated hosted service, retrieved 2026-10-21; plan=ChatGPT Business Standard/Premium versus Enterprise; Edu only where explicitly named for eligibility differences; add_ons=Purchased workspace credits or contracted token billing where stated, External app/provider subscriptions and Microsoft add-in approval where required, Enterprise residency, EKM and compliance entitlements only where stated; deployment_mode=multi-tenant-saas; region=Supported commercial regions; Europe means EEA + Switzerland when explicitly configured; app/client availability varies; os=not specified. Limitations: - Unverified parts: tenant_isolation. - Read each atomic answer for its plan, access and feature limits. - encryption_at_rest — Is data encrypted at rest? [supported]: OpenAI states AES-256 at rest and TLS 1.2+ in transit. Sources: chatgpt:oa-privacy. - customer_managed_keys — Can the customer manage or hold the keys? [partial]: Eligible Enterprise/Edu EKM uses external AWS/GCP/Azure master keys and an account representative; feature coverage requires the EKM matrix. Sources: chatgpt:oa-ekm. - private_networking — Is private connectivity or IP restriction available? [partial]: Enterprise/Edu IP allowlists block off-list user traffic; the Compliance API has separate enforced policies. This does not establish private-link connectivity. Sources: chatgpt:oa-ip. - tenant_isolation — How are customers separated in shared SaaS? [unknown]: How are customers separated in shared SaaS? Unverified after checking enterprise privacy, EKM and IP documentation; tenant-isolation implementation and full key-location/feature matrix not tested. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: chatgpt:oa-privacy, chatgpt:oa-ekm, chatgpt:oa-ip #### Claude Team / Enterprise Verification status: Agent cross-checked (agent-cross-checked) Support: partial The DPA specifies encryption and logical isolation; Enterprise adds eligible customer keys and IP controls. Availability: generally-available Delivery: native Scope: surfaces=Claude Team and Enterprise web workspaces, Claude desktop and mobile clients, Claude connectors and remote MCP integrations, Claude for Microsoft 365 official add-ins, Claude Cowork cloud and desktop task execution; version=Continuously updated commercial service, retrieved 2026-10-21; plan=Claude Team Standard/Premium versus current usage-based Enterprise; legacy Enterprise only when explicitly named; add_ons=Enterprise token usage at API rates, Optional US-only inference surcharge, External provider/app subscriptions and Office deployment approval where applicable, CMEK and compliance only on eligible Enterprise configurations; deployment_mode=multi-tenant-saas; region=Commercial supported regions; default global inference and US storage where documented; no EU/Swiss-only residency assumption; os=not specified. Limitations: - Read each atomic answer for its plan, access and feature limits. - encryption_at_rest — Is data encrypted at rest? [supported]: DPA Schedule 2 E specifies at least AES-256 at rest and TLS 1.2+ over public networks. Sources: claude:cl-dpa. - customer_managed_keys — Can the customer manage or hold the keys? [partial]: Eligible Enterprise organizations can connect AWS/GCP/Azure KMS keys for specified content; key locations and all feature exclusions need account-specific verification. Sources: claude:cl-cmek. - private_networking — Is private connectivity or IP restriction available? [partial]: Enterprise IP CIDR allowlisting is enabled through support; externally shared artifacts can remain outside it. Private Link/VPN-only service endpoints were not established. Sources: claude:cl-ip. - tenant_isolation — How are customers separated in shared SaaS? [supported]: DPA Schedule 2 H specifies logical separation of customer data and network segmentation; no independent isolation test was performed. Sources: claude:cl-dpa. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: claude:cl-dpa, claude:cl-cmek, claude:cl-ip ### DATA-09: Professional secrecy Judgment rule: For professional secrecy holders (Berufsgeheimnisträger: lawyers, doctors, auditors, tax advisers) under § 203 StGB (DE) and Art. 321 StGB (CH), record whether the vendor signs a contractual secrecy undertaking or a § 203 agreement that binds its staff and its sub-processors; whether this comes as a dedicated offering or a paid add-on, and on which plan; who can access content in plain text (vendor staff, sub-processors, model providers); and the documentation provided. A DPA or a no-training clause alone is not a secrecy undertaking. Banking secrecy and FINMA outsourcing belong to DATA-06, not here. Record contract facts, not a legal assessment. #### ChatGPT Business / Enterprise Verification status: Agent cross-checked (agent-cross-checked) Support: partial Commercial confidentiality and authorized access rules are documented; no plan-specific professional-secrecy undertaking was retrieved. Availability: unknown Delivery: unknown Scope: surfaces=ChatGPT Business and Enterprise web workspaces, ChatGPT desktop and mobile clients, ChatGPT connected apps and custom MCP apps; version=Continuously updated hosted service, retrieved 2026-10-21; plan=ChatGPT Business Standard/Premium versus Enterprise; Edu only where explicitly named for eligibility differences; add_ons=Purchased workspace credits or contracted token billing where stated, External app/provider subscriptions and Microsoft add-in approval where required, Enterprise residency, EKM and compliance entitlements only where stated; deployment_mode=multi-tenant-saas; region=German §203 StGB and Swiss Art.321 StGB use cases; existing hosting, support and provider-location exceptions still apply.; os=not specified. Limitations: - General confidentiality, a DPA and no-training commitments do not establish a professional-secrecy undertaking. No vendor/sales contact or agreement signing was performed. - No legal compliance verdict; unknown does not mean the offering is unavailable. - secrecy_undertaking — Does the vendor sign a secrecy undertaking or § 203 StGB / Art. 321 StGB agreement covering its own staff? [unknown]: Does the vendor sign a secrecy undertaking or § 203 StGB / Art. 321 StGB agreement covering its own staff? Unverified after checking OpenAI Services Agreement confidentiality, DPA personnel/subprocessor clauses, Enterprise privacy, current subprocessor list and official searches for professional secrecy/§203/Art.321. No signed or public template agreement, dedicated offering, plan/add-on price or professional-secrecy obligation chain was retrieved; generic DPA/no-training language is insufficient. - subprocessor_coverage — Does the undertaking extend to its sub-processors, and is that documented? [unknown]: Does the undertaking extend to its sub-processors, and is that documented? Unverified after checking OpenAI Services Agreement confidentiality, DPA personnel/subprocessor clauses, Enterprise privacy, current subprocessor list and official searches for professional secrecy/§203/Art.321. No signed or public template agreement, dedicated offering, plan/add-on price or professional-secrecy obligation chain was retrieved; generic DPA/no-training language is insufficient. - secrecy_offering — Is it a dedicated offering or add-on, and on which plan? [unknown]: Is it a dedicated offering or add-on, and on which plan? Unverified after checking OpenAI Services Agreement confidentiality, DPA personnel/subprocessor clauses, Enterprise privacy, current subprocessor list and official searches for professional secrecy/§203/Art.321. No signed or public template agreement, dedicated offering, plan/add-on price or professional-secrecy obligation chain was retrieved; generic DPA/no-training language is insufficient. - content_access — Who can access content in plain text: vendor staff, sub-processors, model providers? [partial]: Enterprise privacy limits authorized staff access by purpose and the product-scoped subprocessor list includes review of flagged content. This is not a no-human-access commitment; a complete plain-text role/provider matrix and a §203/Art.321 access restriction were not verified. Sources: chatgpt:oa-privacy, chatgpt:oa-subprocessors, chatgpt:oa-dpa. - secrecy_documentation — Is the offering publicly documented (contract template, data-flow description, professional-body guidance)? [unknown]: Is the offering publicly documented (contract template, data-flow description, professional-body guidance)? Unverified after checking OpenAI Services Agreement confidentiality, DPA personnel/subprocessor clauses, Enterprise privacy, current subprocessor list and official searches for professional secrecy/§203/Art.321. No signed or public template agreement, dedicated offering, plan/add-on price or professional-secrecy obligation chain was retrieved; generic DPA/no-training language is insufficient. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: chatgpt:oa-privacy, chatgpt:oa-subprocessors, chatgpt:oa-dpa #### Claude Team / Enterprise Verification status: Agent cross-checked (agent-cross-checked) Support: partial Personnel confidentiality and controlled safety review are documented; a qualified professional-secrecy contract or add-on remains unverified. Availability: unknown Delivery: unknown Scope: surfaces=Claude Team and Enterprise web workspaces, Claude desktop and mobile clients, Claude connectors and remote MCP integrations, Claude for Microsoft 365 official add-ins, Claude Cowork cloud and desktop task execution; version=Continuously updated commercial service, retrieved 2026-10-21; plan=Claude Team Standard/Premium versus current usage-based Enterprise; legacy Enterprise only when explicitly named; add_ons=Enterprise token usage at API rates, Optional US-only inference surcharge, External provider/app subscriptions and Office deployment approval where applicable, CMEK and compliance only on eligible Enterprise configurations; deployment_mode=multi-tenant-saas; region=German §203 StGB and Swiss Art.321 StGB use cases; existing hosting, support and provider-location exceptions still apply.; os=not specified. Limitations: - General confidentiality, a DPA and no-training commitments do not establish a professional-secrecy undertaking. No vendor/sales contact or agreement signing was performed. - No legal compliance verdict; unknown does not mean the offering is unavailable. - secrecy_undertaking — Does the vendor sign a secrecy undertaking or § 203 StGB / Art. 321 StGB agreement covering its own staff? [unknown]: Does the vendor sign a secrecy undertaking or § 203 StGB / Art. 321 StGB agreement covering its own staff? Unverified after checking Commercial Terms E, DPA B.7/C.2 and technical measures, Trust Center, Covered Model access/retention rules and official searches for professional secrecy/§203/Art.321. No qualified staff undertaking, corresponding subprocessor undertaking chain, public contract template or dedicated plan/add-on was retrieved. - subprocessor_coverage — Does the undertaking extend to its sub-processors, and is that documented? [unknown]: Does the undertaking extend to its sub-processors, and is that documented? Unverified after checking Commercial Terms E, DPA B.7/C.2 and technical measures, Trust Center, Covered Model access/retention rules and official searches for professional secrecy/§203/Art.321. No qualified staff undertaking, corresponding subprocessor undertaking chain, public contract template or dedicated plan/add-on was retrieved. - secrecy_offering — Is it a dedicated offering or add-on, and on which plan? [unknown]: Is it a dedicated offering or add-on, and on which plan? Unverified after checking Commercial Terms E, DPA B.7/C.2 and technical measures, Trust Center, Covered Model access/retention rules and official searches for professional secrecy/§203/Art.321. No qualified staff undertaking, corresponding subprocessor undertaking chain, public contract template or dedicated plan/add-on was retrieved. - content_access — Who can access content in plain text: vendor staff, sub-processors, model providers? [partial]: Commercial Terms E and DPA B.7/Schedule2 constrain authorized personnel and subprocessor processing; Covered Model retained data can be accessed by approved safety reviewers through a logged controlled path. A complete subprocessor plain-text access matrix and §203/Art.321-specific restriction were not verified. Sources: claude:cl-terms, claude:cl-dpa, claude:cl-covered-review. - secrecy_documentation — Is the offering publicly documented (contract template, data-flow description, professional-body guidance)? [unknown]: Is the offering publicly documented (contract template, data-flow description, professional-body guidance)? Unverified after checking Commercial Terms E, DPA B.7/C.2 and technical measures, Trust Center, Covered Model access/retention rules and official searches for professional secrecy/§203/Art.321. No qualified staff undertaking, corresponding subprocessor undertaking chain, public contract template or dedicated plan/add-on was retrieved. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: claude:cl-terms, claude:cl-dpa, claude:cl-covered-review ## Commercials and vendor ### VEN-01: Pricing model and list prices Judgment rule: Record pricing unit (per seat, per active user, usage-based, platform fee, hybrid), list prices per plan in original currency with date, included usage and credits, add-on prices (connectors, agents, image generation) and overage rates. Cite public prices or dated quotes. Per-seat versus usage is a fact, not a quality judgment. #### ChatGPT Business / Enterprise Verification status: Agent cross-checked (agent-cross-checked) Support: partial Business has mixed seat pricing plus optional credits; Enterprise can use contracted credit or token billing. Availability: generally-available Delivery: native Scope: surfaces=ChatGPT Business and Enterprise web workspaces, ChatGPT desktop and mobile clients, ChatGPT connected apps and custom MCP apps; version=Continuously updated hosted service, retrieved 2026-10-21; plan=ChatGPT Business Standard/Premium versus Enterprise; Edu only where explicitly named for eligibility differences; add_ons=Purchased workspace credits or contracted token billing where stated, External app/provider subscriptions and Microsoft add-in approval where required, Enterprise residency, EKM and compliance entitlements only where stated; deployment_mode=multi-tenant-saas; region=Supported commercial regions; Europe means EEA + Switzerland when explicitly configured; app/client availability varies; os=not specified. Limitations: - Read each atomic answer for its plan, access and feature limits. - pricing_unit — What is the pricing unit? [supported]: Business combines Standard/Premium seats with optional workspace credit use. Enterprise pricing depends on its agreement. Sources: chatgpt:oa-business, chatgpt:oa-models. - list_prices — What are list prices per plan, with date and currency? [partial]: Retrieved 2026-10-21: Standard USD 20/user/month annual or USD 25 monthly; Premium USD 100 annual-equivalent or USD 125 monthly. Enterprise quote not obtained. Sources: chatgpt:oa-billing. - included_usage — What usage is included? [partial]: Premium has five times Standard included usage and no five-hour usage cap; allowances are task/model-dependent. Sources: chatgpt:oa-business. - add_ons — Which features cost extra? [partial]: Credits extend eligible use; external app subscriptions and optional contracted enterprise capabilities can affect total cost. Sources: chatgpt:oa-credit-controls. - overage — What do usage beyond limits and premium models cost? [partial]: Eligible activity can use workspace credits; Enterprise may bill tokens in USD. A complete scoped tariff/default workload was not priced. Sources: chatgpt:oa-credit-controls, chatgpt:oa-models. