--- schema_version: 1 rubric_version: "1.1" kind: pair canonical_url: "https://onaihq.com/compare/agents/chatgpt-vs-librechat/" data_url: "https://onaihq.com/compare/agents/chatgpt-vs-librechat/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 LibreChat > 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. This comparison has 45 criteria with sourced findings for both products, including 45 that a second agent cross-checked for both. 51 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. - LibreChat source checks: 2026-10-21 to 2026-10-26. - Canonical HTML: https://onaihq.com/compare/agents/chatgpt-vs-librechat/ - Machine-readable JSON: https://onaihq.com/compare/agents/chatgpt-vs-librechat/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 #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: partial The model catalog is configured by the customer across first-party provider integrations and custom endpoints. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified. Limitations: - providers: Documented routes include OpenAI, Anthropic, Google, Azure OpenAI, AWS Bedrock and custom compatible services; selection requires enabled credentials and model access. - current_models: v0.8.8 release notes mention GPT-6/GPT-6.1 Sol, Claude Opus/Sonnet 5.5 and Gemini 3.8 Flash support. Actual selectable IDs still depend on the installed configuration and provider account. - auto_routing: Does the product route between models automatically, and is the chosen model shown? No automatic routing policy showing a chosen model was established, and no configured endpoint was exercised. - multimodal_input: Provider-native files support images/PDFs and some providers accept additional Office/audio/video types. Exact acceptance depends on the selected model and transport; no matrix was tested. - providers — Which model providers are available? [partial]: Documented routes include OpenAI, Anthropic, Google, Azure OpenAI, AWS Bedrock and custom compatible services; selection requires enabled credentials and model access. Sources: librechat:librechat:custom, librechat:librechat:azure, librechat:librechat:bedrock, librechat:librechat:vertex. - current_models — Which current models are selectable on this plan? [partial]: v0.8.8 release notes mention GPT-6/GPT-6.1 Sol, Claude Opus/Sonnet 5.5 and Gemini 3.8 Flash support. Actual selectable IDs still depend on the installed configuration and provider account. Sources: librechat:librechat:releases. - user_choice — Can users pick the model per chat? [supported]: Users choose an endpoint/model unless admins enforce model specs or a fixed Agent. Sources: librechat:librechat:modelspec, librechat:librechat:agents. - auto_routing — Does the product route between models automatically, and is the chosen model shown? [unknown]: auto_routing: Does the product route between models automatically, and is the chosen model shown? No automatic routing policy showing a chosen model was established, and no configured endpoint was exercised. - multimodal_input — Which models accept images, audio or files? [partial]: Provider-native files support images/PDFs and some providers accept additional Office/audio/video types. Exact acceptance depends on the selected model and transport; no matrix was tested. Sources: librechat:librechat:ocr. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:custom, librechat:librechat:azure, librechat:librechat:bedrock, librechat:librechat:vertex, librechat:librechat:releases, librechat:librechat:modelspec, librechat:librechat:agents, librechat:librechat:ocr ### 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 #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: partial Dated releases document model updates, but measured availability lags and retirement notice periods remain unknown. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified. Limitations: - release_lag_days: What was the lag for each of the last three major releases, per provider? No paired general-release/LibreChat-availability dates for the last three major releases per provider, or binding retirement-notice period, were established. - deprecation_notice: How much notice is given before a model is removed? No paired general-release/LibreChat-availability dates for the last three major releases per provider, or binding retirement-notice period, were established. - version_pinning: Admins can name explicit model IDs in endpoints/model specs; continuing remote availability remains under provider control. - release_lag_days — What was the lag for each of the last three major releases, per provider? [unknown]: release_lag_days: What was the lag for each of the last three major releases, per provider? No paired general-release/LibreChat-availability dates for the last three major releases per provider, or binding retirement-notice period, were established. - changelog — Is there a dated public model changelog? [supported]: Public releases and the LibreChat changelog date model updates; v0.8.8 was published 2026-10-01. Sources: librechat:librechat:releases. - deprecation_notice — How much notice is given before a model is removed? [unknown]: deprecation_notice: How much notice is given before a model is removed? No paired general-release/LibreChat-availability dates for the last three major releases per provider, or binding retirement-notice period, were established. - version_pinning — Can an admin keep an older model version? [partial]: Admins can name explicit model IDs in endpoints/model specs; continuing remote availability remains under provider control. Sources: librechat:librechat:modelspec, librechat:librechat:custom. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:releases, librechat:librechat:modelspec, librechat:librechat:custom ### 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. #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: partial Customer-held provider keys, customer Azure/AWS/Vertex configurations and custom endpoints are documented. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified. Limitations: - byo_restrictions: File modalities, tools and other capabilities depend on provider/model support and optional services. A universal BYO feature-parity guarantee was not established. - own_api_keys — Can the customer use its own provider API keys? [supported]: Provider keys can be operator-supplied or user_provided, with user key controls in Settings. Sources: librechat:librechat:firstchat, librechat:librechat:custom. - own_cloud_contract — Can it use its own Azure OpenAI, Bedrock or Vertex deployment? [supported]: Customer Azure OpenAI deployments, AWS Bedrock region/credentials and Anthropic Vertex project/region routes are documented separately. Sources: librechat:librechat:azure, librechat:librechat:bedrock, librechat:librechat:vertex. - custom_endpoint — Can an admin add any OpenAI-compatible endpoint? [supported]: Operators can configure a custom compatible API URL and model list. Sources: librechat:librechat:custom. - byo_pricing — Does BYO change the licence price? [supported]: MIT repository use has no per-seat licence fee; customers separately procure provider service usage. Sources: librechat:librechat:license, librechat:librechat:firstchat. - byo_restrictions — Which features stop working with BYO? [partial]: File modalities, tools and other capabilities depend on provider/model support and optional services. A universal BYO feature-parity guarantee was not established. Sources: librechat:librechat:ocr, librechat:librechat:code. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:firstchat, librechat:librechat:custom, librechat:librechat:azure, librechat:librechat:bedrock, librechat:librechat:vertex, librechat:librechat:license, librechat:librechat:ocr, librechat:librechat:code ### 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. #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: partial Local compatible inference and Ollama embeddings are documented; optional services must also be local for a fully private stack. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified. Limitations: - feature_parity: Chat and retrieval can use local endpoints. Tool calling and vision depend on the model; external OCR/search/code services are separate. No complete offline fixture was run. - vendor_hosted_open_models: Does the vendor host open-weight models in EU/CH? A vendor-hosted EU/Swiss open-weight model service was not established for the MIT self-hosted project. - self_hosted_chat — Can chat use a customer-hosted model? [supported]: Custom endpoints can point at customer-hosted compatible model servers, including Ollama-compatible setups. Sources: librechat:librechat:custom. - self_hosted_embeddings — Can retrieval use customer-hosted embeddings? [supported]: The RAG configuration documents Ollama embeddings and local Hugging Face through the appropriate full image. Sources: librechat:librechat:ragcfg. - feature_parity — Which features fail with self-hosted models? [partial]: Chat and retrieval can use local endpoints. Tool calling and vision depend on the model; external OCR/search/code services are separate. No complete offline fixture was run. Sources: librechat:librechat:ragcfg, librechat:librechat:ocr, librechat:librechat:code. - vendor_hosted_open_models — Does the vendor host open-weight models in EU/CH? [unknown]: vendor_hosted_open_models: Does the vendor host open-weight models in EU/CH? A vendor-hosted EU/Swiss open-weight model service was not established for the MIT self-hosted project. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:custom, librechat:librechat:ragcfg, librechat:librechat:ocr, librechat:librechat:code ### 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 #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: partial Model specs and scoped configuration can limit choices; optional user credit reservations provide a blocking mechanism. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified. Limitations: - model_allowlist_by_group: Enforced model specs and role/group configuration overrides can restrict available endpoints/models. The separate management UI is preview; a two-group fixture was not run. - data_bound_models: Can admins restrict which models receive connector or knowledge content? A hard binding between each enterprise content source and a permitted model provider was not established in the Agent and access-control guides. - user_limits: Balance tracking, initial credits/refills and message moderation limits are operator-configurable, rather than a universal vendor allowance. - model_allowlist_by_group — Can admins limit models per group? [partial]: Enforced model specs and role/group configuration overrides can restrict available endpoints/models. The separate management UI is preview; a two-group fixture was not run. Sources: librechat:librechat:modelspec, librechat:librechat:admin, librechat:librechat:access. - data_bound_models — Can admins restrict which models receive connector or knowledge content? [unknown]: data_bound_models: Can admins restrict which models receive connector or knowledge content? A hard binding between each enterprise content source and a permitted model provider was not established in the Agent and access-control guides. - default_model — Can admins set the default model? [supported]: Model-spec presets can define default endpoint/model configurations. Sources: librechat:librechat:modelspec. - user_limits — What per-user message or token limits apply, and are they published? [partial]: Balance tracking, initial credits/refills and message moderation limits are operator-configurable, rather than a universal vendor allowance. Sources: librechat:librechat:balance, librechat:librechat:mod. - limit_behaviour — What happens when a limit is reached? [supported]: Pinned checkBalance reserves credits and throws a TOKEN_BALANCE error when insufficient. This establishes a blocking code path, not an observed end-to-end quota test. Sources: librechat:librechat:balance-pin. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:modelspec, librechat:librechat:admin, librechat:librechat:access, librechat:librechat:balance, librechat:librechat:mod, librechat:librechat:balance-pin ## 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 #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: partial Files can be indexed, injected as extracted text or sent directly to compatible model providers. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=New spreadsheet finding at development source a378657583567310c841d652b0f6b00c83e2bd6b; earlier accepted facts retain their cited release pins; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified. Limitations: - File counts, sizes and provider acceptance depend on deployment settings. - Spreadsheet parsing yields named sheets and CSV values; layout/formula fidelity and the shared fixture remain untested. - formats — Which formats are accepted? [supported]: Documents include PDF/text/Office formats through configured extraction; provider-native acceptance varies, including Bedrock Office formats and Google audio/video. Sources: librechat:librechat:ocr, librechat:librechat:filecfg. - limits — What size and count limits apply per file and chat? [partial]: File counts, sizes and MIME patterns are operator/endpoint settings; provider limits may be stricter. The shared fixture was not uploaded. Sources: librechat:librechat:filecfg, librechat:librechat:ocr. - ocr — Are scanned PDFs read? [supported]: Optional Mistral OCR, Azure/Vertex Mistral OCR and provider-native file processing are documented. Sources: librechat:librechat:ocr. - spreadsheets — Are Excel tables read with structure intact? [partial]: The inspected built-in XLSX/XLS/ODS parser emits each sheet name and CSV values. The current guide lists a 15 MB built-in parser limit. Workbook formatting, formula recalculation and shared-fixture accuracy were not established. Sources: librechat:librechat:r4-spreadsheet-parser, librechat:librechat:r4-text-current. - full_vs_chunked — Is the whole file used or only retrieved parts, and does the user see which? [supported]: RAG retrieves indexed chunks; Upload as Text and Agent File Context inject extracted full text, subject to context limits. Sources: librechat:librechat:rag, librechat:librechat:text, librechat:librechat:ocr. Checked 2026-10-26; agent cross-checked 2026-10-26; check again by 2026-12-25. Sources: librechat:librechat:ocr, librechat:librechat:filecfg, librechat:librechat:rag, librechat:librechat:text, librechat:librechat:r4-spreadsheet-parser, librechat:librechat:r4-text-current ### 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 #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: partial Agents and personal Projects keep files across chats; shared Agent access is distinct from personal Project ownership. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified. Limitations: - sharing_scope: Agents can share files/knowledge with permitted users/groups/roles; Projects themselves are personal and cannot be shared or transferred. - size_limits: What are the collection limits? No universal collection storage/size allowance was established; limits are deployment and file-configuration dependent. - persistent_collections — Can users keep document collections across chats? [supported]: Agent File Search/File Context and Project reference files persist for later chats. Sources: librechat:librechat:agents, librechat:librechat:projects. - sharing_scope — Can collections be shared with users, groups or the whole organisation? [partial]: Agents can share files/knowledge with permitted users/groups/roles; Projects themselves are personal and cannot be shared or transferred. Sources: librechat:librechat:access, librechat:librechat:agents, librechat:librechat:projects. - size_limits — What are the collection limits? [unknown]: size_limits: What are the collection limits? No universal collection storage/size allowance was established; limits are deployment and file-configuration dependent. - assistant_binding — Can collections be bound to an assistant? [supported]: Agent File Search and File Context bind retrieved or extracted knowledge to an Agent. Sources: librechat:librechat:agents, librechat:librechat:ocr. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:agents, librechat:librechat:projects, librechat:librechat:access, librechat:librechat:ocr ### 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 #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: partial SharePoint and OneDrive have a documented delegated file picker. Other enterprise systems require separately verified tools or connectors. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified. Limitations: - microsoft_365: SharePoint Online and OneDrive for Business can be browsed and attached through Entra token reuse/OBO, delegated AllSites.Read and Files.Read.All, and admin consent. Outlook/Teams source access was not established. - google_workspace: Which Google sources are connected? Google Drive/Gmail, Confluence/Jira and other named business-system connectors were not verified from first-party maintained connector documentation; generic MCP compatibility is not a connector catalog. - atlassian: Confluence and Jira? Google Drive/Gmail, Confluence/Jira and other named business-system connectors were not verified from first-party maintained connector documentation; generic MCP compatibility is not a connector catalog. - other_systems: Which other business systems? Google Drive/Gmail, Confluence/Jira and other named business-system connectors were not verified from first-party maintained connector documentation; generic MCP compatibility is not a connector catalog. - on_prem_sources: Custom local MCP stdio servers can reach systems available to the deployment, but a maintained file-share/database connector and its permissions were not verified. - microsoft_365 — Which M365 sources (SharePoint, OneDrive, Outlook, Teams) are connected? [partial]: SharePoint Online and OneDrive for Business can be browsed and attached through Entra token reuse/OBO, delegated AllSites.Read and Files.Read.All, and admin consent. Outlook/Teams source access was not established. Sources: librechat:librechat:sharepoint. - google_workspace — Which Google sources are connected? [unknown]: google_workspace: Which Google sources are connected? Google Drive/Gmail, Confluence/Jira and other named business-system connectors were not verified from first-party maintained connector documentation; generic MCP compatibility is not a connector catalog. - atlassian — Confluence and Jira? [unknown]: atlassian: Confluence and Jira? Google Drive/Gmail, Confluence/Jira and other named business-system connectors were not verified from first-party maintained connector documentation; generic MCP compatibility is not a connector catalog. - other_systems — Which other business systems? [unknown]: other_systems: Which other business systems? Google Drive/Gmail, Confluence/Jira and other named business-system connectors were not verified from first-party maintained connector documentation; generic MCP compatibility is not a connector catalog. - on_prem_sources — Can on-prem file shares or databases be connected? [partial]: Custom local MCP stdio servers can reach systems available to the deployment, but a maintained file-share/database connector and its permissions were not verified. Sources: librechat:librechat:mcpcfg. - connector_provider — Who builds and maintains each connector? [supported]: LibreChat documents the Microsoft picker. Other MCP tool integrations are separately configured and maintained by their respective server authors/operators. Sources: librechat:librechat:sharepoint, librechat:librechat:mcp. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:sharepoint, librechat:librechat:mcpcfg, librechat:librechat:mcp ### 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 #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: partial Product resource ACLs and delegated Microsoft file selection are documented. Continuing source permissions for copied content remain untested. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified. Limitations: - source_permissions_respected: Are source permissions enforced per user? No restricted-document two-user fixture or grant/revocation test was run. Source permission enforcement, revocation delay and Purview label handling remain unverified. - enforcement_point: LibreChat ACLs control Agent/file resources; Microsoft delegated OBO limits source downloads as the signed-in user. No query-time source ACL check for previously copied chunks was established. - revocation_delay: How quickly does a removed permission take effect? No restricted-document two-user fixture or grant/revocation test was run. Source permission enforcement, revocation delay and Purview label handling remain unverified. - admin_scope_controls: Operators can scope Agent/resource grants and its selected files. Site/folder/label exclusion across sources was not established. - sensitivity_labels: Are Microsoft Purview or similar labels respected? No restricted-document two-user fixture or grant/revocation test was run. Source permission enforcement, revocation delay and Purview label handling remain unverified. - source_permissions_respected — Are source permissions enforced per user? [unknown]: source_permissions_respected: Are source permissions enforced per user? No restricted-document two-user fixture or grant/revocation test was run. Source permission enforcement, revocation delay and Purview label handling remain unverified. - enforcement_point — Does the source system, a mirrored index or nothing enforce them? [partial]: LibreChat ACLs control Agent/file resources; Microsoft delegated OBO limits source downloads as the signed-in user. No query-time source ACL check for previously copied chunks was established. Sources: librechat:librechat:access, librechat:librechat:sharepoint. - revocation_delay — How quickly does a removed permission take effect? [unknown]: revocation_delay: How quickly does a removed permission take effect? No restricted-document two-user fixture or grant/revocation test was run. Source permission enforcement, revocation delay and Purview label handling remain unverified. - admin_scope_controls — Can admins exclude sites, folders or labels? [partial]: Operators can scope Agent/resource grants and its selected files. Site/folder/label exclusion across sources was not established. Sources: librechat:librechat:access, librechat:librechat:agents. - sensitivity_labels — Are Microsoft Purview or similar labels respected? [unknown]: sensitivity_labels: Are Microsoft Purview or similar labels respected? No restricted-document two-user fixture or grant/revocation test was run. Source permission enforcement, revocation delay and Purview label handling remain unverified. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:access, librechat:librechat:sharepoint, librechat:librechat:agents ### 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 #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: partial The RAG API copies uploaded content into PGVector; imported files do not by themselves establish live enterprise synchronization. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified. Limitations: - sync_interval: How often does an index refresh? No periodic enterprise-source sync contract, source edit/delete propagation bound or timed fixture was established from the RAG and Microsoft import guides. - deletion_propagation: How quickly does a deleted document disappear? No periodic enterprise-source sync contract, source edit/delete propagation bound or timed fixture was established from the RAG and Microsoft import guides. - live_or_indexed — Is content searched live or copied into an index? [supported]: The RAG API indexes uploaded documents into PostgreSQL/PGVector; file-context mode stores extracted text in Agent instructions. Sources: librechat:librechat:rag, librechat:librechat:ocr. - sync_interval — How often does an index refresh? [unknown]: sync_interval: How often does an index refresh? No periodic enterprise-source sync contract, source edit/delete propagation bound or timed fixture was established from the RAG and Microsoft import guides. - deletion_propagation — How quickly does a deleted document disappear? [unknown]: deletion_propagation: How quickly does a deleted document disappear? No periodic enterprise-source sync contract, source edit/delete propagation bound or timed fixture was established from the RAG and Microsoft import guides. - index_location — Where is indexed content stored? [supported]: The operator chooses the RAG database and its location, independently of the inference provider. Sources: librechat:librechat:rag, librechat:librechat:compose-pin. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:rag, librechat:librechat:ocr, librechat:librechat:compose-pin ### 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 #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: partial File-search citations are documented; retrieval accuracy remains unmeasured. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified. Limitations: - citation_accuracy: Do the cited passages support the answer? The shared multilingual factual/cross-document/no-answer question set was not run. Citation correctness, cross-language success, no-answer reliability and observed accuracy remain unknown. - cross_language: Does a question in one language find documents in another? The shared multilingual factual/cross-document/no-answer question set was not run. Citation correctness, cross-language success, no-answer reliability and observed accuracy remain unknown. - no_answer_behaviour: Does it say when the corpus has no answer? The shared multilingual factual/cross-document/no-answer question set was not run. Citation correctness, cross-language success, no-answer reliability and observed accuracy remain unknown. - observed_accuracy: How many of the question set were answered correctly? The shared multilingual factual/cross-document/no-answer question set was not run. Citation correctness, cross-language success, no-answer reliability and observed accuracy remain unknown. - citations — Are answers linked to specific sources? [supported]: RAG/File Search provides retrieved source references and citation controls. Sources: librechat:librechat:rag, librechat:librechat:access. - citation_accuracy — Do the cited passages support the answer? [unknown]: citation_accuracy: Do the cited passages support the answer? The shared multilingual factual/cross-document/no-answer question set was not run. Citation correctness, cross-language success, no-answer reliability and observed accuracy remain unknown. - cross_language — Does a question in one language find documents in another? [unknown]: cross_language: Does a question in one language find documents in another? The shared multilingual factual/cross-document/no-answer question set was not run. Citation correctness, cross-language success, no-answer reliability and observed accuracy remain unknown. - no_answer_behaviour — Does it say when the corpus has no answer? [unknown]: no_answer_behaviour: Does it say when the corpus has no answer? The shared multilingual factual/cross-document/no-answer question set was not run. Citation correctness, cross-language success, no-answer reliability and observed accuracy remain unknown. - observed_accuracy — How many of the question set were answered correctly? [unknown]: observed_accuracy: How many of the question set were answered correctly? The shared multilingual factual/cross-document/no-answer question set was not run. Citation correctness, cross-language success, no-answer reliability and observed accuracy remain unknown. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:rag, librechat:librechat:access ### 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 #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: supported Opt-in user memory stores editable key/value context across chats; Projects and Agents provide additional persistent instructions. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified. - custom_instructions — Can users set persistent instructions? [supported]: Projects retain instructions across their chats; Agents retain system instructions. Sources: librechat:librechat:projects, librechat:librechat:agents. - cross_chat_memory — Does the product remember facts across chats? [supported]: User Memory injects configured key/value entries across chats and is not semantic search over all past conversations. Sources: librechat:librechat:memory. - user_memory_controls — Can users view, edit and delete memories? [supported]: Users add/edit/remove entries and can toggle memory when permitted. Sources: librechat:librechat:memory. - admin_memory_controls — Can admins turn memory off? [supported]: Memory is disabled until configured and its feature permissions can be restricted by role. Sources: librechat:librechat:memory, librechat:librechat:access. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:projects, librechat:librechat:agents, librechat:librechat:memory, librechat:librechat:access ## 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 #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: supported Agents combine instructions, a model, knowledge and tools, with version history and a permissioned internal catalog. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified. - create_assistants — Can users create assistants with instructions, knowledge and tools? [supported]: The Agent Builder creates reusable instructions/model/files/tools/skills configurations. Sources: librechat:librechat:agents. - creator_permissions — Can admins limit who creates them? [supported]: AGENTS CREATE and sharing permissions can be restricted by role; resource grants control access. Sources: librechat:librechat:access. - sharing_scope — Can assistants be shared with users, groups or everyone? [supported]: Agent ACLs support users, groups, roles and all authenticated users when public sharing is permitted. Sources: librechat:librechat:access. - catalogue — Is there an internal assistant directory? [supported]: Agents have a marketplace/catalog and searchable builder tool library. Sources: librechat:librechat:agents. - prompt_library — Are shared prompt templates available? [supported]: Prompt resources have use/create/share/share-public permissions and ACLs. Sources: librechat:librechat:access. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:agents, librechat:librechat:access ### 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 #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: partial Agent tools include file search, code, web and Actions, with local/remote MCP and configurable approval boundaries. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=Customer-operated or third-party MCP servers, Optional separate Code Interpreter service; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified. Limitations: - tool_approval: Agent/code environments document approval modes and individual tool-call approvals. The default policy and every external side-effect boundary were not exercised. - builtin_tools — Which tools are built in? [supported]: Agent capabilities include file search/context, web search, memory and optionally configured code execution/image tools. Sources: librechat:librechat:agents, librechat:librechat:images. - custom_actions — Can admins add API actions? [supported]: Agents support custom API Actions configured in the tool library. Sources: librechat:librechat:agents. - mcp_client — Can it use remote MCP servers, and with what admin control? [supported]: Configured MCP transports include stdio, SSE and Streamable HTTP; YAML and permissioned UI setup are documented. Sources: librechat:librechat:mcp, librechat:librechat:mcpcfg. - tool_auth — Do tools act as the user or as a shared account? [supported]: MCP supports configured credentials/headers and OAuth; credential and resource ownership scope depends on each server configuration. Sources: librechat:librechat:mcp, librechat:librechat:mcpcfg. - tool_approval — Can admins approve or block tools, and can users confirm actions before they run? [partial]: Agent/code environments document approval modes and individual tool-call approvals. The default policy and every external side-effect boundary were not exercised. Sources: librechat:librechat:agents, librechat:librechat:code. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:agents, librechat:librechat:images, librechat:librechat:mcp, librechat:librechat:mcpcfg, librechat:librechat:code ### 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 #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: partial Web search combines configured search, scraping and optional reranking services; source queries can leave the installation boundary. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified. Limitations: - deep_research: Agents can perform repeated tool operations and web research. No dedicated report fixture, quality result or preset research SLA was verified. - web_search — Is web search available? [supported]: Tool-capable chats/Agents can use the configured web search capability. Sources: librechat:librechat:web, librechat:librechat:agents. - admin_toggle — Can admins disable it per organisation or group? [supported]: WEB_SEARCH feature permissions control use; operators configure whether its provider stack is available. Sources: librechat:librechat:access, librechat:librechat:web. - search_provider — Which search provider handles queries, and where? [supported]: Documented choices include Serper, SearXNG, Tavily and Keenable, with Firecrawl/Tavily/Keenable scraping and optional Jina/Cohere reranking. Geography depends on the chosen services. Sources: librechat:librechat:web. - deep_research — Is multi-step research with a report available? [partial]: Agents can perform repeated tool operations and web research. No dedicated report fixture, quality result or preset research SLA was verified. Sources: librechat:librechat:agents, librechat:librechat:web. - web_citations — Are web sources cited? [supported]: The web-search guide documents source references/citations from search and fetched content. Sources: librechat:librechat:web. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:web, librechat:librechat:agents, librechat:librechat:access ### 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 #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: partial Experimental Scheduled Chats run saved Agents on cron schedules; beta Agent Events can receive external deliveries. Availability: beta Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=Experimental schedules explicitly enabled, Beta Agents API for external Agent Events; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified. Limitations: - workflow_builder: Agent Builder supports tool workflows and subagent configurations; no general business no-code flow editor was established. - event_triggers: The beta Agents API includes authenticated Agent Events. A built-in email/form trigger catalog was not verified. - workflow_builder — Is there a workflow or chain builder? [partial]: Agent Builder supports tool workflows and subagent configurations; no general business no-code flow editor was established. Sources: librechat:librechat:agents. - scheduled_tasks — Can prompts or assistants run on a schedule? [supported]: Scheduled Chats supports hourly/daily/weekly/custom cron with time zones, owner scope and execution checks; it is experimental and off by default. Sources: librechat:librechat:schedule. - event_triggers — Can external events start a workflow? [partial]: The beta Agents API includes authenticated Agent Events. A built-in email/form trigger catalog was not verified. Sources: librechat:librechat:api. - builder_audience — Is building aimed at business users, IT or developers? [supported]: Agent Builder is a user UI; API-event and runtime configuration require technical deployment work. Sources: librechat:librechat:agents, librechat:librechat:schedule, librechat:librechat:api. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:agents, librechat:librechat:schedule, librechat:librechat:api ### 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 #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: partial Agent runs expose reasoning/tool activity and optional approval, interruption and cooperative stop controls. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified. Limitations: - No gather-documents, draft-summary and propose-email task was run. - Highly experimental attached workspaces are distinct from ordinary Agent tool use. - agent_mode — Is there an agent mode for multi-step tasks? [supported]: Agents execute multi-step tool workflows; code/workspace capabilities require a compatible separately deployed service. Sources: librechat:librechat:agents, librechat:librechat:code. - visible_steps — Are steps and tool calls shown? [supported]: Activity groups and tool cards distinguish preparation, execution, completion, cancellation and failure. Sources: librechat:librechat:agents. - side_effect_confirmation — Must the user confirm actions with side effects? [partial]: Attached environments can expose Ask before changes/Accept edits/Full access, bounded by operator tool rules. This is configurable, not a guarantee that all side effects require confirmation. Sources: librechat:librechat:agents, librechat:librechat:code. - stop_control — Can the user stop a running task? [partial]: The release documents interruption/steering; ordinary background-tool cancellation is optional and cooperative, so an uncooperative tool may still finish. Sources: librechat:librechat:agents, librechat:librechat:releases. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:agents, librechat:librechat:code, librechat:librechat:releases ### 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 #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: partial The beta Agents API provides inference, Agent management and authenticated events; deployment guards and limitations are explicit. Availability: beta Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified. Limitations: - knowledge_api: The beta management surface includes Agent/Skill management. A complete public knowledge-ingestion contract and fixture were not verified. - api_governance: Agent access and remote-agent permissions gate APIs, with source identity bound for events. Complete logging/budget/model parity across routes was not tested. - mcp_server: Does the product expose itself to other agents over MCP? A native product-wide MCP server was not established; being an MCP client does not establish that interface. - chat_api — Is there an API for chat and assistants? [supported]: Chat Completions and Open Responses interfaces expose saved Agents, with API-key or configured OIDC authentication. Sources: librechat:librechat:api. - knowledge_api — Can documents be loaded through an API? [partial]: The beta management surface includes Agent/Skill management. A complete public knowledge-ingestion contract and fixture were not verified. Sources: librechat:librechat:api. - api_governance — Do audit, budgets and model rules apply to API use? [partial]: Agent access and remote-agent permissions gate APIs, with source identity bound for events. Complete logging/budget/model parity across routes was not tested. Sources: librechat:librechat:api, librechat:librechat:access. - mcp_server — Does the product expose itself to other agents over MCP? [unknown]: mcp_server: Does the product expose itself to other agents over MCP? A native product-wide MCP server was not established; being an MCP client does not establish that interface. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:api, librechat:librechat:access ## 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 #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: partial The main deployment is a responsive browser client. Native clients, MDM and a supported sidebar extension were not verified. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified. Limitations: - desktop_apps: Windows and macOS apps? The self-host installation and client docs did not establish native Windows/macOS apps, a first-party browser extension or Intune/MDM configuration. - mobile_apps: Docs describe mobile navigation and temporary-chat controls in the web UI. No native iOS/Android client with company SSO was established. - browser_extension: Is there a browser extension or sidebar? The self-host installation and client docs did not establish native Windows/macOS apps, a first-party browser extension or Intune/MDM configuration. - managed_deployment: Can IT deploy and configure clients through MDM? The self-host installation and client docs did not establish native Windows/macOS apps, a first-party browser extension or Intune/MDM configuration. - client_feature_gaps: Desktop/mobile layouts expose different navigation controls; no comprehensive parity matrix was tested. - web — Is a full web client available? [supported]: A Docker/npm deployment serves a browser application at the configured server URL. Sources: librechat:librechat:firstchat, librechat:librechat:local. - desktop_apps — Windows and macOS apps? [unknown]: desktop_apps: Windows and macOS apps? The self-host installation and client docs did not establish native Windows/macOS apps, a first-party browser extension or Intune/MDM configuration. - mobile_apps — iOS and Android apps with SSO? [partial]: Docs describe mobile navigation and temporary-chat controls in the web UI. No native iOS/Android client with company SSO was established. Sources: librechat:librechat:retention, librechat:librechat:insights. - browser_extension — Is there a browser extension or sidebar? [unknown]: browser_extension: Is there a browser extension or sidebar? The self-host installation and client docs did not establish native Windows/macOS apps, a first-party browser extension or Intune/MDM configuration. - managed_deployment — Can IT deploy and configure clients through MDM? [unknown]: managed_deployment: Can IT deploy and configure clients through MDM? The self-host installation and client docs did not establish native Windows/macOS apps, a first-party browser extension or Intune/MDM configuration. - client_feature_gaps — Which features are missing on mobile? [partial]: Desktop/mobile layouts expose different navigation controls; no comprehensive parity matrix was tested. Sources: librechat:librechat:retention, librechat:librechat:insights. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:firstchat, librechat:librechat:local, librechat:librechat:retention, librechat:librechat:insights ### 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 #### LibreChat 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. ### 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 #### LibreChat 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. ### 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 #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: partial Configured Agent image tools generate and edit images; model service rights/costs remain separate. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified. Limitations: - admin_control: Operators control tool credentials/configuration and Agent creation/access permissions. A dedicated per-group image-spend switch was not established. - usage_terms: What usage rights apply to output? Generated-output rights and complete per-image cost visibility were not established as a LibreChat software entitlement. - image_generation — Can users generate images, with which models? [supported]: OpenAI Image Tools and additional documented provider tools attach to an Agent; the current guide defaults OpenAI tools to gpt-image-2.5-flare. Sources: librechat:librechat:images. - image_editing — Can users edit uploaded images? [supported]: The image guide documents editing/remixing uploaded images using image IDs and compatible tools. Sources: librechat:librechat:images. - admin_control — Can admins restrict image generation? [partial]: Operators control tool credentials/configuration and Agent creation/access permissions. A dedicated per-group image-spend switch was not established. Sources: librechat:librechat:images, librechat:librechat:access. - usage_terms — What usage rights apply to output? [unknown]: usage_terms: What usage rights apply to output? Generated-output rights and complete per-image cost visibility were not established as a LibreChat software entitlement. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:images, librechat:librechat:access ### 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 #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: partial LibreChat documents STT, TTS and a hands-free conversation mode that chains them. Real-time speech-to-speech behavior, meeting outcomes and Swiss German recognition remain unverified. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Current self-hosted LibreChat Speech Settings documentation retrieved 2026-10-21; no voice-latency or dialect fixture performed; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=Optional configured STT/TTS engines and provider credentials; self-hosted speech services need allowedAddresses; deployment_mode=on-premise; region=Customer-selected app infrastructure; audio processing depends on browser or configured external/self-hosted speech engines, with no universal region verified; os=not specified. Limitations: - Conversation mode is a chain of transcription, text generation and playback; real-time audio-to-audio behavior, interruption and latency were not verified. - Audio location depends on the chosen engine. No meeting or Swiss German fixture was run. - dictation — Can users dictate prompts? [supported]: Speech configuration provides STT for audio input. Sources: librechat:librechat:speech. - read_aloud — Can answers be read aloud? [supported]: Speech configuration provides TTS for model responses. Sources: librechat:librechat:speech. - voice_conversation — Is a live voice mode available? [partial]: speechTab.conversationMode chains STT and TTS for hands-free turns: autoSendText sends the transcript after a configured delay, and automaticPlayback reads a completed response. Microphone recording is initially started by the user. Real-time speech-to-speech, interruption behavior and end-to-end latency were not tested. Sources: librechat:librechat:speech-conversation-r2. - meeting_summaries — Are meetings transcribed and summarised? [unknown]: No meeting capture/integration, speaker diarization or meeting-summary fixture was verified in the reviewed speech documentation. - swiss_german_speech — Is Swiss German speech recognised? [unknown]: Swiss German recognition and transcript quality were not tested; a language setting does not establish dialect accuracy. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:speech, librechat:librechat:speech-conversation-r2 ### 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 #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: partial The separate Code Interpreter runs analysis and produces downloadable files; artifacts provide code/HTML/diagram previews. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=Separately operated compatible Code Interpreter service, Experimental stateful workspaces only if explicitly configured; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified. Limitations: - charts: Code execution and generated-file downloads support chart artifacts, but the shared spreadsheet/chart fixture was not run. - office_file_output: Generated files are downloadable; editable Word/Excel/PowerPoint fidelity was not established with a fixture. - canvas_editing: Artifacts render React/HTML/Mermaid content and source; a rich Office document editor was not established. - data_analysis — Can it analyse spreadsheets with executed code? [supported]: Configured Code Interpreter executes programs against uploaded files in its separate sandbox. Sources: librechat:librechat:code. - charts — Can it produce charts? [partial]: Code execution and generated-file downloads support chart artifacts, but the shared spreadsheet/chart fixture was not run. Sources: librechat:librechat:code. - office_file_output — Can it create Word, Excel or PowerPoint files? [partial]: Generated files are downloadable; editable Word/Excel/PowerPoint fidelity was not established with a fixture. Sources: librechat:librechat:code. - canvas_editing — Is there a document or canvas editor for iterating on output? [partial]: Artifacts render React/HTML/Mermaid content and source; a rich Office document editor was not established. Sources: librechat:librechat:artifacts. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:code, librechat:librechat:artifacts ### 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 #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: partial Shared chat links publish transcript snapshots and optional files. Projects are personal, and shared source permission boundaries need care. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified. Limitations: - group_chat: Can several people chat together with the AI? Simultaneous multi-person AI group chat was not established from Projects and shareable-link documentation; link continuation creates a separate personal copy. - share_permission_boundary: Published file snapshots are served independently of the owner’s live file ACL. Sharing grants access to the published copy, not continuing source-system authorization; no restricted-source fixture was run. - share_chats — Can chats be shared inside the organisation? [supported]: Authenticated shared links are supported, with optional public viewing; public unauthenticated access is off by default. Sources: librechat:librechat:share. - team_spaces — Are shared projects or workspaces available? [unsupported]: Projects specifically cannot be shared or transferred and are personal to the creator. Shared Agents/resources are a separate capability. Sources: librechat:librechat:projects. - group_chat — Can several people chat together with the AI? [unknown]: group_chat: Can several people chat together with the AI? Simultaneous multi-person AI group chat was not established from Projects and shareable-link documentation; link continuation creates a separate personal copy. - share_permission_boundary — Does sharing respect the recipient's access to sources? [partial]: Published file snapshots are served independently of the owner’s live file ACL. Sharing grants access to the published copy, not continuing source-system authorization; no restricted-source fixture was run. Sources: librechat:librechat:share. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:share, librechat:librechat:projects ### 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 #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: partial English, German, French and Italian UI resources are registered in the pinned client; quality and accessibility conformance were not evaluated. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified. Limitations: - dach_language_quality: Are German, French and Italian UIs complete and natural? No complete DE/FR/IT walkthrough, German separate-admin-panel coverage test or WCAG conformance statement/report was verified. - accessibility_statement: Is there a WCAG conformance statement? No complete DE/FR/IT walkthrough, German separate-admin-panel coverage test or WCAG conformance statement/report was verified. - admin_ui_languages: Is the admin interface available in German? No complete DE/FR/IT walkthrough, German separate-admin-panel coverage test or WCAG conformance statement/report was verified. - ui_languages — Which UI languages are offered? [supported]: The client i18n implementation registers en, de, fr and it among community-maintained translations. Sources: librechat:librechat:i18n-pin. - dach_language_quality — Are German, French and Italian UIs complete and natural? [unknown]: dach_language_quality: Are German, French and Italian UIs complete and natural? No complete DE/FR/IT walkthrough, German separate-admin-panel coverage test or WCAG conformance statement/report was verified. - accessibility_statement — Is there a WCAG conformance statement? [unknown]: accessibility_statement: Is there a WCAG conformance statement? No complete DE/FR/IT walkthrough, German separate-admin-panel coverage test or WCAG conformance statement/report was verified. - admin_ui_languages — Is the admin interface available in German? [unknown]: admin_ui_languages: Is the admin interface available in German? No complete DE/FR/IT walkthrough, German separate-admin-panel coverage test or WCAG conformance statement/report was verified. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:i18n-pin ## 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 #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: partial Self-hosted authentication supports OAuth/OIDC, SAML and LDAP; local/LDAP TOTP can be enforced. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified. Limitations: - conditional_access: Entra authentication and token reuse are documented, but an actual conditional-access/device-policy login was not tested. - domain_capture: Can the company claim its email domain? Registration/domain filters were not established as a tenant-wide company-domain ownership claim. - sso_protocols — Which SSO protocols and identity providers work? [supported]: OIDC/OAuth providers include Entra, Google, Keycloak and Auth0; SAML and LDAP are documented separately. Sources: librechat:librechat:openid, librechat:librechat:saml, librechat:librechat:auth. - sso_plan — Which plan includes SSO? [supported]: The authentication configuration belongs to the MIT self-hosted project, with no separate SSO licence tariff. Sources: librechat:librechat:license, librechat:librechat:auth. - mfa — Can MFA be enforced? [supported]: ENFORCE_TWO_FACTOR_AUTHENTICATION requires local/LDAP enrollment and prevents disabling it; federated accounts depend on IdP MFA. Sources: librechat:librechat:auth. - conditional_access — Do Entra conditional-access policies apply? [partial]: Entra authentication and token reuse are documented, but an actual conditional-access/device-policy login was not tested. Sources: librechat:librechat:entra. - domain_capture — Can the company claim its email domain? [unknown]: domain_capture: Can the company claim its email domain? Registration/domain filters were not established as a tenant-wide company-domain ownership claim. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:openid, librechat:librechat:saml, librechat:librechat:auth, librechat:librechat:license, librechat:librechat:entra ### 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 #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: partial Entra group synchronization and federated account creation are documented; SCIM and leaver content transfer remain unknown. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified. Limitations: - scim: Is SCIM provisioning supported? SCIM was not established in the authentication/access docs or pinned repository path review. No two-user deprovisioning fixture was run. - deprovisioning: The docs provide user deletion scripts, but content ownership transfer and revocation behavior were not fixture-tested. - seat_assignment: Operators manage accounts/roles under an MIT licence; there is no per-seat licence entitlement in the scoped source. - scim — Is SCIM provisioning supported? [unknown]: scim: Is SCIM provisioning supported? SCIM was not established in the authentication/access docs or pinned repository path review. No two-user deprovisioning fixture was run. - group_sync — Are identity-provider groups synced? [supported]: With Entra OIDC token reuse, Graph groups sync at login; resource ACL principal membership has a documented cache. Sources: librechat:librechat:access, librechat:librechat:entra. - jit_provisioning — Are users created at first login? [supported]: Federated login creates accounts according to the authentication configuration; OpenID/SAML registration cannot be independently disabled. Sources: librechat:librechat:auth. - deprovisioning — What happens to a removed user's data and shared assets? [partial]: The docs provide user deletion scripts, but content ownership transfer and revocation behavior were not fixture-tested. Sources: librechat:librechat:auth. - seat_assignment — Can admins assign and reclaim seats? [partial]: Operators manage accounts/roles under an MIT licence; there is no per-seat licence entitlement in the scoped source. Sources: librechat:librechat:auth, librechat:librechat:license. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:access, librechat:librechat:entra, librechat:librechat:auth, librechat:librechat:license ### 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 #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: partial Role permissions, resource ACLs and system grants support granular governance; the separate management UI remains preview. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server, Separately deployed LibreChat Admin Panel preview; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=Separate Admin Panel preview for GUI management; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified. Limitations: - Separate admin management UI is preview; the core authorization model is documented as available. - No two-group disabled-feature fixture was run. - admin_roles — Which admin roles exist, and can admin rights be delegated? [supported]: ADMIN/USER and custom roles exist; capability grants can delegate selected administrative functions without full admin. Sources: librechat:librechat:access. - groups — Can permissions be set per group? [supported]: Local and Entra groups can receive ACLs, system grants and configuration overrides. Sources: librechat:librechat:access, librechat:librechat:admin. - feature_toggles — Which features can be switched on or off per group? [supported]: Permissions include Agents, MCP, prompts, memory, search, file search/citations and code execution. Sources: librechat:librechat:access. - multi_entity — Can subsidiaries or departments be separated within one contract? [partial]: Tenant-scoped API queries and group/configuration boundaries are documented. A commercial multi-entity contract and tested tenant isolation were not established. Sources: librechat:librechat:insights, librechat:librechat:access. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:access, librechat:librechat:admin, librechat:librechat:insights ### 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 #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: partial Optional Insights reports identifiable activity; token transactions and optional tracing are separate sources of usage detail. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified. Limitations: - breakdowns: Insights supports Agent filtering and user activity; recorded token/context cost details are per model/endpoint. Complete group/feature/assistant exports were not established. - export: Can usage data be exported? A documented complete admin analytics export and group/cost-centre dataset were not verified. - privacy_modes: Insights is off unless enabled and is capability-gated; it can display names, emails and first-message content. Pseudonymized reporting was not established. - adoption_dashboard — Is there an adoption dashboard? [supported]: Opt-in Insights reports conversations, unique users, messages, tokens, top users and recent conversations. Sources: librechat:librechat:insights. - breakdowns — Can usage be broken down by group, model, feature and assistant? [partial]: Insights supports Agent filtering and user activity; recorded token/context cost details are per model/endpoint. Complete group/feature/assistant exports were not established. Sources: librechat:librechat:insights, librechat:librechat:tokens. - export — Can usage data be exported? [unknown]: export: Can usage data be exported? A documented complete admin analytics export and group/cost-centre dataset were not verified. - privacy_modes — Can per-person reporting be limited or pseudonymised? [partial]: Insights is off unless enabled and is capability-gated; it can display names, emails and first-message content. Pseudonymized reporting was not established. Sources: librechat:librechat:insights. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:insights, librechat:librechat:tokens ### 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 #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: partial Optional token-credit balances block admission when insufficient; credit estimates differ from actual cloud invoices. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified. Limitations: - cost_visibility: Token transactions and configured token prices support per-user/model estimates. Insights explicitly reports activity rather than monetary billing. - budgets: Optional per-user start balances and automatic refills are documented. Group/cost-centre pooled budgets were not established. - chargeback: Can costs be exported per cost centre? Cost-centre chargeback exports and reconciliation to actual vendor invoices were not established. - cost_visibility — Can admins see cost or consumption per user and group? [partial]: Token transactions and configured token prices support per-user/model estimates. Insights explicitly reports activity rather than monetary billing. Sources: librechat:librechat:tokens, librechat:librechat:insights. - budgets — Can budgets be set per user or group? [partial]: Optional per-user start balances and automatic refills are documented. Group/cost-centre pooled budgets were not established. Sources: librechat:librechat:balance. - budget_enforcement — Does reaching a budget alert, block or downgrade? [supported]: Pinned balance middleware reserves estimated token cost and throws an error if credits cannot be reserved; no low-budget trial was run. Sources: librechat:librechat:balance-pin. - chargeback — Can costs be exported per cost centre? [unknown]: chargeback: Can costs be exported per cost centre? Cost-centre chargeback exports and reconciliation to actual vendor invoices were not established. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:tokens, librechat:librechat:insights, librechat:librechat:balance, librechat:librechat:balance-pin ### 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 #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: partial Operational logs and persisted chats are available; a complete audit retention/integrity or eDiscovery system was not verified. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified. Limitations: - admin_events: Backend logs capture errors/debug activity and can include operational/security actions. A complete immutable admin-event schema was not established. - content_logging: Chats are persisted in MongoDB subject to retention settings; external tracing is optional. This is not a verified compliance archive. - siem_export: Operators can feed log files to external systems such as ELK. A native managed SIEM stream and integrity guarantee were not verified. - ediscovery: Are eDiscovery and legal hold supported? No eDiscovery/legal hold, tamper-evident archive or complete prompt/file/connector event coverage was verified. - log_retention: The logging guide describes 14-day rotation. Rotation is not evidence of an enforced legal retention or deletion guarantee across external sinks. - admin_events — Are admin and security events logged? [partial]: Backend logs capture errors/debug activity and can include operational/security actions. A complete immutable admin-event schema was not established. Sources: librechat:librechat:logging. - content_logging — Can prompts and answers be retained for compliance, and is it configurable? [partial]: Chats are persisted in MongoDB subject to retention settings; external tracing is optional. This is not a verified compliance archive. Sources: librechat:librechat:retention, librechat:librechat:compose-pin. - siem_export — Can logs stream to a SIEM or be exported? [partial]: Operators can feed log files to external systems such as ELK. A native managed SIEM stream and integrity guarantee were not verified. Sources: librechat:librechat:logging. - ediscovery — Are eDiscovery and legal hold supported? [unknown]: ediscovery: Are eDiscovery and legal hold supported? No eDiscovery/legal hold, tamper-evident archive or complete prompt/file/connector event coverage was verified. - log_retention — How long are logs kept? [partial]: The logging guide describes 14-day rotation. Rotation is not evidence of an enforced legal retention or deletion guarantee across external sinks. Sources: librechat:librechat:logging. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:logging, librechat:librechat:retention, librechat:librechat:compose-pin ### 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 #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: partial Optional server-side content filters support configured pattern detection, blocking and auditing, plus narrowly scoped Agent text redaction. External DLP integration and fixture accuracy remain unknown. Availability: source-only Delivery: native Scope: surfaces=Customer-operated web application and server; version=Development source a378657583567310c841d652b0f6b00c83e2bd6b; current Latest (dev) documentation; limited redaction announced in config v1.3.18 on 2026-10-22; plan=Customer-operated LibreChat; optional base-YAML content policies, disabled unless configured; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified. Limitations: - Development-source finding; no running instance or AHV/IBAN fixture. - Filtering is opt-in and limited to configured sources/fields. Default patterns cover credential shapes, not every PII class. - Redaction applies only to eligible fresh Agent text; encrypted originals remain stored. - A dedicated external DLP integration remains unverified. - pii_detection — Is personal data detected in prompts and files? [partial]: Configured source-aware policies can inspect selected prompt fields and file names/extracted text/transcripts. Built-in starter rules match credentials; admins must supply additional personal-data patterns. Opaque files may be allowed by default or explicitly blocked. AHV/IBAN and confidential-file detection accuracy were not tested. Sources: librechat:librechat:r4-content-filter, librechat:librechat:r4-pii-runtime, librechat:librechat:r4-patterns, librechat:librechat:r4-private-submission, librechat:librechat:r4-filter-middleware. - pii_action — Is it redacted, masked, blocked or only warned? [partial]: Configured matches can block or audit. Redaction transforms only fresh, text-only interactive Agent submissions carrying clientRequestId and a valid CREDS_KEY; edits, resumes, files, quotes and other endpoints retain blocking checks. Original text is encrypted and unindexed, rather than discarded. No running deployment was tested. Sources: librechat:librechat:r4-content-filter, librechat:librechat:r4-pii-runtime, librechat:librechat:r4-patterns, librechat:librechat:r4-private-submission, librechat:librechat:r4-filter-middleware. - custom_patterns — Can admins add custom patterns or terms? [supported]: Operators can add labelled custom RE2JS regular expressions in base librechat.yaml, with optional categories. Database/role/group/user overrides cannot modify the policy; all replicas must load matching configuration. Invalid rules are rejected on configuration load. Sources: librechat:librechat:r4-content-filter, librechat:librechat:r4-patterns, librechat:librechat:r4-filter-middleware. - dlp_integration — Does it integrate with an existing DLP product? [unknown]: No first-party Purview/Netskope or other external DLP connector was established from the content-filter guide, current public repository tree and targeted official-site search. Configurable local patterns are not evidence of an external enterprise DLP integration. - filter_location — Where does filtering run? [supported]: Inspected content-filter middleware and rule evaluation run in the customer-operated LibreChat API backend. Optional extraction/OCR and inference providers remain separate data flows; no named deployment region or traffic path was tested. Sources: librechat:librechat:r4-pii-runtime, librechat:librechat:r4-filter-middleware. Checked 2026-10-26; agent cross-checked 2026-10-26; check again by 2026-12-25. Sources: librechat:librechat:r4-content-filter, librechat:librechat:r4-pii-runtime, librechat:librechat:r4-patterns, librechat:librechat:r4-private-submission, librechat:librechat:r4-filter-middleware, librechat:librechat:r4-config-1318 ### 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 #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: partial Operators can configure prompts and usage terms; abuse moderation is distinct from semantic content-policy enforcement. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified. Limitations: - org_instructions: Enforced model-spec presets and Agent instructions can guide behavior; model-followed instructions are not guaranteed policy enforcement. - content_filters: Automated moderation scores rate/authentication/message abuse and can ban users. Semantic topic or PII policy coverage was not established. - violation_reporting: Abuse scoring is documented, but a complete organization content-policy violation dashboard and reporting fixture were not established. - org_instructions — Can admins set organisation-wide instructions? [partial]: Enforced model-spec presets and Agent instructions can guide behavior; model-followed instructions are not guaranteed policy enforcement. Sources: librechat:librechat:modelspec, librechat:librechat:agents. - usage_notice — Can users be required to accept a usage policy? [supported]: Interface configuration includes custom terms of service and acceptance settings. Sources: librechat:librechat:interface. - content_filters — Are content filters configurable? [partial]: Automated moderation scores rate/authentication/message abuse and can ban users. Semantic topic or PII policy coverage was not established. Sources: librechat:librechat:mod. - violation_reporting — Are policy hits visible to admins? [partial]: Abuse scoring is documented, but a complete organization content-policy violation dashboard and reporting fixture were not established. Sources: librechat:librechat:mod. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:modelspec, librechat:librechat:agents, librechat:librechat:interface, librechat:librechat:mod ## 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 #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: partial Customer operators choose storage and service locations; external model, OCR, search and code services need separate residency decisions. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified. Limitations: - backups_logs_region: Logs and mounted data reside in the configured deployment; backup, telemetry and optional tracing geographies depend on operator choices and were not audited. - support_access_region: From where can vendor staff access data? No vendor or integrator support-access country restriction was reviewed for this customer-operated deployment. - swiss_hosting: A customer may run the software on Swiss infrastructure; no bundled Swiss managed inference/support commitment was established. - storage_region — Where are chats, files and indexes stored? [supported]: The reference self-hosted stack keeps application data in configured MongoDB/files and retrieval data in PGVector. Its country is chosen by the deployer. Sources: librechat:librechat:compose-pin, librechat:librechat:remote. - inference_region — Where do model calls run, per provider? [supported]: Customer-selected cloud endpoints/regions or local endpoints determine inference; hosting LibreChat in Switzerland does not place every external model there. Sources: librechat:librechat:custom, librechat:librechat:bedrock, librechat:librechat:vertex. - backups_logs_region — Where are backups, logs and telemetry? [partial]: Logs and mounted data reside in the configured deployment; backup, telemetry and optional tracing geographies depend on operator choices and were not audited. Sources: librechat:librechat:logging, librechat:librechat:compose-pin. - support_access_region — From where can vendor staff access data? [unknown]: support_access_region: From where can vendor staff access data? No vendor or integrator support-access country restriction was reviewed for this customer-operated deployment. - swiss_hosting — Is Swiss hosting available? [partial]: A customer may run the software on Swiss infrastructure; no bundled Swiss managed inference/support commitment was established. Sources: librechat:librechat:remote, librechat:librechat:license. - residency_plan — Which plan or option provides residency? [supported]: Customer-controlled placement is a self-hosted deployment property, not a separately priced residency licence. Sources: librechat:librechat:remote, librechat:librechat:license. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:compose-pin, librechat:librechat:remote, librechat:librechat:custom, librechat:librechat:bedrock, librechat:librechat:vertex, librechat:librechat:logging, librechat:librechat:license ### 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 #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: partial The project documents local and customer-cloud installs. A free public demo is separate from a production managed service. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server, LibreChat public evaluation demo; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified. Limitations: - multi_tenant_saas: The project operates a free public evaluation Demo, not a reviewed production business SaaS offer. Its terms permit data cleanups and disclaim persistence. - dedicated_instance: Is a dedicated single-tenant instance offered, from what size? A vendor-operated dedicated production service and its contractual size floor were not established. - air_gapped: Local chat/embedding routes exist, but a complete disconnected installation and its full dependency behavior were not verified. - mode_feature_gaps: External APIs, OCR/search services and separate code runtimes need their own availability/networking; there is no verified SaaS/on-prem feature-parity matrix. - multi_tenant_saas — Is a shared SaaS offered? [partial]: The project operates a free public evaluation Demo, not a reviewed production business SaaS offer. Its terms permit data cleanups and disclaim persistence. Sources: librechat:librechat:demo, librechat:librechat:firstchat. - dedicated_instance — Is a dedicated single-tenant instance offered, from what size? [unknown]: dedicated_instance: Is a dedicated single-tenant instance offered, from what size? A vendor-operated dedicated production service and its contractual size floor were not established. - customer_cloud — Can it run in the customer's own cloud account, from what size? [supported]: Remote hosting documentation describes customer-selected servers/cloud hosting without a software seat minimum. Sources: librechat:librechat:remote, librechat:librechat:license. - on_premise — Can the whole platform run on customer infrastructure, from what size? [supported]: Docker/npm installation can run the application and dependencies on customer infrastructure. Sources: librechat:librechat:local, librechat:librechat:compose-pin. - air_gapped — Can it run without internet access? [partial]: Local chat/embedding routes exist, but a complete disconnected installation and its full dependency behavior were not verified. Sources: librechat:librechat:custom, librechat:librechat:ragcfg. - mode_feature_gaps — Which features are missing outside SaaS? [partial]: External APIs, OCR/search services and separate code runtimes need their own availability/networking; there is no verified SaaS/on-prem feature-parity matrix. Sources: librechat:librechat:ocr, librechat:librechat:web, librechat:librechat:code. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:demo, librechat:librechat:firstchat, librechat:librechat:remote, librechat:librechat:license, librechat:librechat:local, librechat:librechat:compose-pin, librechat:librechat:custom, librechat:librechat:ragcfg, librechat:librechat:ocr, librechat:librechat:web, librechat:librechat:code ### 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 #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: partial The customer configures model contracts and data paths; a universal no-training or provider-retention promise was not established. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified. Limitations: - vendor_training: The self-hosted application stores data in the customer’s configured stack; this architecture is not a contractual promise covering every optional external service. - provider_training: Do model providers train on it under this product's contracts? No specific customer provider agreement, abuse retention/human-review period or zero-retention entitlement was reviewed. Website and Demo privacy policies do not govern arbitrary self-hosted providers. - provider_retention: How long do model providers keep prompts, including for abuse monitoring? No specific customer provider agreement, abuse retention/human-review period or zero-retention entitlement was reviewed. Website and Demo privacy policies do not govern arbitrary self-hosted providers. - zero_retention: Is zero data retention available, and on which plan? No specific customer provider agreement, abuse retention/human-review period or zero-retention entitlement was reviewed. Website and Demo privacy policies do not govern arbitrary self-hosted providers. - human_review: Can provider staff review content? No specific customer provider agreement, abuse retention/human-review period or zero-retention entitlement was reviewed. Website and Demo privacy policies do not govern arbitrary self-hosted providers. - vendor_training — Does the vendor train on customer content? [partial]: The self-hosted application stores data in the customer’s configured stack; this architecture is not a contractual promise covering every optional external service. Sources: librechat:librechat:compose-pin, librechat:librechat:firstchat. - provider_training — Do model providers train on it under this product's contracts? [unknown]: provider_training: Do model providers train on it under this product's contracts? No specific customer provider agreement, abuse retention/human-review period or zero-retention entitlement was reviewed. Website and Demo privacy policies do not govern arbitrary self-hosted providers. - provider_retention — How long do model providers keep prompts, including for abuse monitoring? [unknown]: provider_retention: How long do model providers keep prompts, including for abuse monitoring? No specific customer provider agreement, abuse retention/human-review period or zero-retention entitlement was reviewed. Website and Demo privacy policies do not govern arbitrary self-hosted providers. - zero_retention — Is zero data retention available, and on which plan? [unknown]: zero_retention: Is zero data retention available, and on which plan? No specific customer provider agreement, abuse retention/human-review period or zero-retention entitlement was reviewed. Website and Demo privacy policies do not govern arbitrary self-hosted providers. - human_review — Can provider staff review content? [unknown]: human_review: Can provider staff review content? No specific customer provider agreement, abuse retention/human-review period or zero-retention entitlement was reviewed. Website and Demo privacy policies do not govern arbitrary self-hosted providers. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:compose-pin, librechat:librechat:firstchat ### 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 #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: partial Normal chats have no default expiry; temporary chats default to 30 days and admins can configure broader expiry modes. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified. Limitations: - user_deletion: Users can delete conversations/data and retention sweeps remove files. Copies, backups and external provider deletion were not end-to-end verified. - contract_end_deletion: What is deleted at contract end, and when? No commercial contract-end purge/confirmation deadline was reviewed; the Demo’s retention terms are a separate offer. - default_retention — What is retained and for how long by default? [supported]: The default temporary retention is 720 hours; normal chats persist unless configured under all/ephemeral modes. Memories do not expire with chats. Sources: librechat:librechat:retention. - admin_retention — Can admins set retention periods? [supported]: Admins set all or ephemeral retention, regular/temporary deadlines and Agent file retention. New settings apply on later saves rather than rewriting every existing record immediately. Sources: librechat:librechat:retention. - user_deletion — Can users delete their chats and files permanently? [partial]: Users can delete conversations/data and retention sweeps remove files. Copies, backups and external provider deletion were not end-to-end verified. Sources: librechat:librechat:retention, librechat:librechat:settings. - contract_end_deletion — What is deleted at contract end, and when? [unknown]: contract_end_deletion: What is deleted at contract end, and when? No commercial contract-end purge/confirmation deadline was reviewed; the Demo’s retention terms are a separate offer. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:retention, librechat:librechat:settings ### 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 #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: partial ClickHouse’s acquisition is sourced; the self-hosted deployment still selects its own external processors and contracts. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified. Limitations: - subprocessor_list: Is a dated sub-processor list published? No project-wide dated sub-processor/country list, change-notification schedule, transfer instrument or government-access policy was established for arbitrary customer-operated deployments. Website/Demo policies are separate scopes. - subprocessor_countries: Which countries do sub-processors operate in? No project-wide dated sub-processor/country list, change-notification schedule, transfer instrument or government-access policy was established for arbitrary customer-operated deployments. Website/Demo policies are separate scopes. - change_notification: Are customers notified of sub-processor changes? No project-wide dated sub-processor/country list, change-notification schedule, transfer instrument or government-access policy was established for arbitrary customer-operated deployments. Website/Demo policies are separate scopes. - parent_jurisdiction: ClickHouse, Inc. announced the LibreChat acquisition on 2025-11-04 from San Francisco and brought founder/team into ClickHouse. A self-hosted customer contracting entity/governing jurisdiction was not established from that announcement. - transfer_mechanism: Which transfer mechanism applies to non-EU/CH processing? No project-wide dated sub-processor/country list, change-notification schedule, transfer instrument or government-access policy was established for arbitrary customer-operated deployments. Website/Demo policies are separate scopes. - government_access_policy: Is there a published government-access or transparency policy? No project-wide dated sub-processor/country list, change-notification schedule, transfer instrument or government-access policy was established for arbitrary customer-operated deployments. Website/Demo policies are separate scopes. - subprocessor_list — Is a dated sub-processor list published? [unknown]: subprocessor_list: Is a dated sub-processor list published? No project-wide dated sub-processor/country list, change-notification schedule, transfer instrument or government-access policy was established for arbitrary