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: chatgpt:oa-business, chatgpt:oa-models, chatgpt:oa-billing, chatgpt:oa-credit-controls #### Claude Team / Enterprise Verification status: Agent cross-checked (agent-cross-checked) Support: partial Team bundles usage while current Enterprise separates seat access from all token usage. Availability: generally-available Delivery: native Scope: surfaces=Claude Team and Enterprise web workspaces, Claude desktop and mobile clients, Claude connectors and remote MCP integrations, Claude for Microsoft 365 official add-ins, Claude Cowork cloud and desktop task execution; version=Continuously updated commercial service, retrieved 2026-10-21; plan=Claude Team Standard/Premium versus current usage-based Enterprise; legacy Enterprise only when explicitly named; add_ons=Enterprise token usage at API rates, Optional US-only inference surcharge, External provider/app subscriptions and Office deployment approval where applicable, CMEK and compliance only on eligible Enterprise configurations; deployment_mode=multi-tenant-saas; region=Commercial supported regions; default global inference and US storage where documented; no EU/Swiss-only residency assumption; os=not specified. Limitations: - Read each atomic answer for its plan, access and feature limits. - pricing_unit — What is the pricing unit? [supported]: Team uses Standard/Premium seats with included limits; usage-based Enterprise uses access seats plus separate API-rate token consumption. Legacy Enterprise has different billing. Sources: claude:cl-pricing, claude:cl-enterprise. - list_prices — What are list prices per plan, with date and currency? [supported]: Retrieved 2026-10-21: Team Standard USD 20/month annual or USD 25 monthly; Premium USD 100 annual or USD 125 monthly. Enterprise USD 20/seat/month billed annually, before usage/tax. Sources: claude:cl-pricing, claude:cl-enterprise. - included_usage — What usage is included? [partial]: Team Premium advertises five times Standard usage; exact reproducible message/token quotas were not established. Current Enterprise includes no token usage. Sources: claude:cl-pricing, claude:cl-enterprise. - add_ons — Which features cost extra? [partial]: Enterprise model usage costs extra; applicable US-only inference adds 10%. Third-party services/credits and optional-service charges are not fully priced. Sources: claude:cl-enterprise, claude:cl-us-only. - overage — What do usage beyond limits and premium models cost? [partial]: Enterprise bills all usage at current API rates; Sonnet 5.5 list rate is USD 2/M input and USD 10/M output. Team/legacy overage and each tool surcharge were not exhaustively priced. Sources: claude:cl-enterprise, claude:cl-api-prices. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: claude:cl-pricing, claude:cl-enterprise, claude:cl-us-only, claude:cl-api-prices ### VEN-02: Scenario cost Judgment rule: Price three workloads for 12 months: 200, 1,000 and 5,000 users with a disclosed light/regular/power usage mix, in CHF and EUR excluding VAT. Include licences, platform fees, add-ons, model usage and, for self-hosted options, a stated operating assumption. Separate fixed, variable, included and unknown costs. No invented discounts. #### ChatGPT Business / Enterprise Verification status: Agent cross-checked (agent-cross-checked) Support: partial Only a 200-seat Business licence floor can be calculated; larger new deployments need an Enterprise quote. Availability: generally-available Delivery: native Scope: surfaces=ChatGPT Business and Enterprise web workspaces, ChatGPT desktop and mobile clients, ChatGPT connected apps and custom MCP apps; version=Continuously updated hosted service, retrieved 2026-10-21; plan=ChatGPT Business Standard/Premium versus Enterprise; Edu only where explicitly named for eligibility differences; add_ons=Purchased workspace credits or contracted token billing where stated, External app/provider subscriptions and Microsoft add-in approval where required, Enterprise residency, EKM and compliance entitlements only where stated; deployment_mode=multi-tenant-saas; region=Supported commercial regions; Europe means EEA + Switzerland when explicitly configured; app/client availability varies; os=not specified. Limitations: - ALM-14 shared cost assumptions v1.4, 2026-10-21: 60% light at 100, 30% regular at 400, 10% power at 1,500 messages/user/month; 3,000 input plus 600 output tokens/message only where separately billed. - ECB 2026-10-20: EUR 1 = USD 1.1215 = CHF 0.9237. Vendor USD is primary. Totals are floor + unknown; no proxy replaces an unknown vendor tariff. - cost_200 — Year-one cost at 200 users? [partial]: From USD 48000.00 + unknown, EUR 42799.82 + unknown or CHF 39534.20 + unknown for 12 months excluding VAT: 200 Standard seats at USD 20/month billed annually. No Premium seats, credits or discounts assumed; included allowance sufficiency is unverified. Sources: chatgpt:oa-billing, chatgpt:oa-services, chatgpt:fx-20261020. - cost_1000 — Year-one cost at 1,000 users? [unknown]: Unknown EUR/CHF total. New Business subscriptions are capped at 200 paid seats; no Enterprise seat/usage quote was obtained. No Business-price extrapolation is used. - cost_5000 — Year-one cost at 5,000 users? [unknown]: Unknown EUR/CHF total. New Business subscriptions are capped at 200 paid seats; no Enterprise seat/usage quote was obtained. No Business-price extrapolation is used. - variable_share — Which part depends on usage? [partial]: Credits after included allowances and Enterprise token-billed work depend on model/task consumption; that workload tariff remains unpriced. Sources: chatgpt:oa-credit-controls, chatgpt:oa-models. - unknown_parts — Which costs could not be priced? [partial]: Enterprise licence/commitment, included capacity, credit/token consumption, optional enterprise features and deployment/support services remain unpriced. Sources: chatgpt:oa-business. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: chatgpt:oa-billing, chatgpt:oa-services, chatgpt:fx-20261020, chatgpt:oa-credit-controls, chatgpt:oa-models, chatgpt:oa-business #### Claude Team / Enterprise Verification status: Agent cross-checked (agent-cross-checked) Support: partial Enterprise list-cost scenarios separate the USD 240 annual access seat floor from modeled Sonnet usage and unpriced services. Availability: generally-available Delivery: unknown Scope: surfaces=Claude Team and Enterprise web workspaces; version=Continuously updated commercial service, retrieved 2026-10-21; plan=Current usage-based Enterprise; standard global inference; admin-configured Sonnet 5.5 low-effort chat scenario; add_ons=All token usage at API list rates, Third-party services and implementation unpriced; deployment_mode=multi-tenant-saas; region=Commercial supported regions; default global inference and US storage where documented; no EU/Swiss-only residency assumption; os=not specified. Limitations: - All figures exclude VAT and invented discounts. Team is capped at 150 seats and is not extrapolated to these sizes. Annual Enterprise access commitment is separate from consumption. - cost_200 — Year-one cost at 200 users? [partial]: From USD 57,504.00 / EUR 51,274.19 / CHF 47,361.97 + unknown services under the disclosed Sonnet 5.5 low-effort chat workload: USD 48,000.00 access seats + USD 9,504.00 modeled tokens. The seat-only floor is USD 48,000.00 / EUR 42,799.82 / CHF 39,534.20. This is modeled list cost, not observed usage or a quote. Sources: claude:cl-enterprise, claude:cl-api-prices, claude:cl-consumption, claude:fx-20261020. - cost_1000 — Year-one cost at 1,000 users? [partial]: From USD 287,520.00 / EUR 256,370.93 / CHF 236,809.83 + unknown services under the disclosed Sonnet 5.5 low-effort chat workload: USD 240,000.00 access seats + USD 47,520.00 modeled tokens. The seat-only floor is USD 240,000.00 / EUR 213,999.11 / CHF 197,670.98. This is modeled list cost, not observed usage or a quote. Sources: claude:cl-enterprise, claude:cl-api-prices, claude:cl-consumption, claude:fx-20261020. - cost_5000 — Year-one cost at 5,000 users? [partial]: From USD 1,437,600.00 / EUR 1,281,854.66 / CHF 1,184,049.15 + unknown services under the disclosed Sonnet 5.5 low-effort chat workload: USD 1,200,000.00 access seats + USD 237,600.00 modeled tokens. The seat-only floor is USD 1,200,000.00 / EUR 1,069,995.54 / CHF 988,354.88. This is modeled list cost, not observed usage or a quote. Sources: claude:cl-enterprise, claude:cl-api-prices, claude:cl-consumption, claude:fx-20261020. - variable_share — Which part depends on usage? [supported]: ALM-14 shared cost assumptions v1.4, 2026-10-21: 12 months, 60% light 100/30% regular 400/10% power 1500 messages monthly = 330/user/month; 3000 input+600 billable output tokens/message incl retrieval/thinking. At Sonnet 5.5 USD 2/M input+USD 10/M output, 11.88M input+2.376M output/year costs USD 47.52/user; access USD 240 => modeled USD 287.52/user/year. Sonnet low effort is the scenario choice, with an admin-configurable default, based on the consumption guide; not a universal fixed default. Sources: claude:cl-consumption, claude:cl-api-prices, claude:cl-enterprise. - unknown_parts — Which costs could not be priced? [partial]: Unpriced: implementation, onboarding/support add-ons, third-party subscriptions and workflow-specific extra tool/context/repeated-step tokens. Scenario excludes US-only 1.1x premium, tax, discounts, cache/batch benefits and agent workloads beyond the fixed token allowance; these require separate pricing. EUR=USD/1.1215; CHF=EUR*0.9237, ECB 2026-10-20. Sources: claude:cl-enterprise, claude:cl-us-only, claude:cl-api-prices, claude:fx-20261020. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: claude:cl-enterprise, claude:cl-api-prices, claude:cl-consumption, claude:fx-20261020, claude:cl-us-only ### VEN-03: Evaluation access Judgment rule: Distinguish free tier, self-serve trial, sales-led pilot, paid proof of concept and open-source self-install. Record card requirement, duration, seat limit, and which features (SSO, connectors, admin) the trial includes. Map which shared scenarios can be run without sales approval. #### ChatGPT Business / Enterprise Verification status: Agent cross-checked (agent-cross-checked) Support: partial Business is self-serve; complete Enterprise evaluation remains sales-dependent and untested. Availability: generally-available Delivery: native Scope: surfaces=ChatGPT Business and Enterprise web workspaces, ChatGPT desktop and mobile clients, ChatGPT connected apps and custom MCP apps; version=Continuously updated hosted service, retrieved 2026-10-21; plan=ChatGPT Business Standard/Premium versus Enterprise; Edu only where explicitly named for eligibility differences; add_ons=Purchased workspace credits or contracted token billing where stated, External app/provider subscriptions and Microsoft add-in approval where required, Enterprise residency, EKM and compliance entitlements only where stated; deployment_mode=multi-tenant-saas; region=Supported commercial regions; Europe means EEA + Switzerland when explicitly configured; app/client availability varies; os=not specified. Limitations: - Unverified parts: self_serve_trial, trial_scope. - Read each atomic answer for its plan, access and feature limits. - free_tier — Is there a free tier for business use? [partial]: A personal Free plan exists, but Business starts with paid seats and a separate managed workspace. Free does not establish Business/Enterprise controls. Sources: chatgpt:oa-business-faq, chatgpt:oa-word. - self_serve_trial — Is a self-serve business trial available? [unknown]: Is a self-serve business trial available? Unverified after checking Business overview, FAQ and public pricing; timed self-serve trial duration, card requirement and trial governance were not verified. - trial_scope — Do trials include SSO, connectors and admin features? [unknown]: Do trials include SSO, connectors and admin features? Unverified after checking Business overview, FAQ and public pricing; timed self-serve trial duration, card requirement and trial governance were not verified. - sales_gate — Does meaningful evaluation require sales contact? [partial]: Business signup is self-serve; Enterprise upgrades and contracted options are directed to sales. No contact was made. Sources: chatgpt:oa-business, chatgpt:oa-business-faq. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: chatgpt:oa-business-faq, chatgpt:oa-word, chatgpt:oa-business #### Claude Team / Enterprise Verification status: Agent cross-checked (agent-cross-checked) Support: partial Commercial self-service purchase is documented; free consumer access is not a scoped Enterprise trial. Availability: generally-available Delivery: native Scope: surfaces=Claude Team and Enterprise web workspaces, Claude desktop and mobile clients, Claude connectors and remote MCP integrations, Claude for Microsoft 365 official add-ins, Claude Cowork cloud and desktop task execution; version=Continuously updated commercial service, retrieved 2026-10-21; plan=Claude Team Standard/Premium versus current usage-based Enterprise; legacy Enterprise only when explicitly named; add_ons=Enterprise token usage at API rates, Optional US-only inference surcharge, External provider/app subscriptions and Office deployment approval where applicable, CMEK and compliance only on eligible Enterprise configurations; deployment_mode=multi-tenant-saas; region=Commercial supported regions; default global inference and US storage where documented; no EU/Swiss-only residency assumption; os=not specified. Limitations: - Unverified parts: self_serve_trial, trial_scope. - Read each atomic answer for its plan, access and feature limits. - free_tier — Is there a free tier for business use? [partial]: Claude Free is a separate consumer plan; no free Team/Enterprise organization entitlement was established. Sources: claude:cl-pricing. - self_serve_trial — Is a self-serve business trial available? [unknown]: Is a self-serve business trial available? Unverified after checking pricing and Enterprise acquisition guides; no self-serve business trial duration, card rule or trial identity/compliance/connector inclusion confirmed. - trial_scope — Do trials include SSO, connectors and admin features? [unknown]: Do trials include SSO, connectors and admin features? Unverified after checking pricing and Enterprise acquisition guides; no self-serve business trial duration, card rule or trial identity/compliance/connector inclusion confirmed. - sales_gate — Does meaningful evaluation require sales contact? [supported]: Team can be bought self-serve. Enterprise self-serve starts at 20 seats; sales-assisted Enterprise starts at 50. No purchase or sales contact was performed. Sources: claude:cl-enterprise. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: claude:cl-pricing, claude:cl-enterprise ### VEN-04: Contract terms and pricing transparency Judgment rule: Record minimum seats or commitment, contract length, monthly versus annual billing, price-change rules, cancellation and downgrade terms, and invoicing in CHF/EUR. Classify pricing as transparent, partially specified, quote-only or unknown, naming the missing fields. Quote-only pricing is a disclosed constraint. #### ChatGPT Business / Enterprise Verification status: Agent cross-checked (agent-cross-checked) Support: partial Business terms are public; Enterprise pricing and commercial scope need a quote. Availability: generally-available Delivery: native Scope: surfaces=ChatGPT Business and Enterprise web workspaces, ChatGPT desktop and mobile clients, ChatGPT connected apps and custom MCP apps; version=Continuously updated hosted service, retrieved 2026-10-21; plan=ChatGPT Business Standard/Premium versus Enterprise; Edu only where explicitly named for eligibility differences; add_ons=Purchased workspace credits or contracted token billing where stated, External app/provider subscriptions and Microsoft add-in approval where required, Enterprise residency, EKM and compliance entitlements only where stated; deployment_mode=multi-tenant-saas; region=Supported commercial regions; Europe means EEA + Switzerland when explicitly configured; app/client availability varies; os=not specified. Limitations: - Read each atomic answer for its plan, access and feature limits. - minimum_commitment — What seat or spend minimum applies? [supported]: New Business workspaces require at least two Standard/Premium seats and allow at most 200 paid seats since 2026-08-24; grandfathered workspaces differ. Sources: chatgpt:oa-business-faq. - contract_length — What contract lengths are offered? [supported]: Business supports monthly or annual billing; Enterprise term is on its order form. Sources: chatgpt:oa-billing, chatgpt:oa-services. - cancellation — How can the contract be cancelled or reduced? [partial]: Business seat reductions take effect next billing cycle. Contracted renewal reductions normally need 30-day notice under the standard agreement. Sources: chatgpt:oa-billing, chatgpt:oa-services. - local_invoicing — Can it be invoiced in CHF or EUR from a European entity? [partial]: EEA/Swiss customers have an Irish contracting party; self-serve invoice/PO/bank-transfer requirements are directed to a contracted plan. Exact CHF/EUR billing availability was not established. Sources: chatgpt:oa-services, chatgpt:oa-business. - transparency_class — Is pricing transparent, partial, quote-only or unknown? [partial]: Business seat pricing is public but usage remains partly specified; Enterprise total is quote-only in this pass. Sources: chatgpt:oa-business. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: chatgpt:oa-business-faq, chatgpt:oa-billing, chatgpt:oa-services, chatgpt:oa-business #### Claude Team / Enterprise Verification status: Agent cross-checked (agent-cross-checked) Support: partial Seat prices are public, with plan caps, annual Enterprise commitment and variable usage. Availability: generally-available Delivery: native Scope: surfaces=Claude Team and Enterprise web workspaces, Claude desktop and mobile clients, Claude connectors and remote MCP integrations, Claude for Microsoft 365 official add-ins, Claude Cowork cloud and desktop task execution; version=Continuously updated commercial service, retrieved 2026-10-21; plan=Claude Team Standard/Premium versus current usage-based Enterprise; legacy Enterprise only when explicitly named; add_ons=Enterprise token usage at API rates, Optional US-only inference surcharge, External provider/app subscriptions and Office deployment approval where applicable, CMEK and compliance only on eligible Enterprise configurations; deployment_mode=multi-tenant-saas; region=Commercial supported regions; default global inference and US storage where documented; no EU/Swiss-only residency assumption; os=not specified. Limitations: - Read each atomic answer for its plan, access and feature limits. - minimum_commitment — What seat or spend minimum applies? [supported]: Team: 2-150 seats. Current Enterprise self-serve: 20-seat minimum; sales-assisted: 50. Sources: claude:cl-pricing, claude:cl-enterprise. - contract_length — What contract lengths are offered? [supported]: Team lists monthly and annual billing; Enterprise access seats are annual. Consumption is additional under the purchase route. Sources: claude:cl-pricing, claude:cl-enterprise. - cancellation — How can the contract be cancelled or reduced? [partial]: General Terms I.2 permit customer termination with notice and vendor convenience termination with30-day notice; annual seat refunds, reductions and renewal cancellation depend on plan/order and were not verified. Sources: claude:cl-terms. - local_invoicing — Can it be invoiced in CHF or EUR from a European entity? [partial]: Enterprise self-serve bills USD by credit/ACH; sales-assisted supports multicurrency/invoicing. Irish contracting is stated for Swiss/EEA customers, but a CHF/EUR invoice tariff was not verified. Sources: claude:cl-enterprise, claude:cl-terms. - transparency_class — Is pricing transparent, partial, quote-only or unknown? [partial]: Partially specified: public seat/API rates and minimums, but actual consumption, third-party services, Enterprise optional charges and local invoice terms require more detail. Sources: claude:cl-enterprise, claude:cl-api-prices. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: claude:cl-pricing, claude:cl-enterprise, claude:cl-terms, claude:cl-api-prices ### VEN-05: Source licence Judgment rule: Record licence per component (client, server, connectors, hosted extensions) and revision. Distinguish OSI open source, source-available with restrictions (branding clauses, user caps), and closed. Repository visibility is not a licence classification. Licences change between releases: record the current terms, and never carry a fork's historical licence over to the upstream product or the reverse. #### ChatGPT Business / Enterprise Verification status: Agent cross-checked (agent-cross-checked) Support: partial The hosted service is provided under commercial access terms; a component source-licence inventory was not verified. Availability: generally-available Delivery: native Scope: surfaces=ChatGPT Business and Enterprise web workspaces, ChatGPT desktop and mobile clients, ChatGPT connected apps and custom MCP apps; version=Continuously updated hosted service, retrieved 2026-10-21; plan=ChatGPT Business Standard/Premium versus Enterprise; Edu only where explicitly named for eligibility differences; add_ons=Purchased workspace credits or contracted token billing where stated, External app/provider subscriptions and Microsoft add-in approval where required, Enterprise residency, EKM and compliance entitlements only where stated; deployment_mode=multi-tenant-saas; region=Supported commercial regions; Europe means EEA + Switzerland when explicitly configured; app/client availability varies; os=not specified. Limitations: - Unverified parts: enterprise_features_closed. - Read each atomic answer for its plan, access and feature limits. - licence_type — Which licence applies to each component? [partial]: Services Agreement grants a term-limited non-exclusive service-use right and restricts reverse engineering; no OSI licence for the hosted workspace was established. Sources: chatgpt:oa-services. - branding_restrictions — Do licence terms restrict branding or user counts? [partial]: Account resale/sharing and rate-limit circumvention are contractually restricted; component-specific branding terms were not retrieved. Sources: chatgpt:oa-services. - enterprise_features_closed — Are enterprise features in a separate closed edition? [unknown]: Are enterprise features in a separate closed edition? Unverified after checking Services Agreement; repository visibility of SDKs/examples does not establish the hosted product source licence. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: chatgpt:oa-services #### Claude Team / Enterprise Verification status: Agent cross-checked (agent-cross-checked) Support: partial Commercial service rights are public; a complete component-source licence inventory was not established. Availability: generally-available Delivery: native Scope: surfaces=Claude Team and Enterprise web workspaces, Claude desktop and mobile clients, Claude connectors and remote MCP integrations, Claude for Microsoft 365 official add-ins, Claude Cowork cloud and desktop task execution; version=Continuously updated commercial service, retrieved 2026-10-21; plan=Claude Team Standard/Premium versus current usage-based Enterprise; legacy Enterprise only when explicitly named; add_ons=Enterprise token usage at API rates, Optional US-only inference surcharge, External provider/app subscriptions and Office deployment approval where applicable, CMEK and compliance only on eligible Enterprise configurations; deployment_mode=multi-tenant-saas; region=Commercial supported regions; default global inference and US storage where documented; no EU/Swiss-only residency assumption; os=not specified. Limitations: - Unverified parts: branding_restrictions, enterprise_features_closed. - Read each atomic answer for its plan, access and feature limits. - licence_type — Which licence applies to each component? [partial]: Commercial Terms grant service use and allocate customer input/output rights; this does not establish an OSI licence for the hosted platform, clients or connector code. Sources: claude:cl-terms. - branding_restrictions — Do licence terms restrict branding or user counts? [unknown]: Do licence terms restrict branding or user counts? Unverified after checking Commercial Terms and public Claude Code issue repository; component revisions, client/server/connector source licences, branding restrictions and separate enterprise-edition source status not verified. - enterprise_features_closed — Are enterprise features in a separate closed edition? [unknown]: Are enterprise features in a separate closed edition? Unverified after checking Commercial Terms and public Claude Code issue repository; component revisions, client/server/connector source licences, branding restrictions and separate enterprise-edition source status not verified. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: claude:cl-terms ### VEN-06: Data export and exit Judgment rule: Record admin export of chats, assistants, knowledge bases, prompts and audit logs, formats, export completeness, user self-export, and what survives contract end. Run an admin export on a trial. Exported chats alone do not make assistants and knowledge portable. #### ChatGPT Business / Enterprise Verification status: Agent cross-checked (agent-cross-checked) Support: partial Business restricts member self-export but documents conditional owner exports; Enterprise/Edu Compliance retrieval is separate. Availability: generally-available Delivery: native Scope: surfaces=ChatGPT Business and Enterprise web workspaces, ChatGPT desktop and mobile clients, ChatGPT connected apps and custom MCP apps; version=Continuously updated hosted service, retrieved 2026-10-21; plan=ChatGPT Business Standard/Premium versus Enterprise; Edu only where explicitly named for eligibility differences; add_ons=Purchased workspace credits or contracted token billing where stated, External app/provider subscriptions and Microsoft add-in approval where required, Enterprise residency, EKM and compliance entitlements only where stated; deployment_mode=multi-tenant-saas; region=Supported commercial regions; Europe means EEA + Switzerland when explicitly configured; app/client availability varies; os=not specified. Limitations: - The documented Business owner export is conditional and per member; the guide does not establish a bulk workspace export or complete archive. - Enterprise/Edu Compliance retrieval is not a complete portable workspace export. No admin archive or exit fixture. - chat_export — Can admins export all chats? [partial]: Business members cannot self-export workspace data through Settings > Data controls. An owner can select the Business workspace > Members > member three-dot menu > Export data, if available, to export that member's data. Bulk all-chat coverage is unverified. Enterprise/Edu owners can separately grant Compliance conversation access. Sources: chatgpt:oa-business-faq-r2, chatgpt:oa-business-owner-export-r3, chatgpt:oa-compliance-r2. - assistant_export — Can assistants and prompts be exported in a reusable format? [unknown]: Can assistants and prompts be exported in a reusable format? Unverified after checking Business FAQ, Compliance Platform and DPA; no complete assistant/knowledge export or leaver exit fixture. - knowledge_export — Can knowledge bases and their sources be exported? [unknown]: Can knowledge bases and their sources be exported? Unverified after checking Business FAQ, Compliance Platform and DPA; no complete assistant/knowledge export or leaver exit fixture. - export_format — Are formats documented and machine-readable? [partial]: Enterprise/Edu has documented compliance log/state API access. No complete Business admin archive format or reusable chat/assistant/knowledge package was verified. Sources: chatgpt:oa-compliance-r2. - post_termination_window — How long can data be retrieved after termination? [partial]: The DPA provides return/deletion on instruction after expiry but no fixed recovery window was verified. Sources: chatgpt:oa-dpa. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: chatgpt:oa-business-faq-r2, chatgpt:oa-business-owner-export-r3, chatgpt:oa-compliance-r2, chatgpt:oa-dpa #### Claude Team / Enterprise Verification status: Agent cross-checked (agent-cross-checked) Support: partial Team/Enterprise exports provide conversations but do not prove portable assistants and knowledge. Availability: generally-available Delivery: native Scope: surfaces=Claude Team and Enterprise web workspaces, Claude desktop and mobile clients, Claude connectors and remote MCP integrations, Claude for Microsoft 365 official add-ins, Claude Cowork cloud and desktop task execution; version=Continuously updated commercial service, retrieved 2026-10-21; plan=Claude Team Standard/Premium versus current usage-based Enterprise; legacy Enterprise only when explicitly named; add_ons=Enterprise token usage at API rates, Optional US-only inference surcharge, External provider/app subscriptions and Office deployment approval where applicable, CMEK and compliance only on eligible Enterprise configurations; deployment_mode=multi-tenant-saas; region=Commercial supported regions; default global inference and US storage where documented; no EU/Swiss-only residency assumption; os=not specified. Limitations: - chat_export: Team/Enterprise Primary Owners export organization conversation/user data, excluding deleted items. Members can export their own chats if enabled; uploaded-file contents are excluded. - assistant_export: Can assistants and prompts be exported in a reusable format? Unverified after checking organization/member export and Compliance API docs; no export fixture, reusable assistant/prompts or complete knowledge-base/source-file package verified. Search on 2026-10-26: https://support.claude.com/en/articles/13346720-export-your-organization-s-data, https://support.claude.com/en/articles/9450526-export-your-claude-data, https://support.claude.com/en/articles/13015708-access-the-compliance-api. No additional scoped evidence established this answer. - knowledge_export: The organization export guide covers conversation/user data and excludes generated Office/PDF files; members’ personal exports exclude uploaded-file contents. A complete reusable project/knowledge-source archive was not established and no export fixture was run. - export_format: Documented exports and Compliance API support structured access; the complete archive schema/file manifest was not downloaded or inspected. - chat_export — Can admins export all chats? [partial]: Team/Enterprise Primary Owners export organization conversation/user data, excluding deleted items. Members can export their own chats if enabled; uploaded-file contents are excluded. Sources: claude:cl-export-org-20261026, claude:cl-export-user-20261026. - assistant_export — Can assistants and prompts be exported in a reusable format? [unknown]: Can assistants and prompts be exported in a reusable format? Unverified after checking organization/member export and Compliance API docs; no export fixture, reusable assistant/prompts or complete knowledge-base/source-file package verified. Search on 2026-10-26: https://support.claude.com/en/articles/13346720-export-your-organization-s-data, https://support.claude.com/en/articles/9450526-export-your-claude-data, https://support.claude.com/en/articles/13015708-access-the-compliance-api. No additional scoped evidence established this answer. - knowledge_export — Can knowledge bases and their sources be exported? [partial]: The organization export guide covers conversation/user data and excludes generated Office/PDF files; members’ personal exports exclude uploaded-file contents. A complete reusable project/knowledge-source archive was not established and no export fixture was run. Sources: claude:cl-export-org-20261026, claude:cl-export-user-20261026. - export_format — Are formats documented and machine-readable? [partial]: Documented exports and Compliance API support structured access; the complete archive schema/file manifest was not downloaded or inspected. Sources: claude:cl-export-org-20261026, claude:cl-compliance-20261026. - post_termination_window — How long can data be retrieved after termination? [supported]: DPA H requires a return request within 30 days after expiry/termination, with deletion obligations and legal/dispute/harmful-use exceptions. Sources: claude:cl-dpa-20261026. Checked 2026-10-26; agent cross-checked 2026-10-26; check again by 2026-12-20. Sources: claude:cl-export-org-20261026, claude:cl-export-user-20261026, claude:cl-compliance-20261026, claude:cl-dpa-20261026 ### VEN-07: Support and service levels Judgment rule: Record support channels, languages (German, French, Italian), hours and time zone, local or regional presence, documented response times, uptime SLA and credits, public status page and incident history. Popularity is not a reliability score. #### ChatGPT Business / Enterprise Verification status: Agent cross-checked (agent-cross-checked) Support: partial A public component status page is available; language-specific support and SLA credits remain unverified. Availability: generally-available Delivery: native Scope: surfaces=ChatGPT Business and Enterprise web workspaces, ChatGPT desktop and mobile clients, ChatGPT connected apps and custom MCP apps; version=Continuously updated hosted service, retrieved 2026-10-21; plan=ChatGPT Business Standard/Premium versus Enterprise; Edu only where explicitly named for eligibility differences; add_ons=Purchased workspace credits or contracted token billing where stated, External app/provider subscriptions and Microsoft add-in approval where required, Enterprise residency, EKM and compliance entitlements only where stated; deployment_mode=multi-tenant-saas; region=Supported commercial regions; Europe means EEA + Switzerland when explicitly configured; app/client availability varies; os=not specified. Limitations: - support_channels: The Business FAQ directs workspace credit-usage questions to OpenAI Support. For affected Enterprise GPT migrations, the migration FAQ directs customers to their account team to confirm the applicable timeline. General Enterprise support coverage, service hours and response targets remain unverified. - support_languages: Is support available in German, French or Italian? Unverified after checking OpenAI Status, Business FAQ and Services Agreement; DE/FR/IT support, regional support staffing and applicable SLA credits not verified. Search on 2026-10-26: https://help.openai.com/en/articles/8542115-chatgpt-business-general-faq, https://status.openai.com/, https://help.openai.com/en/articles/8792828-chatgpt-business-overview. No additional scoped evidence established this answer. - regional_presence: OpenAI’s May 2025 company announcement records a Munich office and German local team. Current staffing, a Swiss contracting entity and guaranteed local-language support were not established. - uptime_sla: Is there an uptime SLA with credits? Unverified after checking OpenAI Status, Business FAQ and Services Agreement; DE/FR/IT support, regional support staffing and applicable SLA credits not verified. Search on 2026-10-26: https://help.openai.com/en/articles/8542115-chatgpt-business-general-faq, https://status.openai.com/, https://help.openai.com/en/articles/8792828-chatgpt-business-overview. No additional scoped evidence established this answer. - support_channels — Which support channels are available on each plan? [partial]: The Business FAQ directs workspace credit-usage questions to OpenAI Support. For affected Enterprise GPT migrations, the migration FAQ directs customers to their account team to confirm the applicable timeline. General Enterprise support coverage, service hours and response targets remain unverified. Sources: chatgpt:chatgpt:review-fix-support-channel-20261026, chatgpt:chatgpt:review-fix-gpt-creation-freeze-20261026. - support_languages — Is support available in German, French or Italian? [unknown]: Is support available in German, French or Italian? Unverified after checking OpenAI Status, Business FAQ and Services Agreement; DE/FR/IT support, regional support staffing and applicable SLA credits not verified. Search on 2026-10-26: https://help.openai.com/en/articles/8542115-chatgpt-business-general-faq, https://status.openai.com/, https://help.openai.com/en/articles/8792828-chatgpt-business-overview. No additional scoped evidence established this answer. - regional_presence — Is there a DACH or Swiss entity, team or partner? [partial]: OpenAI’s May 2025 company announcement records a Munich office and German local team. Current staffing, a Swiss contracting entity and guaranteed local-language support were not established. Sources: chatgpt:chatgpt:german-office-20261026. - uptime_sla — Is there an uptime SLA with credits? [unknown]: Is there an uptime SLA with credits? Unverified after checking OpenAI Status, Business FAQ and Services Agreement; DE/FR/IT support, regional support staffing and applicable SLA credits not verified. Search on 2026-10-26: https://help.openai.com/en/articles/8542115-chatgpt-business-general-faq, https://status.openai.com/, https://help.openai.com/en/articles/8792828-chatgpt-business-overview. No additional scoped evidence established this answer. - status_page — Is there a public status page with history? [supported]: OpenAI Status lists component health and incident updates; no historical uptime score was computed. Sources: chatgpt:oa-status-20261026. Checked 2026-10-26; agent cross-checked 2026-10-26; check again by 2026-12-20. Sources: chatgpt:oa-business-faq-20261026, chatgpt:oa-status-20261026, chatgpt:chatgpt:german-office-20261026, chatgpt:chatgpt:review-fix-support-channel-20261026, chatgpt:chatgpt:review-fix-gpt-creation-freeze-20261026 #### Claude Team / Enterprise Verification status: Agent cross-checked (agent-cross-checked) Support: partial Public support/status channels exist; local-language commitments and contractual SLA remain unverified. Availability: generally-available Delivery: native Scope: surfaces=Claude Team and Enterprise web workspaces, Claude desktop and mobile clients, Claude connectors and remote MCP integrations, Claude for Microsoft 365 official add-ins, Claude Cowork cloud and desktop task execution; version=Continuously updated commercial service, retrieved 2026-10-21; plan=Claude Team Standard/Premium versus current usage-based Enterprise; legacy Enterprise only when explicitly named; add_ons=Enterprise token usage at API rates, Optional US-only inference surcharge, External provider/app subscriptions and Office deployment approval where applicable, CMEK and compliance only on eligible Enterprise configurations; deployment_mode=multi-tenant-saas; region=Commercial supported regions; default global inference and US storage where documented; no EU/Swiss-only residency assumption; os=not specified. Limitations: - support_channels: Help Center support is available; Enterprise self-serve and sales-assisted support/CSM arrangements differ. Exact response times/hours were not established. - support_languages: Is support available in German, French or Italian? Unverified after checking Enterprise support comparison, official Help Center, status history and Commercial Terms; DE/FR/IT support guarantees, DACH/Swiss staffing, response targets and uptime/credit SLA not verified. Search on 2026-10-26: https://support.claude.com/en/articles/9797531-what-is-the-enterprise-plan, https://status.claude.com/, https://claude.com/pricing. No additional scoped evidence established this answer. - regional_presence: Anthropic’s November 2025 company announcement identifies an existing Zurich office and planned Munich expansion. Current staffing, Swiss contracting terms and local-language support guarantees were not established. - uptime_sla: Is there an uptime SLA with credits? Unverified after checking Enterprise support comparison, official Help Center, status history and Commercial Terms; DE/FR/IT support guarantees, DACH/Swiss staffing, response targets and uptime/credit SLA not verified. Search on 2026-10-26: https://support.claude.com/en/articles/9797531-what-is-the-enterprise-plan, https://status.claude.com/, https://claude.com/pricing. No additional scoped evidence established this answer. - support_channels — Which support channels are available on each plan? [partial]: Help Center support is available; Enterprise self-serve and sales-assisted support/CSM arrangements differ. Exact response times/hours were not established. Sources: claude:cl-enterprise-20261026. - support_languages — Is support available in German, French or Italian? [unknown]: Is support available in German, French or Italian? Unverified after checking Enterprise support comparison, official Help Center, status history and Commercial Terms; DE/FR/IT support guarantees, DACH/Swiss staffing, response targets and uptime/credit SLA not verified. Search on 2026-10-26: https://support.claude.com/en/articles/9797531-what-is-the-enterprise-plan, https://status.claude.com/, https://claude.com/pricing. No additional scoped evidence established this answer. - regional_presence — Is there a DACH or Swiss entity, team or partner? [partial]: Anthropic’s November 2025 company announcement identifies an existing Zurich office and planned Munich expansion. Current staffing, Swiss contracting terms and local-language support guarantees were not established. Sources: claude:claude:regional-presence-20261026. - uptime_sla — Is there an uptime SLA with credits? [unknown]: Is there an uptime SLA with credits? Unverified after checking Enterprise support comparison, official Help Center, status history and Commercial Terms; DE/FR/IT support guarantees, DACH/Swiss staffing, response targets and uptime/credit SLA not verified. Search on 2026-10-26: https://support.claude.com/en/articles/9797531-what-is-the-enterprise-plan, https://status.claude.com/, https://claude.com/pricing. No additional scoped evidence established this answer. - status_page — Is there a public status page with history? [supported]: status.claude.com publishes component health and incident history; it is not a contractual reliability score. Sources: claude:cl-status-20261026. Checked 2026-10-26; agent cross-checked 2026-10-26; check again by 2026-12-20. Sources: claude:cl-enterprise-20261026, claude:cl-status-20261026, claude:claude:regional-presence-20261026 ### VEN-08: Onboarding, training and adoption Judgment rule: Record vendor-led onboarding, admin training, end-user training (live, e-learning, languages), use-case libraries, champion programmes, change-management materials and their cost. Distinguish included services from paid professional services and partner offerings. #### ChatGPT Business / Enterprise Verification status: Agent cross-checked (agent-cross-checked) Support: partial Public learning and implementation guidance are available; included service entitlements remain open. Availability: generally-available Delivery: native Scope: surfaces=ChatGPT Business and Enterprise web workspaces, ChatGPT desktop and mobile clients, ChatGPT connected apps and custom MCP apps; version=Continuously updated hosted service, retrieved 2026-10-21; plan=ChatGPT Business Standard/Premium versus Enterprise; Edu only where explicitly named for eligibility differences; add_ons=Purchased workspace credits or contracted token billing where stated, External app/provider subscriptions and Microsoft add-in approval where required, Enterprise residency, EKM and compliance entitlements only where stated; deployment_mode=multi-tenant-saas; region=Supported commercial regions; Europe means EEA + Switzerland when explicitly configured; app/client availability varies; os=not specified. Limitations: - Unverified parts: onboarding_service, service_cost. - Read each atomic answer for its plan, access and feature limits. - onboarding_service — Is guided onboarding included? [unknown]: Is guided onboarding included? Unverified after checking Academy and Enterprise quickstart; guided onboarding entitlement and professional-service fees not obtained. - user_training — Is end-user training offered, in which languages? [partial]: Academy offers worker/builder/leader courses and live/on-demand events; DE/FR/IT delivery was not established. Sources: chatgpt:oa-academy. - use_case_library — Are role-based use cases and templates provided? [partial]: Academy and Enterprise quickstart provide role/use-case and deployment guidance; a complete template catalogue was not audited. Sources: chatgpt:oa-academy, chatgpt:oa-admin-quickstart. - adoption_programme — Is there a champion or adoption programme? [partial]: Academy includes leadership/adoption learning; an included formal champion programme was not verified. Sources: chatgpt:oa-academy. - service_cost — Which services cost extra? [unknown]: Which services cost extra? Unverified after checking Academy and Enterprise quickstart; guided onboarding entitlement and professional-service fees not obtained. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: chatgpt:oa-academy, chatgpt:oa-admin-quickstart #### Claude Team / Enterprise Verification status: Agent cross-checked (agent-cross-checked) Support: partial Academy tutorials and use-case material are public; commercial service entitlements need clarification. Availability: generally-available Delivery: native Scope: surfaces=Claude Team and Enterprise web workspaces, Claude desktop and mobile clients, Claude connectors and remote MCP integrations, Claude for Microsoft 365 official add-ins, Claude Cowork cloud and desktop task execution; version=Continuously updated commercial service, retrieved 2026-10-21; plan=Claude Team Standard/Premium versus current usage-based Enterprise; legacy Enterprise only when explicitly named; add_ons=Enterprise token usage at API rates, Optional US-only inference surcharge, External provider/app subscriptions and Office deployment approval where applicable, CMEK and compliance only on eligible Enterprise configurations; deployment_mode=multi-tenant-saas; region=Commercial supported regions; default global inference and US storage where documented; no EU/Swiss-only residency assumption; os=not specified. Limitations: - Unverified parts: onboarding_service, adoption_programme, service_cost. - Read each atomic answer for its plan, access and feature limits. - onboarding_service — Is guided onboarding included? [unknown]: Is guided onboarding included? Unverified after checking Academy, pricing and Enterprise comparison; included guided onboarding, champion programme, paid professional-services scope and charges not established. - user_training — Is end-user training offered, in which languages? [partial]: Claude Academy provides written/video training for chat, Cowork, Office, connectors and skills; German/French/Italian delivery was not established. Sources: claude:cl-academy. - use_case_library — Are role-based use cases and templates provided? [partial]: Academy has workflow/tutorial examples and Office use cases; the library was not exhaustively mapped to organizational roles. Sources: claude:cl-academy. - adoption_programme — Is there a champion or adoption programme? [unknown]: Is there a champion or adoption programme? Unverified after checking Academy, pricing and Enterprise comparison; included guided onboarding, champion programme, paid professional-services scope and charges not established. - service_cost — Which services cost extra? [unknown]: Which services cost extra? Unverified after checking Academy, pricing and Enterprise comparison; included guided onboarding, champion programme, paid professional-services scope and charges not established. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: claude:cl-academy ## Sources ### chatgpt:oa-files Uploading files and audio to ChatGPT. Uploads have format-specific limits, 40-file Business/Enterprise projects, 20-file GPT knowledge and Enterprise-only PDF visual retrieval. - URL: https://help.openai.com/en/articles/8555545-uploading-files-and-audio-to-chatgpt - Locator: Formats; size/rate/storage limits; projects; PDF visual retrieval - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### chatgpt:oa-business-models-r2 ChatGPT Business models and limits. Business distinguishes GPT6 Chat powered by Sol/Astra from separate Work models, with Standard/Premium allowances and rollout limits. - URL: https://help.openai.com/en/articles/12003714-chatgpt-business-models-and-limits - Locator: Chat picker; Higher intelligence; Pro; Work models - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### chatgpt:oa-enterprise-models-r2 ChatGPT Enterprise and Edu models and limits. Enterprise Chat names GPT6 powered by Sol and Pro/Astra, while Work has separate model options and workspace/role controls. - URL: https://help.openai.com/en/articles/11165333-chatgpt-enterprise-and-edu-models-and-limits - Locator: Enterprise Chat rollout; Work/Codex distinction; model picker; tools - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### chatgpt:oa-work-r2 ChatGPT Work and Codex. Work has its own model picker and task/output capabilities; Chat-specific model guides define the GPT6 Chat alias rather than Work model labels. - URL: https://help.openai.com/en/articles/20001275-chatgpt-work-and-codex - Locator: Work deliverables; picker; access and permissions - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### claude:claude:fable-plan-20261026 Claude Fable models on your plan. Fable 5/5.1 are available on paid plans. Team/legacy Enterprise Premium include a capped share of weekly usage; Standard uses paid usage credits. Current usage-based Enterprise bills at API rates. Organization model access can restrict availability. - URL: https://support.claude.com/en/articles/15424964-claude-fable-models-on-your-plan - Locator: How Fable models work on each plan and model-picker access; HTTP 200, body SHA256 c7e39ae19952ae2186de8c95a8034bd16a43b7da9e5b6750eca0b7c30614456a - Evidence kind: documented - Source date: 2026-09-02 - Retrieved: 2026-10-26 ### claude:claude:transparent-fallback-20261026 Claude Fable automatic model switching. Hosted Fable safety fallbacks rerun requests on an Opus model with a visible switch notice and response model label. Users can disable automatic switching. This is a safety fallback, not general task-based multi-provider routing. - URL: https://support.claude.com/en/articles/15363606-why-claude-switched-models-in-your-conversation-with-fable-5-or-fable-5-1 - Locator: What happens after a fallback, settings and where switching applies; HTTP 200, body SHA256 98a2769ab04b54a170b3034afde3b042c016f76ccd332e98c4065288a60ea846 - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-26 ### claude:cl-model-menu-r2-20261026 Change the model, effort, and thinking settings. The chat-selector guide names model families and effort controls but does not provide a complete Team seat-tier or per-product entitlement matrix. - URL: https://support.claude.com/en/articles/8664678-change-the-model-effort-and-thinking-settings - Locator: Chat selector; supported effort models; Enterprise restrictions; retrieved without credentials with Python3 requests, HTTP 200, body SHA256 74026587f919fac61d5fc3f4747ea1c889b2d3b2b6b2ee895dfbcc2dfae25cae on 2026-10-26 - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-26 ### claude:cl-context-plans-r2-20261026 Context windows on paid Claude plans. The paid-plan guide distinguishes Chat and Cowork context/model tables; it does not guarantee every model on each Team seat tier or Office add-in. - URL: https://support.claude.com/en/articles/8606394-how-large-is-the-context-window-on-paid-claude-plans - Locator: Paid-plan scope; separate Chat and Cowork tables; retrieved without credentials with Python3 requests, HTTP 200, body SHA256 6f8fa356708c3a887106e33876dea65b71a3a9dae2ec09600ef035e14cb448e4 on 2026-10-26 - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-26 ### claude:cl-upload-r2-20261026 Upload files to Claude. The attachment guide specifies500 MB chat uploads,30 MB project files, and separate PDF visual/text behavior; these are not universal tool-path limits. - URL: https://support.claude.com/en/articles/8241126-upload-files-to-claude - Locator: Chat attachments versus project Files; PDF handling; retrieved without credentials with Python3 requests, HTTP 200, body SHA256 640974fd8725ee528375e7fca7fe66265f94a30fb0c82071022d3da529b437ed on 2026-10-26 - Evidence kind: documented - Source date: 2026-07-23 - Retrieved: 2026-10-26 ### claude:cl-pricing-20261026 Claude pricing. Team is listed for 2-150 seats with Standard/Premium pricing; current Enterprise lists USD 20/seat/month annual access plus usage and a 20-seat self-serve minimum. - URL: https://claude.com/pricing - Locator: Team/Enterprise cards; commercial comparison; retrieved without credentials with Python3 requests, HTTP 200, body SHA256 9dac8ef940d7d07738f28ea203879b59cd98dfefd0bef624a91b361049a23a9f on 2026-10-26 - Evidence kind: vendor-claimed - Source date: Not stated - Retrieved: 2026-10-26 ### claude:cl-model-control-20261026 Manage model access for your organization. Enterprise controls model/effort access by organization and custom role, while Haiku cannot be disabled and coverage has named exceptions. - URL: https://support.claude.com/en/articles/15694740-manage-model-access-for-your-organization - Locator: Organization and custom-role ceilings; Haiku exception; coverage; retrieved without credentials with Python3 requests, HTTP 200, body SHA256 449e547e02b145fe3878d3591a80eca230ddff996580d601b38f007b78aba179 on 2026-10-26 - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-26 ### chatgpt:oa-enterprise-notes ChatGPT Enterprise and Edu release notes. Dated Enterprise/Edu notes record live-app migration, collaboration and add-in changes, Intune eligibility and planned GPT retirement. - URL: https://help.openai.com/en/articles/10128477-chatgpt-enterprise-and-edu-release-notes - Locator: October 16 sync retirement; September 25 Teams; September GPT migration; May 6 Intune - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### chatgpt:oa-business-notes ChatGPT Business release notes. Dated Business notes document workspace analytics, Excel/Sheets integration, agent/work changes and app-template access. - URL: https://help.openai.com/en/articles/11391654-chatgpt-business-release-notes - Locator: April 16 analytics; May 5 Sheets; May 22 agents; July 9 Work - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### claude:cl-release Claude release notes. Dated notes distinguish current models, cloud/unified Cowork rollout, memory defaults and connector changes. - URL: https://support.claude.com/en/articles/12138966-release-notes - Locator: Model launches; memory; Office/connector changes; Cowork transition - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### claude:cl-haiku-notice Claude Haiku 4.5 is leaving the model selector. The dated consumer Haiku retirement excludes Team/Enterprise, so it does not prove removal from their model catalogue. - URL: https://support.claude.com/en/articles/17444146-claude-haiku-4-5-is-leaving-the-model-selector - Locator: October 15 notice; October 29 removal; Team/Enterprise exceptions - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### claude:cl-office Claude for Microsoft 365. Claude advertises native Excel/PowerPoint/Word add-ins, Outlook beta and optional Foundry/Bedrock/Gemini Enterprise Agent Platform credentials. - URL: https://claude.com/claude-for-microsoft-365 - Locator: App capabilities; GA/beta; cloud credentials; review controls - Evidence kind: vendor-claimed - Source date: Not stated - Retrieved: 2026-10-21 ### chatgpt:oa-business ChatGPT Business - Overview. Business is self-serve with Standard/Premium seats, includes Chat/Work, and remains separate from API billing. - URL: https://help.openai.com/en/articles/8792828-chatgpt-business-overview - Locator: Standard/Premium seats; plan comparison; Team rename - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### chatgpt:oa-admin-quickstart ChatGPT Enterprise admin quickstart. Enterprise rollout uses SSO, tenant directory sync, groups/RBAC and workspace-specific product access. - URL: https://help.openai.com/en/articles/20001264-chatgpt-enterprise-admin-quickstart - Locator: Identity; SCIM; groups; controls; billing - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### chatgpt:oa-admin-settings Managing workspace settings in ChatGPT Enterprise. Enterprise settings include model defaults, role-scoped features/memory and a recurring AI-policy modal. - URL: https://help.openai.com/en/articles/8411955-managing-workspace-settings-in-chatgpt-enterprise - Locator: General; permissions; models; AI policy modal - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### chatgpt:oa-models ChatGPT Enterprise and Edu models and limits. Enterprise Chat is rolling to GPT-6 powered by Sol with a separate Astra Pro control; Work has distinct model choices and RBAC eligibility. - URL: https://help.openai.com/en/articles/11165333-chatgpt-enterprise-and-edu-models-and-limits - Locator: GPT-6 Chat; Work models; routing; Astra controls - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### chatgpt:oa-credit-controls Managing credits and spend controls in ChatGPT Business. Business can apply credit usage and recharge limits after included seat allowances, with credit-backed features unavailable when credits are insufficient. - URL: https://help.openai.com/en/articles/20001155-managing-credits-and-spend-controls-in-chatgpt-business - Locator: Included use; recharge cap; per-seat/user limits - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### claude:cl-enterprise What is the Enterprise plan?. Current Enterprise has no included tokens, bills all usage at API rates and differs from legacy seat-based arrangements. - URL: https://support.claude.com/en/articles/9797531-what-is-the-enterprise-plan - Locator: Pricing; self-serve versus sales-assisted; legacy sections - Evidence kind: documented - Source date: 2026-09-01 - Retrieved: 2026-10-21 ### claude:cl-model-control-r2 Manage model access for your organization. Enterprise model and effort access uses organization ceilings/custom roles; Haiku cannot be disabled and product/version limits apply. - URL: https://support.claude.com/en/articles/15694740-manage-model-access-for-your-organization - Locator: Enterprise eligibility; role ceilings; Haiku; fallback/coverage - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### claude:cl-default-r2 Set a default model for your organization. Enterprise defaults are distinct from the beta forced-start switch, which preserves existing chat-project choices and permits in-chat changes. - URL: https://support.claude.com/en/articles/15330088-set-a-default-model-for-your-organization - Locator: Ordinary defaults; Always start beta; projects and product fallback - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### chatgpt:oa-analysis Data analysis with ChatGPT. Analysis uses a stateful Jupyter/Python environment, supports chart generation and cannot make external network requests from that environment. - URL: https://help.openai.com/en/articles/8437071-data-analysis-with-chatgpt - Locator: Python execution; charts; network constraint - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### claude:cl-rag Retrieval augmented generation for projects. Paid projects automatically switch to retrieval when knowledge approaches context limits and show a RAG indicator. - URL: https://support.claude.com/en/articles/11473015-retrieval-augmented-generation-rag-for-projects - Locator: Activation; search tool; context indicator - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### claude:cl-upload-r2 Upload files to Claude. The attachment guide specifies500 MB chat uploads,30 MB project files, and separate PDF visual/text behavior; these are not universal tool-path limits. - URL: https://support.claude.com/en/articles/8241126-upload-files-to-claude - Locator: Chat attachments versus project Files; PDF handling - Evidence kind: documented - Source date: 2026-07-23 - Retrieved: 2026-10-21 ### claude:cl-code-files-r2 Create and edit files with Claude. Chat code/file tools create Office/PDF output and document a30 MB upload/download path; the same page has inconsistent Team egress defaults. - URL: https://support.claude.com/en/articles/12111783-create-and-edit-files-with-claude - Locator: Availability; computing/file-tool limits; file output; network sections - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### chatgpt:oa-projects Projects in ChatGPT. Projects persist chats/files/instructions; shared members can read and download project files and branch chats. - URL: https://help.openai.com/en/articles/10169521-projects-in-chatgpt - Locator: Sharing; visibility; memory; GPT use; retention - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### claude:cl-upload Upload files to Claude. The page distinguishes 500 MB chat uploads, 30 MB project files and PDF visual processing up to 100 pages. - URL: https://support.claude.com/en/articles/8241126-upload-files-to-claude - Locator: Formats; chat/project limits; visual PDF processing - Evidence kind: documented - Source date: 2026-07-23 - Retrieved: 2026-10-21 ### claude:cl-projects What are projects?. Projects persist selected knowledge/instructions and provide organization sharing with view/edit permissions. - URL: https://support.claude.com/en/articles/9517075-what-are-projects - Locator: Knowledge; instructions; Team/Enterprise collaboration - Evidence kind: documented - Source date: 2026-07-23 - Retrieved: 2026-10-21 ### claude:cl-groups Manage groups and group spend limits on Enterprise plans. Enterprise groups support roles and shared resources, per-user limits and optional shared monthly budgets in beta. - URL: https://support.claude.com/en/articles/13799932-manage-groups-and-group-spend-limits-on-enterprise-plans - Locator: Group sharing; SCIM; role controls; budgets - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### chatgpt:oa-sharepoint SharePoint app and setup in ChatGPT. Live SharePoint searches accessible SharePoint/OneDrive content and uses Microsoft consent plus separate ChatGPT action and site controls. - URL: https://help.openai.com/en/articles/12143177-sharepoint-app-and-setup-in-chatgpt - Locator: Live access; delegated permissions; site allowlist; labels; file limits - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### chatgpt:oa-apps Connected apps in ChatGPT. Apps use workspace and account permissions, can support actions and events, and have separate plugin installation and provider authorization. - URL: https://help.openai.com/en/articles/11487775-connected-apps-in-chatgpt - Locator: Availability; authorization; actions; event tasks - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### chatgpt:oa-mcp Developer mode and MCP apps in ChatGPT. Custom remote MCP apps support write tools in beta with plan-specific developer/publishing controls and action approvals. - URL: https://help.openai.com/en/articles/12584461-developer-mode-and-full-mcp-connectors-in-chatgpt - Locator: Beta availability; Business versus Enterprise/Edu; remote connections; actions - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### chatgpt:oa-team-tasks Creating and managing team tasks in ChatGPT. Business/Enterprise team tasks run in the cloud under a team service account using approved connections and scheduled or supported app-event triggers. - URL: https://help.openai.com/en/articles/20001540-creating-and-managing-team-tasks-in-chatgpt - Locator: Availability; service account; triggers; control; sharing - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### claude:claude:atlassian-enterprise-20261026 Enterprise-managed authorization for MCP connectors. Claude Enterprise documents generally available organization-managed authorization through Okta for named MCP providers including Atlassian. Its Atlassian section names Jira, Confluence and Teamwork Graph. - URL: https://claude.com/blog/enterprise-managed-auth - Locator: August 24 GA update and Atlassian Rovo MCP description; HTTP 200, body SHA256 5d973cd85982883fc28f409f6919e829a1e3791223634ca167e12524c411284e - Evidence kind: documented - Source date: 2026-08-24 - Retrieved: 2026-10-26 ### claude:cl-mcp-20261026 Get started with custom connectors using remote MCP. Remote MCP originates from Anthropic cloud, can use per-user OAuth or shared credentials, and differs from Desktop-local MCP. - URL: https://support.claude.com/en/articles/11175166-get-started-with-custom-connectors-using-remote-mcp - Locator: Network route; owner publication; OAuth/request headers; local distinction; retrieved without credentials with Python3 requests, HTTP 200, body SHA256 e6307ff6f907b387075c5f8db3a45fae8cf8ea9eb15fd576b44f3368e1c5ed43 on 2026-10-26 - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-26 ### claude:cl-release-20261026 Claude release notes. Dated notes distinguish current models, cloud/unified Cowork rollout, memory defaults and connector changes. - URL: https://support.claude.com/en/articles/12138966-release-notes - Locator: Model launches; memory; Office/connector changes; Cowork transition; retrieved without credentials with Python3 requests, HTTP 200, body SHA256 07f9dcfff3c0fc1f7a6060ad0b718558075286175f3b4e1b13c665d79cab3616 on 2026-10-26 - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-26 ### claude:cl-enterprise-20261026 What is the Enterprise plan?. Current Enterprise has no included tokens, bills all usage at API rates and differs from legacy seat-based arrangements. - URL: https://support.claude.com/en/articles/9797531-what-is-the-enterprise-plan - Locator: Pricing; self-serve versus sales-assisted; legacy sections; retrieved without credentials with Python3 requests, HTTP 200, body SHA256 de2b461205d4426c558e88750f5be23f7d495804c407827fc5695ecd5e1a20ee on 2026-10-26 - Evidence kind: documented - Source date: 2026-09-01 - Retrieved: 2026-10-26 ### claude:cl-m365-20261026 Microsoft 365 connector security guide. The Anthropic-hosted Microsoft Graph proxy retrieves on demand without file-content caching and has separately enabled write tools and delegated permissions. - URL: https://support.claude.com/en/articles/12684923-microsoft-365-connector-security-guide - Locator: On-demand proxy; delegated permissions; consent; write controls; retrieved without credentials with Python3 requests, HTTP 200, body SHA256 8965fd2ee1dbdd7b494b834a1cbae1cd4194bf096abd2d916244178108738d3f on 2026-10-26 - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-26 ### claude:cl-google-20261026 Use Google Workspace connectors. Google connectors retrieve user-authorized data, sync referenced Google Docs and support live editing with separate app controls. - URL: https://support.claude.com/en/articles/10166901-use-google-workspace-connectors - Locator: Sources; private project sync; live Docs/Sheets/Slides; authorization; retrieved without credentials with Python3 requests, HTTP 200, body SHA256 b61eb14f3e2efb4ab2a9cc441eb6beb363b5514d3c55e6f9dc8cd2565d48d135 on 2026-10-26 - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-26 ### chatgpt:oa-company-r2 Company knowledge in ChatGPT. Current Company Knowledge uses enabled eligible app connections for Business/Enterprise/Edu and inherits source access without claiming a universal copied index. - URL: https://help.openai.com/en/articles/12628342-company-knowledge-in-chatgpt - Locator: Current app-based workflow; plans; source permissions - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### chatgpt:oa-sharepoint-r2 SharePoint app and setup in ChatGPT. The live app uses Microsoft delegated access and separately enabled actions; site-policy controls need workspace enablement rather than inheriting a blanket plan entitlement. - URL: https://help.openai.com/en/articles/12143177-sharepoint-app-and-setup-in-chatgpt - Locator: Live app; Microsoft permissions; action enablement - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### chatgpt:oa-sharepoint-policy-r2 Managing SharePoint site access and sensitivity-label exclusions. The guide documents enabled-workspace site/label controls but does not state a complete Business/Enterprise/Edu entitlement matrix. - URL: https://help.openai.com/en/articles/20001502-managing-sharepoint-site-access-and-sensitivity-label-exclusions - Locator: Availability; site-collection rules; label GUIDs - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### claude:cl-m365 Microsoft 365 connector security guide. The Anthropic-hosted Microsoft Graph proxy retrieves on demand without file-content caching and has separately enabled write tools and delegated permissions. - URL: https://support.claude.com/en/articles/12684923-microsoft-365-connector-security-guide - Locator: On-demand proxy; delegated permissions; consent; write controls - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### claude:cl-m365-user Connect to Microsoft 365. Microsoft 365 connects SharePoint/OneDrive/Outlook/Teams, excludes Sites.Selected allowlisting and OneNote reads, and requires organizational consent. - URL: https://support.claude.com/en/articles/15183774-connect-to-microsoft-365 - Locator: Setup; supported content; site restrictions; permissions - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### claude:cl-google Use Google Workspace connectors. Google connectors retrieve user-authorized data, sync referenced Google Docs and support live editing with separate app controls. - URL: https://support.claude.com/en/articles/10166901-use-google-workspace-connectors - Locator: Sources; private project sync; live Docs/Sheets/Slides; authorization - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### chatgpt:oa-residency-r2 Data residency and inference residency for ChatGPT. Current residency guidance describes scoped content/processing and external-app exceptions; it no longer establishes an administrator-managed sync configuration. - URL: https://help.openai.com/en/articles/9903489-data-residency-and-inference-residency-for-chatgpt - Locator: Current feature/storage scope; external integrations - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### chatgpt:oa-enterprise-notes-r2 ChatGPT Enterprise and Edu release notes. The October16 notice retires administrator-managed sync and directs eligible Enterprise workspaces to real-time GoogleDrive/SharePoint/Teams apps. - URL: https://help.openai.com/en/articles/10128477-chatgpt-enterprise-and-edu-release-notes - Locator: October16 administrator-managed sync retirement - Evidence kind: documented - Source date: 2026-10-16 - Retrieved: 2026-10-21 ### chatgpt:oa-company Company knowledge in ChatGPT. Company Knowledge is a plugin for eligible Business/Enterprise/Edu users and uses authorized connected sources rather than granting new data access. - URL: https://help.openai.com/en/articles/12628342-company-knowledge-in-chatgpt - Locator: Requirements; source permissions; supported apps - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### chatgpt:oa-memory Memory in ChatGPT. Memory and custom instructions differ; users can manage remembered information and admins control supported workspace settings. - URL: https://help.openai.com/en/articles/8590148-memory-in-chatgpt - Locator: Controls; sources; removal; workspace memory - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### claude:cl-memory-r2 Chat search and memory. Improved memory has Team/Enterprise owner controls and cloud-Cowork sharing; legacy Team lacks org controls and legacy memory is chat-only. - URL: https://support.claude.com/en/articles/11817273-use-claude-s-chat-search-and-memory-to-build-on-previous-context - Locator: Improved Settings>Memory versus legacy; owners; Cowork; exclusions - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### chatgpt:oa-enterprise-notes-20261026 ChatGPT Enterprise and Edu release notes. Dated Enterprise/Edu notes record live-app migration, collaboration and add-in changes, Intune eligibility and planned GPT retirement. - URL: https://help.openai.com/en/articles/10128477-chatgpt-enterprise-and-edu-release-notes - Locator: October 16 sync retirement; September 25 Teams; September GPT migration; May 6 Intune; public web-reader representation retrieved 2026-10-26, representation SHA256 8781183db68eb81bcf7367e33925fbcec071340b0b8901192b83ef01c70a778e - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-26 ### chatgpt:oa-gpt-migration-r2-20261026 Custom GPT retirement and migration FAQ. The accessible FAQ confirms migration to plugins, standard/approved-deferral dates, and that models/actions/sharing settings do not transfer automatically. - URL: https://help.openai.com/en/articles/20001519-custom-gpt-retirement-and-migration-faq - Locator: Plugin migration; Enterprise guidance and dates; non-transferring actions; public web-reader representation retrieved 2026-10-26, representation SHA256 dd951ed04244057574ab0c432d8a8279430ac2da83c342351588edf8d66e0a9b - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-26 ### chatgpt:oa-admin-settings-20261026 Managing workspace settings in ChatGPT Enterprise. Enterprise settings include model defaults, role-scoped features/memory and a recurring AI-policy modal. - URL: https://help.openai.com/en/articles/8411955-managing-workspace-settings-in-chatgpt-enterprise - Locator: General; permissions; models; AI policy modal; public web-reader representation retrieved 2026-10-26, representation SHA256 96c9b041bf9174a50f86db93e70e0298c6a367658ecba1cdd9db1ccaf5bb68bc - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-26 ### chatgpt:oa-business-notes-20261026 ChatGPT Business release notes. Dated Business notes document workspace analytics, Excel/Sheets integration, agent/work changes and app-template access. - URL: https://help.openai.com/en/articles/11391654-chatgpt-business-release-notes - Locator: April 16 analytics; May 5 Sheets; May 22 agents; July 9 Work; public web-reader representation retrieved 2026-10-26, representation SHA256 a76daa1b273dbced3f3f607908c1965a3ed86fc0cc21c798be3582eca50e374d - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-26 ### chatgpt:oa-business-20261026 ChatGPT Business - Overview. Business is self-serve with Standard/Premium seats, includes Chat/Work, and remains separate from API billing. - URL: https://help.openai.com/en/articles/8792828-chatgpt-business-overview - Locator: Standard/Premium seats; plan comparison; Team rename; public web-reader representation retrieved 2026-10-26, representation SHA256 7af98911edbf31de1850b4de99233ea6bbee5f443dce05c9d6958e004181ee13 - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-26 ### chatgpt:oa-files-20261026 Uploading files and audio to ChatGPT. Uploads have format-specific limits, 40-file Business/Enterprise projects, 20-file GPT knowledge and Enterprise-only PDF visual retrieval. - URL: https://help.openai.com/en/articles/8555545-uploading-files-and-audio-to-chatgpt - Locator: Formats; size/rate/storage limits; projects; PDF visual retrieval; public web-reader representation retrieved 2026-10-26, representation SHA256 8fbf08df3b56a93ebaf27c2ca223eb2cd449e5b1b43e5f5d09995eaeb7bb7907 - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-26 ### chatgpt:oa-company-r2-20261026 Company knowledge in ChatGPT. Current Company Knowledge uses enabled eligible app connections for Business/Enterprise/Edu and inherits source access without claiming a universal copied index. - URL: https://help.openai.com/en/articles/12628342-company-knowledge-in-chatgpt - Locator: Current app-based workflow; plans; source permissions; public web-reader representation retrieved 2026-10-26, representation SHA256 2d451d442061ec6222039e4f287ed4f08226239e708b96200ee8ea33bd7971ed - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-26 ### chatgpt:oa-residency-r2-20261026 Data residency and inference residency for ChatGPT. Current residency guidance describes scoped content/processing and external-app exceptions; it no longer establishes an administrator-managed sync configuration. - URL: https://help.openai.com/en/articles/9903489-data-residency-and-inference-residency-for-chatgpt - Locator: Current feature/storage scope; external integrations; public web-reader representation retrieved 2026-10-26, representation SHA256 7bc187a8fb32db1e17c0bb7e93763c0ccb2c8528a6b220f4b3d011bd151f53d3 - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-26 ### chatgpt:oa-plugins-r2-20261026 Plugins in ChatGPT. Plugins package reusable workflow instructions/apps for Chat/Work, with Business/Enterprise sharing subject to workspace controls and per-surface capabilities. - URL: https://help.openai.com/en/articles/20001256-plugins-in-chatgpt - Locator: Reusable skills; references/apps; workspace sharing; surface limits; public web-reader representation retrieved 2026-10-26, representation SHA256 fcb0960b3bb65bf48aafc243940aa11c934ae0735ba6f9f1e847e1fc425ad1e4 - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-26 ### chatgpt:oa-word-r2-20261026 ChatGPT for Word. The native Word add-in drafts/revises text, but plugins are unsupported and regular ChatGPT memory/skills/history do not carry over. - URL: https://help.openai.com/en/articles/20001526-chatgpt-for-word - Locator: Availability; writing; skills; plugin and history limitations; public web-reader representation retrieved 2026-10-26, representation SHA256 93ee7796175a908a7cd559677e9e27203399c07d0c5147311b6610272e4c93e3 - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-26 ### chatgpt:chatgpt:review-fix-gpt-creation-freeze-20261026 Custom GPT migration: creation freeze and existing edits. October 26 is a planned freeze on new GPT creation in affected Enterprise workspaces; drafts needed for migration should be published beforehand. Existing unmigrated GPTs remain editable, while migration makes the original read-only. The FAQ covers all plans for scheduled retirement and directs Enterprise customers to their account team to confirm their migration timeline. - URL: https://help.openai.com/en/articles/20001519-custom-gpt-retirement-and-migration-faq - Locator: Enterprise workspace guidance, October 26 planned milestone; all-plan retirement; timeline confirmation paragraph; public web-reader representation retrieved 2026-10-26, SHA256 4b3144d23ceb8bfd0e24a6f5b6a3c0a8cf29a4d84f64091ddafda7242ff0695c - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-26 ### claude:cl-academy Claude Academy tutorials. Academy publishes written/video guides for chat, connectors, agents, Office work and skills. - URL: https://academy.claude.com/tutorials - Locator: Chat; Cowork; Office; AI fluency guides - Evidence kind: vendor-claimed - Source date: Not stated - Retrieved: 2026-10-21 ### chatgpt:oa-mcp-r2 Connecting custom MCP servers in ChatGPT. Custom MCP is available on Business/Enterprise/Edu web; the current Plugins flow does not require Developer Mode, with admin publication and plan-specific creator controls. - URL: https://help.openai.com/en/articles/12584461-connecting-custom-mcp-servers-in-chatgpt - Locator: Availability; current Plugins flow; plan roles; action permissions - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### claude:cl-pricing Claude pricing. Team is listed for 2-150 seats with Standard/Premium pricing; current Enterprise lists USD 20/seat/month annual access plus usage and a 20-seat self-serve minimum. - URL: https://claude.com/pricing - Locator: Team/Enterprise cards; commercial comparison - Evidence kind: vendor-claimed - Source date: Not stated - Retrieved: 2026-10-21 ### claude:cl-mcp Get started with custom connectors using remote MCP. Remote MCP originates from Anthropic cloud, can use per-user OAuth or shared credentials, and differs from Desktop-local MCP. - URL: https://support.claude.com/en/articles/11175166-get-started-with-custom-connectors-using-remote-mcp - Locator: Network route; owner publication; OAuth/request headers; local distinction - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### chatgpt:oa-search Searching the web with ChatGPT. Search can send rewritten queries/general location to external providers and supplies cited results and an optional Chrome search extension. - URL: https://help.openai.com/en/articles/9237897-searching-the-web-with-chatgpt - Locator: Availability; sources; external providers; Chrome extension - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### chatgpt:oa-residency Data residency and inference residency for ChatGPT. Eligible Enterprise/Edu regional storage and optional same-region GPU inference exclude system data, global CPU processing and external integrations. - URL: https://help.openai.com/en/articles/9903489-data-residency-and-inference-residency-for-chatgpt - Locator: Eligibility; storage/backups; GPU processing; exceptions - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### claude:claude:web-search-controls-20261026 Enable and use Claude web search. Team/Enterprise Owners first enable web search for the workspace, after which members use it in chat. Search answers include citations and source links. The article does not identify a universal search backend or query-processing region. - URL: https://support.claude.com/en/articles/10684626-enable-and-use-web-search - Locator: Team/Enterprise workspace enablement and How web search works; HTTP 200, body SHA256 76f79d8a3eb4181b4e1028b23a4df9821c316008015fe0290feb4582d6b9a83d - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-26 ### claude:cl-cowork Get started with Claude Cowork. Paid Cowork runs multi-step tasks with local access where permitted and cloud task persistence, with Team/Enterprise cloud availability in beta. - URL: https://support.claude.com/en/articles/13345190-get-started-with-claude-cowork - Locator: Availability; cloud beta; task flow; tools; scheduling - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### claude:claude:cowork-stop-20261026 Use Claude Cowork safely. The paid-plan Cowork safety guide instructs users to monitor and stop a task when needed. It does not promise rollback of completed external actions or a guaranteed cancellation boundary. - URL: https://support.claude.com/en/articles/13364135-use-claude-cowork-safely - Locator: Paid-plan availability, monitoring tasks and stopping suspicious behavior; HTTP 200, body SHA256 363aa11b90d168d68950bcf4820d677b076c63c1f27598be7d17ef04c727da24 - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-26 ### claude:cl-cowork-20261026 Get started with Claude Cowork. Paid Cowork runs multi-step tasks with local access where permitted and cloud task persistence, with Team/Enterprise cloud availability in beta. - URL: https://support.claude.com/en/articles/13345190-get-started-with-claude-cowork - Locator: Availability; cloud beta; task flow; tools; scheduling; retrieved without credentials with Python3 requests, HTTP 200, body SHA256 0c2c6bcedbe79e9bc84268a92da091133ea4c9737d6790eb74583def73350c02 on 2026-10-26 - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-26 ### chatgpt:oa-business-faq ChatGPT Business: General FAQ. The FAQ lists current seat prices, a 200-paid-seat cap for new subscriptions since August 24 2026, and unavailable self-service Business export. - URL: https://help.openai.com/en/articles/8542115-chatgpt-business-general-faq - Locator: Prices; seat cap; export; privacy - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### claude:cl-compliance Access the Compliance API. Enterprise Compliance API exposes events, chats and file content with primary-owner activation and scoped organization keys. - URL: https://support.claude.com/en/articles/13015708-access-the-compliance-api - Locator: Eligibility; primary-owner activation; event/chat/file data - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### claude:cl-api-prices Claude Platform pricing. Current public API prices include Sonnet 5.5 at USD 2/M input and USD 10/M output, while model choice, tokens and features change usage cost. - URL: https://platform.claude.com/docs/en/about-claude/pricing - Locator: Model pricing table; regional rates; tool token charges - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### chatgpt:oa-work ChatGPT Work and Codex. Work is the multi-step deliverable experience on eligible paid plans; cloud/local task execution and model access differ from regular Chat. - URL: https://help.openai.com/en/articles/20001275-chatgpt-work-and-codex - Locator: Chat versus Work; models; availability; deliverables - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### claude:cl-export-user Export your Claude data. Organization members can export their own chats when enabled, without uploaded-file contents; exports are web/Desktop only. - URL: https://support.claude.com/en/articles/9450526-export-your-claude-data - Locator: Team/Enterprise owner enablement; contents; 24-hour link - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### chatgpt:oa-word ChatGPT for Word. The shared Office add-in embeds ChatGPT in Word, requires M365 administrator approval and uses the applicable model/token allowance. - URL: https://help.openai.com/en/articles/20001526-chatgpt-for-word - Locator: Office add-in; admin approval; limitations; pricing - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### claude:cl-google-addon Use Claude in Google Docs, Sheets, and Slides. A native Google Workspace sidebar beta supports Team/Enterprise, separate from connectors; edits require approval by default and extension data does not inherit organization retention. - URL: https://support.claude.com/en/articles/16951679-use-claude-in-google-docs-sheets-and-slides - Locator: Beta eligibility; native extension; approvals; data retention - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### chatgpt:oa-word-r2 ChatGPT for Word. The native Word add-in drafts/revises text, but plugins are unsupported and regular ChatGPT memory/skills/history do not carry over. - URL: https://help.openai.com/en/articles/20001526-chatgpt-for-word - Locator: Availability; writing; skills; plugin and history limitations - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### chatgpt:chatgpt:images-editing-20261026 Images in ChatGPT. The official guide documents editing uploaded or generated images. Images are available on all tiers; Images with thinking is currently Plus/Pro/Business, with Enterprise/Edu described as coming later. - URL: https://help.openai.com/en/articles/11084440-im - Locator: Overview, Availability and Edit your image; public web-reader representation SHA256 44b31a6adea07ee1fbba7c7f8094c14b2d08b85d14db6ac37f0732f9ad291979 - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-26 ### chatgpt:oa-enterprise-models-r2-20261026 ChatGPT Enterprise and Edu models and limits. Enterprise Chat names GPT6 powered by Sol and Pro/Astra, while Work has separate model options and workspace/role controls. - URL: https://help.openai.com/en/articles/11165333-chatgpt-enterprise-and-edu-models-and-limits - Locator: Enterprise Chat rollout; Work/Codex distinction; model picker; tools; public web-reader representation retrieved 2026-10-26, representation SHA256 da70d2c757d5cb302998f802acc290c8a1a4f26b86a8ab34ff9a83627f9ac7fd - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-26 ### chatgpt:oa-services-20261026 OpenAI Services Agreement. The business contract protects customer content, assigns output rights, limits service use and defines Irish contracting/law for EEA/Swiss customers. - URL: https://openai.com/policies/services-agreement/ - Locator: Sections 3-7; 16.3; definitions of contracting party, governing laws and venue; public web-reader representation retrieved 2026-10-26, representation SHA256 0233863b855363cf290708260721bf7d470cd68b01718c219c441018b00e846e - Evidence kind: documented - Source date: 2025-12-01 - Retrieved: 2026-10-26 ### claude:claude:image-generation-boundary-20261026 Can Claude produce images?. The vendor explicitly says Claude does not generate photos or illustrations like image-generation tools. HTML/SVG diagrams, charts and interactive visuals are a separate beta web/desktop capability; uploaded-image analysis is also separate. - URL: https://support.claude.com/en/articles/9002504-can-claude-produce-images - Locator: Native image generation versus HTML/SVG custom visuals; HTTP 200, body SHA256 4d918af1acc08fe9d2c1ea21ae840029c1c9109acad12cb2eaeeb8b8daab4da9 - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-26 ### chatgpt:oa-voice ChatGPT Voice. Eligible workspaces have Voice, with Business seat-dependent allowances and separate Enterprise credit/token billing and audio retention. - URL: https://help.openai.com/en/articles/20001274-chatgpt-voice - Locator: Business/Enterprise availability; limits; data controls - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### chatgpt:chatgpt:mobile-read-aloud-20261026 ChatGPT mobile response actions. Supported mobile response actions can include Read aloud; availability varies by message. This is distinct from a live Voice session and does not establish Swiss German recognition. - URL: https://help.openai.com/en/articles/8142208-chatgpt-ios-and-android-app-faq - Locator: How do I select text or use response actions on Android?; public web-reader representation SHA256 5a659925d335100a37be401edb3f15327e8a679e3670bd3e945c97b20ca6ca4d - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-26 ### chatgpt:oa-analysis-r2 Data analysis with ChatGPT. Data analysis documents code execution and static/interactive visualizations; Enterprise model inventory establishes the scoped plan entitlement. - URL: https://help.openai.com/en/articles/8437071-data-analysis-with-chatgpt - Locator: Python/Jupyter execution and chart types - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### claude:cl-artifacts-admin Artifacts admin guide for Team and Enterprise plans. Admins control artifact templates, while standalone Claude Design closes 2026-12-14 and in-Claude design continues. - URL: https://support.claude.com/en/articles/16994751-artifacts-admin-guide-for-team-and-enterprise-plans - Locator: Templates; October defaults; standalone Design closure; data handling - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### chatgpt:oa-language How to change your language setting in ChatGPT. ChatGPT documents German, French and Italian UI settings alongside other supported languages. - URL: https://help.openai.com/en/articles/8357869-how-to-change-your-language-setting-in-chatgpt - Locator: Browser/mobile language setting; supported list - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### chatgpt:oa-trust OpenAI Trust Portal. The portal claims ISO and SOC coverage and lists reports, EKM, penetration testing and a VPAT, without establishing certificate validity in this pass. - URL: https://trust.openai.com/ - Locator: Compliance; documents; ChatGPT security features - Evidence kind: vendor-claimed - Source date: Not stated - Retrieved: 2026-10-21 ### claude:claude:display-languages-20261026 Claude display-language settings. Claude documents English, French, German, Italian, Hindi, Indonesian, Japanese, Korean, Brazilian Portuguese and Latin American/Spain Spanish interfaces on web and desktop. Voice language is a separate setting. - URL: https://support.claude.com/en/articles/10769299-how-to-use-claude-in-your-preferred-language - Locator: Supported Languages and On Web and Desktop; HTTP 200, body SHA256 9a6fd87cbba7b558c9972e24b7bcd94249d6cb04003eea26541794f93dbae61b - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-26 ### chatgpt:oa-business-sso Setting up single sign-on for ChatGPT Business. Business supports SAML/OIDC and verified domains but standalone Business excludes SCIM and synchronized groups. - URL: https://help.openai.com/en/articles/11489188-setting-up-single-sign-on-sso-for-chatgpt-business - Locator: Supported protocols; plan limits; automatic account creation - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### chatgpt:chatgpt:native-mfa-enforcement-20261026 Managing multi-factor authentication. Individuals can configure MFA, but the guide explicitly says administrators cannot currently enforce MFA at the ChatGPT workspace or API organization level. Identity-provider policy is a separate control. - URL: https://help.openai.com/en/articles/7967234-managing-multi-factor-authentication-mfa - Locator: Can admins enforce MFA for a workspace or organization?; public web-reader representation SHA256 c263aa5ec4b4533980634f9fc563829448056ddfb38d44108adfc1f2af92555e - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-26 ### claude:cl-sso Set up single sign-on. SSO and JIT are available to Team/Enterprise with owner configuration and verified domains. - URL: https://support.claude.com/en/articles/13132885-set-up-single-sign-on-sso - Locator: Team/Enterprise eligibility; IdP; owner roles; provisioning - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### claude:cl-provision Set up JIT or SCIM provisioning. Team supports JIT but not SCIM; Enterprise SCIM synchronizes membership and role/seat mappings with documented removal differences. - URL: https://support.claude.com/en/articles/13133195-set-up-jit-or-scim-provisioning - Locator: Plan eligibility; provisioning matrix; group mapping - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### chatgpt:oa-billing Managing billing and seats in ChatGPT Business. Business lists USD 20/25 Standard and USD 100/125 Premium annual/monthly equivalents, at least two seats, and next-cycle reductions. - URL: https://help.openai.com/en/articles/8792536-managing-billing-and-seats-in-chatgpt-business - Locator: Seat types; minimum; billing changes - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### chatgpt:oa-members Managing members, workspace roles, and seats in ChatGPT Enterprise and Edu. Enterprise/Edu distinguish member, analytics viewer, admin and owner; Enterprise can delegate group management and assign seat types. - URL: https://help.openai.com/en/articles/8266401-managing-members-workspace-roles-and-seats-in-chatgpt-enterprise-and-edu - Locator: Built-in roles; seat types; invitations - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### chatgpt:oa-leavers Data retention when a member is removed from a workspace. Removal revokes access immediately, follows Enterprise retention policies, preserves Business data indefinitely, and reassigns projects/GPT ownership without exposing private conversations. - URL: https://help.openai.com/en/articles/8266418-data-retention-when-a-member-is-removed-from-a-workspace - Locator: Enterprise/Edu versus Business; ownership reassignment - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### chatgpt:oa-services OpenAI Services Agreement. The business contract protects customer content, assigns output rights, limits service use and defines Irish contracting/law for EEA/Swiss customers. - URL: https://openai.com/policies/services-agreement/ - Locator: Sections 3-7; 16.3; definitions of contracting party, governing laws and venue - Evidence kind: documented - Source date: 2025-12-01 - Retrieved: 2026-10-21 ### claude:cl-model-control Manage model access for your organization. Enterprise controls model/effort access by organization and custom role, while Haiku cannot be disabled and coverage has named exceptions. - URL: https://support.claude.com/en/articles/15694740-manage-model-access-for-your-organization - Locator: Organization and custom-role ceilings; Haiku exception; coverage - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### chatgpt:chatgpt:enterprise-analytics-export-20261026 Workspace analytics for Enterprise and Edu. Enterprise/Edu supports CSV reports by user and GPT/project usage, with separate survey/benchmark exports. Task insights aggregate work categories and can be disabled; survey export identifiers depend on a setting. Ordinary user reports remain identifiable. - URL: https://help.openai.com/en/articles/10875114-workspace-analytics-for-chatgpt-enterprise-and-edu - Locator: Export a report by user, Export GPT or project usage, User surveys, Task insights; public web-reader representation SHA256 6aeca6e22f4c2c5cfa4d623934a911693c329ba68f2b3af43c1527c662a89bfb - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-26 ### claude:cl-analytics View usage analytics for Team and Enterprise plans. Admins have plan-scoped adoption and spend views, including per-user/model CSVs and separate seat-based overage reporting. - URL: https://support.claude.com/en/articles/12883420-view-usage-analytics-for-team-and-enterprise-plans - Locator: Roles; product/model/user data; CSV exports - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### chatgpt:oa-business-faq-r2 ChatGPT Business general FAQ. Business members retain private histories by default and self-service workspace data export is unavailable; this does not define every conditional admin access route. - URL: https://help.openai.com/en/articles/8542115-chatgpt-business-general-faq - Locator: Private chats; self-service export; roles - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### chatgpt:oa-business-privacy-r2 Managing data, sharing, and privacy in ChatGPT Business. Usage/spend analytics does not automatically grant private-chat transcript access; member self-export through Settings is unavailable. - URL: https://help.openai.com/en/articles/8798634-managing-data-sharing-and-privacy-in-chatgpt-business - Locator: Admin visibility and usage analytics; collaboration; export - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### chatgpt:oa-compliance-r2 OpenAI Compliance Platform for Enterprise and Edu. Enterprise/Edu Compliance Platform separates owner-granted conversation access from delegated log categories and documents30-day log availability. - URL: https://help.openai.com/en/articles/9261474-openai-compliance-platform-for-enterprise-and-edu-customers - Locator: Eligibility; owner-granted content permissions; retention - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### chatgpt:oa-business-owner-export-r3 Managing data, sharing, and privacy in ChatGPT Business. Business members lack Settings self-export. Owners can export an individual member through the workspace Members menu when the option is available; bulk coverage, precise eligibility, format and completeness are unspecified. - URL: https://help.openai.com/en/articles/8798634-managing-data-sharing-and-privacy-in-chatgpt-business - Locator: Can I export my data from a Business workspace? — member restriction and conditional owner export steps - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### claude:cl-audit Access audit logs. Enterprise audit export covers 180 days of metadata, excludes prompt content and has a CMEK export limitation with a Compliance API alternative. - URL: https://support.claude.com/en/articles/9970975-access-audit-logs - Locator: Enterprise export; 180 days; fields; content exclusion; CMEK - Evidence kind: documented - Source date: 2026-06-15 - Retrieved: 2026-10-21 ### claude:cl-compliance-partners Get started with Claude Compliance API integrations. The documentation lists partner compliance/eDiscovery/monitoring integrations; each integration needs separate scope and behavior verification. - URL: https://support.claude.com/en/articles/15167101-get-started-with-claude-compliance-api-integrations - Locator: Security, archive and eDiscovery partners - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### chatgpt:oa-compliance OpenAI Compliance Platform for Enterprise and Edu customers. Enterprise/Edu compliance supports immutable event logs, state queries and SIEM/eDiscovery/DLP integrations, with a 30-day log access window. - URL: https://help.openai.com/en/articles/9261474-openai-compliance-platform-for-enterprise-and-edu-customers - Locator: Access; immutable logs; retention; migration; partner integrations - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### claude:cl-compliance-partners-r2 Get started with Claude Compliance API integrations. Enterprise Compliance integrations are Primary-Owner-enabled; Claude Platform has a separate scope and this is not a Team entitlement or proof of inline redaction. - URL: https://support.claude.com/en/articles/15167101-get-started-with-claude-compliance-api-integrations - Locator: Eligibility and Enterprise activation; monitoring/DLP partners - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### chatgpt:oa-privacy Enterprise privacy at OpenAI. OpenAI describes AES-256/TLS protections and limited authorized staff access, with plan-specific privacy and administrative visibility. - URL: https://openai.com/enterprise-privacy/ - Locator: Security; service-specific human access; Business FAQ - Evidence kind: vendor-claimed - Source date: Not stated - Retrieved: 2026-10-21 ### claude:cl-servers Where are your servers located? Do you host your models on EU servers?. Commercial documentation says data is stored in the US, inference can route globally and internal support/safety processes can occur in affiliate countries. - URL: https://privacy.claude.com/en/articles/7996890-where-are-your-servers-located-do-you-host-your-models-on-eu-servers - Locator: Commercial global routing; US storage; internal processing - Evidence kind: documented - Source date: 2026-06-15 - Retrieved: 2026-10-21 ### claude:cl-us-only Enable US-only inference for your organization. Usage-based Enterprise offers US-only inference at 1.1 times standard rates for applicable newer models, excluding storage and third-party processing. - URL: https://support.claude.com/en/articles/15422948-enable-us-only-inference-for-your-organization - Locator: Eligibility; billing; exclusions - Evidence kind: documented - Source date: 2026-06-15 - Retrieved: 2026-10-21 ### claude:cl-dpa Data Processing Addendum. The DPA covers confidential processing, subprocessors, audit access, security and post-termination return/deletion with transfer schedules. - URL: https://www.anthropic.com/legal/data-processing-addendum - Locator: B.7; C; E/F; H; SCC/Swiss schedules - Evidence kind: documented - Source date: 2025-02-24 - Retrieved: 2026-10-21 ### chatgpt:oa-subprocessors OpenAI Sub-processor list. The dated list names multiple cloud and service processors with product and country scope. - URL: https://openai.com/policies/sub-processor-list/ - Locator: Third-party processors; processing countries; notice subscription - Evidence kind: documented - Source date: 2026-10-14 - Retrieved: 2026-10-21 ### claude:cl-terms Commercial Terms of Service. Commercial terms prohibit model training on customer content, define EEA/Swiss/UK Irish contracting and provide confidentiality and commercial-use restrictions. - URL: https://www.anthropic.com/legal/commercial-terms - Locator: Customer content; confidentiality; contracting party; fees - Evidence kind: documented - Source date: 2025-06-17 - Retrieved: 2026-10-21 ### claude:cl-training Is my data used for model training?. Commercial content is not used for training by default; explicit feedback can be used and retained up to five years, with owner controls. - URL: https://privacy.claude.com/en/articles/7996868-is-my-data-used-for-model-training - Locator: Commercial default; feedback; disable feedback - Evidence kind: documented - Source date: 2026-08-18 - Retrieved: 2026-10-21 ### claude:cl-covered-r2 Covered Models. Covered Models have default minimum retention, with a separate limited agreement-based Fable ZDR exception for eligible internal-business applications. - URL: https://support.claude.com/en/articles/15425695-covered-models - Locator: Default retention; temporary eligible Fable exception; EFS - Evidence kind: documented - Source date: 2026-09-01 - Retrieved: 2026-10-21 ### claude:cl-covered-routes-r2 Data retention practices for Covered Models. The updated guide excludes notified exception customers from the standard ZDR-transition instructions and says hosted Enterprise Chat/Cowork already use standard retention. - URL: https://support.claude.com/en/articles/15425996-data-retention-practices-for-covered-models - Locator: ZDR configurations; eligible notices; cloud-provider storage; hosted Chat/Cowork - Evidence kind: documented - Source date: 2026-09-05 - Retrieved: 2026-10-21 ### claude:cl-retention-r2 How long do you store organization data?. Commercial saved-chat retention differs from API retention; backend deletion normally takes up to 30 days and safety/legal/feedback exceptions remain. - URL: https://privacy.claude.com/en/articles/7996866-how-long-do-you-store-my-organization-s-data - Locator: Saved commercial chats; deletion; safety and feedback exceptions - Evidence kind: documented - Source date: 2026-07-01 - Retrieved: 2026-10-21 ### chatgpt:oa-dpa OpenAI Data Processing Addendum. The DPA covers EEA/Swiss data, subprocessor notifications/objections, international transfers and return/deletion at customer instruction. - URL: https://openai.com/policies/data-processing-addendum/ - Locator: Definitions; 2.9; 2.11; 4.1 - Evidence kind: documented - Source date: 2025-12-01 - Retrieved: 2026-10-21 ### chatgpt:oa-managed-access-r2 Data access for your managed ChatGPT account. Managed-account administrators may access/export/retain/delete content where configuration and law allow; an Enterprise admin role alone does not grant sensitive compliance access. - URL: https://help.openai.com/en/articles/20001067-data-access-for-your-managed-chatgpt-account - Locator: Conditional admin access; configuration; Enterprise sensitive permissions - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### chatgpt:oa-privacy-r2 Enterprise privacy at OpenAI. The privacy page describes Business administrator access/export/deletion and retention control broadly, without documenting a concrete Business export route or settings workflow. - URL: https://openai.com/enterprise-privacy/ - Locator: Business FAQ: organizational access and retention; Enterprise FAQ - Evidence kind: vendor-claimed - Source date: Not stated - Retrieved: 2026-10-21 ### chatgpt:oa-retention-r2 Chat and file retention in ChatGPT. Saved chats and files have separate deletion/policy rules, generally30-day backend deletion with legal/security exceptions and Enterprise backup caveats. - URL: https://help.openai.com/en/articles/8983778-chat-and-file-retention-in-chatgpt - Locator: Chats; Library/project/GPT files; deletion; Enterprise backups - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### chatgpt:oa-leavers-r2 Data retention when a member is removed from a workspace. Business leaver content remains indefinite while Enterprise/Edu follow configured retention; project/GPT ownership reassignment does not expose the former member's private conversations. - URL: https://help.openai.com/en/articles/8266418-data-retention-when-a-member-is-removed-from-a-workspace - Locator: Plan-specific retention; ownership versus conversations - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### claude:cl-retention-admin-r2 Configure custom data retention controls for Enterprise plans. Current English guidance schedules over-age content on save and deletes through a daily background process, preserving project precedence and feature exclusions. - URL: https://support.claude.com/en/articles/10440198-configure-custom-data-retention-controls-for-enterprise-plans - Locator: Project precedence; daily deletion process; role and feature limits - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### chatgpt:chatgpt:government-transparency-20261026 OpenAI trust and transparency. The public page links OpenAI’s Government User Data Request Policy and semiannual request/disclosure reports, currently including January–June 2026. Existence of a policy is distinct from immunity from government access. - URL: https://openai.com/trust-and-transparency/ - Locator: Government requests for user data, Our policy link and semiannual reports; public web-reader representation SHA256 93bafff710834085a0d51dde71f2f1bd3bfe6e7dc86dcb4fd45cea5938355140 - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-26 ### chatgpt:oa-subprocessors-20261026 OpenAI Sub-processor list. The dated list names multiple cloud and service processors with product and country scope. - URL: https://openai.com/policies/sub-processor-list/ - Locator: Third-party processors; processing countries; notice subscription; public web-reader representation retrieved 2026-10-26, representation SHA256 a7d96e1cb585412fcc51ac92669fa0f3b2529082622dfe7f32298849b672f6da - Evidence kind: documented - Source date: 2026-10-14 - Retrieved: 2026-10-26 ### chatgpt:oa-dpa-20261026 OpenAI Data Processing Addendum. The DPA covers EEA/Swiss data, subprocessor notifications/objections, international transfers and return/deletion at customer instruction. - URL: https://openai.com/policies/data-processing-addendum/ - Locator: Definitions; 2.9; 2.11; 4.1; public web-reader representation retrieved 2026-10-26, representation SHA256 11aa41f80669f6238d4e298e39f15fb7530b480effb79ea23111d8f9186adc55 - Evidence kind: documented - Source date: 2025-12-01 - Retrieved: 2026-10-26 ### claude:cl-gov Government requests for user information. Anthropic documents valid-process review, rejection of deficient requests, notice exceptions and generally directing enterprise requests to the customer. - URL: https://privacy.claude.com/en/articles/9519291-what-is-anthropic-s-policy-for-handling-governmental-requests-for-user-information - Locator: Valid process; challenge; customer notice; exceptions - Evidence kind: documented - Source date: 2026-03-16 - Retrieved: 2026-10-21 ### claude:cl-trust-route Anthropic subprocessor list access route. The public list URL redirects to a trust portal that returned no extractable entries in this research; countries and revision remain unverified. - URL: https://www.anthropic.com/subprocessors - Locator: DPA Schedule 4 link; redirect to trust.anthropic.com/subprocessors - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### chatgpt:chatgpt:eu-ai-act-resources-20261026 EU AI Act resources and customer guidance. OpenAI publishes a customer AI Act resource page linking its governance framework, Codes of Practice approach and provenance guidance. A dedicated form is available for relevant model-documentation requests; no request was made and no product compliance verdict is inferred. - URL: https://help.openai.com/en/articles/12141645-eu-ai-act-openai-resources-and-customer-guidance - Locator: OpenAI approach, prohibited practices, governance/provenance resources and model-documentation contact route; public web-reader representation SHA256 cfd90ddfaf879898942c3866d9e555258e38f6268652c64ded7a2d714c1552ed - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-26 ### claude:cl-ai-act Introducing Claude Fable 5.1 and Claude Mythos 5.1. The provider announcement describes transparency-code signing, watermarking for later models and a restricted-preview detection API; this is not a deployer compliance verdict. - URL: https://www.anthropic.com/claude-fable-and-mythos-5-1 - Locator: Compliance with the EU AI Act - Evidence kind: vendor-claimed - Source date: Not stated - Retrieved: 2026-10-21 ### claude:claude:commercial-certifications-20261026 Anthropic commercial compliance credentials. The commercial privacy page claims ISO 27001:2022, ISO/IEC 42001:2023 and SOC 2 Type I/II. Copies are request-gated; issuer, certificate/report scope, period and validity were not inspected. - URL: https://privacy.claude.com/en/articles/10015870-what-certifications-has-anthropic-obtained - Locator: Commercial-products applicability and credential list; HTTP 200, body SHA256 d44ecb66e9cf7636e39a9b9da3c61cc6513dfca890e68fcdaa1bc7051f310335 - Evidence kind: vendor-claimed - Source date: 2026-03-16 - Retrieved: 2026-10-26 ### claude:cl-dpa-20261026 Data Processing Addendum. The DPA covers confidential processing, subprocessors, audit access, security and post-termination return/deletion with transfer schedules. - URL: https://www.anthropic.com/legal/data-processing-addendum - Locator: B.7; C; E/F; H; SCC/Swiss schedules; retrieved without credentials with Python3 requests, HTTP 200, body SHA256 c11e0d2d380f6155e900d4357d2a154e85cd0b38db427ca11e5048e02c375218 on 2026-10-26 - Evidence kind: documented - Source date: 2025-02-24 - Retrieved: 2026-10-26 ### chatgpt:oa-ekm OpenAI Enterprise Key Management Overview. EKM for eligible Enterprise/Edu workspaces uses customer-controlled AWS/GCP/Azure master keys with an account representative. - URL: https://help.openai.com/en/articles/20000943 - Locator: Eligibility; external KMS; unsupported features - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### chatgpt:oa-ip IP allowlisting for ChatGPT. Enterprise/Edu IP policies block user requests outside allowed addresses and use a separate Compliance API allowlist. - URL: https://help.openai.com/en/articles/12111596-ip-allowlisting-for-chatgpt - Locator: Eligibility; enforcement; Compliance API - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### claude:cl-cmek What are customer-managed encryption keys?. Eligible Enterprise organizations can use customer AWS/GCP/Azure master keys for certain chats, projects and files, with feature limitations. - URL: https://support.claude.com/en/articles/15505325-what-are-customer-managed-encryption-keys-cmek - Locator: Eligibility; customer KMS; scope - Evidence kind: documented - Source date: 2026-06-15 - Retrieved: 2026-10-21 ### claude:cl-ip Restrict access to Claude with IP allowlisting. Enterprise supports source-IP CIDR restrictions configured through support; externally shared artifacts can remain outside that restriction. - URL: https://support.claude.com/en/articles/13200993-restrict-access-to-claude-with-ip-allowlisting - Locator: Enterprise eligibility; coverage; external sharing exception - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### claude:cl-covered-review Data retention practices for Covered Models. Controlled reviewers may inspect safety-flagged retained data, with logged access; normal chat/Cowork already use standard retention. - URL: https://support.claude.com/en/articles/15425996-data-retention-practices-for-covered-models - Locator: Human review; 30 days; affected ZDR configurations - Evidence kind: documented - Source date: 2026-09-05 - Retrieved: 2026-10-21 ### chatgpt:fx-20261020 ECB euro reference historical rates. Directly retrieved ECB XML gives EUR 1 = USD 1.1215 = CHF 0.9237. - URL: https://www.ecb.europa.eu/stats/eurofxref/eurofxref-hist.xml - Locator: Cube time=2026-10-20; USD and CHF - Evidence kind: documented - Source date: 2026-10-20 - Retrieved: 2026-10-21 ### claude:fx-20261020 ECB euro reference historical rates. Directly retrieved ECB XML gives EUR 1 = USD 1.1215 = CHF 0.9237. - URL: https://www.ecb.europa.eu/stats/eurofxref/eurofxref-hist.xml - Locator: Cube time=2026-10-20; USD and CHF - Evidence kind: documented - Source date: 2026-10-20 - Retrieved: 2026-10-21 ### claude:cl-consumption Claude Enterprise consumption guide. The guide recommends Sonnet for routine/high-volume work and lower effort, while administrators configure the actual default and usage controls. - URL: https://support.claude.com/en/articles/14782391-claude-enterprise-consumption-guide - Locator: Model/effort recommendations; defaults; limits - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### claude:cl-export-org-20261026 Export your organization data. Team/Enterprise Primary Owners can export organization conversation/user data; deleted content is excluded and links expire in 24 hours. - URL: https://support.claude.com/en/articles/13346720-export-your-organization-s-data - Locator: Primary owner; scope; deleted items; link expiry; retrieved without credentials with Python3 requests, HTTP 200, body SHA256 57af2f5ad8f732b35209851f2ba150423ac16e9d6a5c59718d6b0dd9ef672cae on 2026-10-26 - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-26 ### claude:cl-export-user-20261026 Export your Claude data. Organization members can export their own chats when enabled, without uploaded-file contents; exports are web/Desktop only. - URL: https://support.claude.com/en/articles/9450526-export-your-claude-data - Locator: Team/Enterprise owner enablement; contents; 24-hour link; retrieved without credentials with Python3 requests, HTTP 200, body SHA256 5fe1cfd761095719efd95b5bc63049b1ceed6ddc3ed081373247053022153bfc on 2026-10-26 - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-26 ### claude:cl-compliance-20261026 Access the Compliance API. Enterprise Compliance API exposes events, chats and file content with primary-owner activation and scoped organization keys. - URL: https://support.claude.com/en/articles/13015708-access-the-compliance-api - Locator: Eligibility; primary-owner activation; event/chat/file data; retrieved without credentials with Python3 requests, HTTP 200, body SHA256 f641744bc193c80154bdb21a45e3c0527566f256728552432047c12936b79225 on 2026-10-26 - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-26 ### chatgpt:chatgpt:german-office-20261026 OpenAI Deutschland office announcement. The dated first-party announcement states that OpenAI opened its first German office in Munich with a local team. It does not specify guaranteed DE/FR/IT support, a Swiss entity or contract-specific SLA. - URL: https://openai.com/index/openai-deutschland/ - Locator: May 22, 2025 opening announcement and local team scope; public web-reader representation SHA256 d04d9029dd9c337a37c2ae21ffabb048a7cc4f11159ddabc87d20fe082137d5f - Evidence kind: vendor-claimed - Source date: 2025-05-22 - Retrieved: 2026-10-26 ### chatgpt:oa-business-faq-20261026 ChatGPT Business: General FAQ. The FAQ lists current seat prices, a 200-paid-seat cap for new subscriptions since August 24 2026, and unavailable self-service Business export. - URL: https://help.openai.com/en/articles/8542115-chatgpt-business-general-faq - Locator: Prices; seat cap; export; privacy; public web-reader representation retrieved 2026-10-26, representation SHA256 ffd176f38adcc4e1658f36e899249404fb7036503d3f42d042bfca83f10b0d50 - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-26 ### chatgpt:oa-status-20261026 OpenAI Status. The public status page separates ChatGPT, Work, compliance, search, uploads, voice and app components and links incident updates. - URL: https://status.openai.com/ - Locator: System components and incident updates; retrieved without credentials with Python3 requests, HTTP 200, body SHA256 1f749d023fe07ab5992f9b3666fbcb15a5578978c14ddda682cf228310aac396 on 2026-10-26 - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-26 ### chatgpt:chatgpt:review-fix-support-channel-20261026 Business FAQ: credit-usage support route. For workspace credit-usage discrepancies, the Business FAQ directs users to OpenAI Support. It does not itself establish a general Enterprise account-team support entitlement. - URL: https://help.openai.com/en/articles/8542115-chatgpt-business-general-faq - Locator: Does zero workspace credit usage mean no one has used ChatGPT or Codex?; public web-reader representation retrieved 2026-10-26, SHA256 6f1e8ec919c352fec861fb80ad95bbf94efd6f1c73199357b5f01ff3d43d62f3 - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-26 ### claude:claude:regional-presence-20261026 Anthropic European office announcement. The dated company announcement identifies an existing Zurich office and plans for Munich and Paris. It does not establish current staffing, a Swiss contracting entity or guaranteed local-language support. - URL: https://www.anthropic.com/news/new-offices-in-paris-and-munich-expand-european-presence - Locator: November 7, 2025 announcement, Zurich and planned Munich offices; HTTP 200, body SHA256 f73fca94192490d5216bd82ba233110af7093cfb2d08e3848eb79d3c055eea72 - Evidence kind: vendor-claimed - Source date: 2025-11-07 - Retrieved: 2026-10-26 ### claude:cl-status-20261026 Claude Status. Claude publishes separate hosted-product components and an incident history without providing a scoped contractual SLA in this page. - URL: https://status.claude.com/ - Locator: Component health; incident history; retrieved without credentials with Python3 requests, HTTP 200, body SHA256 dabd165cf98d3b64e94051b42876be9d30ed1383af03d4c1a201674b97acb34e on 2026-10-26 - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-26 ### chatgpt:oa-academy OpenAI Academy. Academy offers worker, builder and adoption-leader learning resources with public events. - URL: https://academy.openai.com/ - Locator: Learning paths; live and on-demand events - Evidence kind: vendor-claimed - Source date: Not stated - Retrieved: 2026-10-21