customer-operated deployments. Website/Demo policies are separate scopes. - subprocessor_countries — Which countries do sub-processors operate in? [unknown]: subprocessor_countries: Which countries do sub-processors operate in? No project-wide dated sub-processor/country list, change-notification schedule, transfer instrument or government-access policy was established for arbitrary customer-operated deployments. Website/Demo policies are separate scopes. - change_notification — Are customers notified of sub-processor changes? [unknown]: change_notification: Are customers notified of sub-processor changes? No project-wide dated sub-processor/country list, change-notification schedule, transfer instrument or government-access policy was established for arbitrary customer-operated deployments. Website/Demo policies are separate scopes. - parent_jurisdiction — Which jurisdiction governs the vendor and its parent? [partial]: ClickHouse, Inc. announced the LibreChat acquisition on 2025-11-04 from San Francisco and brought founder/team into ClickHouse. A self-hosted customer contracting entity/governing jurisdiction was not established from that announcement. Sources: librechat:librechat:owner. - transfer_mechanism — Which transfer mechanism applies to non-EU/CH processing? [unknown]: transfer_mechanism: Which transfer mechanism applies to non-EU/CH processing? No project-wide dated sub-processor/country list, change-notification schedule, transfer instrument or government-access policy was established for arbitrary customer-operated deployments. Website/Demo policies are separate scopes. - government_access_policy — Is there a published government-access or transparency policy? [unknown]: government_access_policy: Is there a published government-access or transparency policy? No project-wide dated sub-processor/country list, change-notification schedule, transfer instrument or government-access policy was established for arbitrary customer-operated deployments. Website/Demo policies are separate scopes. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:owner ### 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 #### LibreChat 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. ### 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 #### LibreChat 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. ### 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 #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: partial Network and storage security depend on the customer’s deployment; application authentication does not certify encryption of all stored content. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified. Limitations: - encryption_at_rest: Is data encrypted at rest? No default at-rest encryption guarantee covering MongoDB/files/PGVector or audited multi-tenant managed-service isolation was established from the installation guides. - customer_managed_keys: Operators own infrastructure and application secrets; a documented product HYOK/customer-managed content-encryption service was not verified. - tenant_isolation: How are customers separated in shared SaaS? No default at-rest encryption guarantee covering MongoDB/files/PGVector or audited multi-tenant managed-service isolation was established from the installation guides. - encryption_at_rest — Is data encrypted at rest? [unknown]: encryption_at_rest: Is data encrypted at rest? No default at-rest encryption guarantee covering MongoDB/files/PGVector or audited multi-tenant managed-service isolation was established from the installation guides. - customer_managed_keys — Can the customer manage or hold the keys? [partial]: Operators own infrastructure and application secrets; a documented product HYOK/customer-managed content-encryption service was not verified. Sources: librechat:librechat:auth, librechat:librechat:compose-pin. - private_networking — Is private connectivity or IP restriction available? [supported]: Operators deploy the stack on their own network and configure reverse proxies/HTTPS for remote access. Sources: librechat:librechat:remote, librechat:librechat:local. - tenant_isolation — How are customers separated in shared SaaS? [unknown]: tenant_isolation: How are customers separated in shared SaaS? No default at-rest encryption guarantee covering MongoDB/files/PGVector or audited multi-tenant managed-service isolation was established from the installation guides. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:auth, librechat:librechat:compose-pin, librechat:librechat:remote, librechat:librechat:local ### 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 #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: partial Customer-operated message storage and configurable local/external inference establish part of the content-access boundary. A LibreChat-scoped staff/sub-processor secrecy undertaking or professional-secrecy offering remains unverified. Availability: unknown Delivery: unknown Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; message schema and reference Compose pinned to v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional commercial secrecy terms unverified. Public Demo and website policies checked only to distinguish their scope; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected application, storage and model-service locations; no DE/CH professional-secrecy contract variant verified; os=not specified. Limitations: - The secrecy undertaking, sub-processor coverage, offering and professional-secrecy-specific documentation remain unknown. - content_access: Operator permissions, vendor/support grants, optional service access and provider staff access were not tested or contractually verified. - Technical data controls, a DPA, privacy wording and no-training statements do not establish the requested contractual undertaking. No legal compliance assessment is made. - secrecy_undertaking — Does the vendor sign a secrecy undertaking or § 203 StGB / Art. 321 StGB agreement covering its own staff? [unknown]: No LibreChat-scoped § 203 StGB / Art. 321 StGB undertaking binding vendor staff was obtained from the reviewed project documentation and public legal pages. The website privacy policy expressly excludes the self-hosted application; ClickHouse ownership does not establish a product-specific agreement. Sources: librechat:librechat:siteprivacy, librechat:librechat:owner. - subprocessor_coverage — Does the undertaking extend to its sub-processors, and is that documented? [unknown]: No self-hosted LibreChat professional-secrecy annex or documented extension to sub-processors was obtained. The separate Demo policy describes processor instruction/security obligations, which do not establish the undertaking requested here or coverage of a customer deployment. Sources: librechat:librechat:secrecy-demo-policy. - secrecy_offering — Is it a dedicated offering or add-on, and on which plan? [unknown]: No dedicated professional-secrecy edition, paid add-on, eligible plan or price was established in the public project/legal materials and targeted searches. The public Demo is evaluation-only and excludes confidential or regulated data; it is a separate surface. Sources: librechat:librechat:demo. - content_access — Who can access content in plain text: vendor staff, sub-processors, model providers? [partial]: The pinned reference deployment mounts customer-controlled MongoDB, uploads and logs; the message schema declares ordinary text/content fields. This places host/database operators inside the application trust boundary (an architectural inference, not a permissions audit). The first-chat and endpoint guides route prompts to a selected local or external model with customer credentials. Vendor/support access, optional service operators and provider human access remain deployment- and contract-specific and unverified. Sources: librechat:librechat:compose-pin, librechat:librechat:secrecy-message-pin, librechat:librechat:firstchat, librechat:librechat:custom. - secrecy_documentation — Is the offering publicly documented (contract template, data-flow description, professional-body guidance)? [unknown]: Public installation, endpoint and privacy documents describe technical data paths and distinguish website, Demo and self-hosted software. No LibreChat-specific DE/CH secrecy contract template, covered-party annex or professional-body guidance was located in the reviewed sources. Sources: librechat:librechat:firstchat, librechat:librechat:siteprivacy. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:siteprivacy, librechat:librechat:owner, librechat:librechat:secrecy-demo-policy, librechat:librechat:demo, librechat:librechat:compose-pin, librechat:librechat:secrecy-message-pin, librechat:librechat:firstchat, librechat:librechat:custom ## 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 #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: partial MIT software has no licence subscription; hosting, inference and optional runtime services are separately procured. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified. Limitations: - add_ons: Optional external code/OCR/search/image services need separately configured endpoints and credentials. Their rates depend on the operator’s contracts. - overage: Provider APIs charge their account holder; internal credit balances are governance configuration rather than a single LibreChat usage tariff. - pricing_unit — What is the pricing unit? [supported]: The pinned MIT permission grant has no per-user fee; self-hosting and model accounts are customer responsibilities. Sources: librechat:librechat:license, librechat:librechat:firstchat. - list_prices — What are list prices per plan, with date and currency? [supported]: The repository’s MIT licence permits use without a software fee as retrieved 2026-10-21; there is no bundled inference subscription in this scope. Sources: librechat:librechat:license, librechat:librechat:firstchat. - included_usage — What usage is included? [supported]: LibreChat ships with no model API key and no included provider token balance. Sources: librechat:librechat:firstchat. - add_ons — Which features cost extra? [partial]: Optional external code/OCR/search/image services need separately configured endpoints and credentials. Their rates depend on the operator’s contracts. Sources: librechat:librechat:code, librechat:librechat:ocr, librechat:librechat:web, librechat:librechat:images. - overage — What do usage beyond limits and premium models cost? [partial]: Provider APIs charge their account holder; internal credit balances are governance configuration rather than a single LibreChat usage tariff. Sources: librechat:librechat:balance, librechat:librechat:tokens, librechat:librechat:firstchat. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:license, librechat:librechat:firstchat, librechat:librechat:code, librechat:librechat:ocr, librechat:librechat:web, librechat:librechat:images, librechat:librechat:balance, librechat:librechat:tokens ### 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 #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: partial ALM-14 shared cost assumptions v1.4, 2026-10-21: zero standard licence plus a disclosed Swiss infrastructure/operations and direct-BYO-model budget. Annual CHF/EUR figures are floors plus named unknown costs. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=Analyst-selected direct OpenAI API proxy, not a bundled model, Assumed operations staffing; optional commercial services excluded; deployment_mode=customer-cloud; region=Azure Switzerland North for the reference application infrastructure; standard OpenAI API inference has no Swiss/EU residency assumption; os=not specified. Limitations: - ALM-14 shared cost assumptions v1.4, 2026-10-21 are analyst inputs, not vendor sizing or an uptime promise. - The budget is a floor because named infrastructure and service costs are unpriced. - cost_200 — Year-one cost at 200 users? [partial]: ALM-14 shared cost assumptions v1.4, 2026-10-21. 200 users, 12 months excluding VAT: from CHF 34778.28 / EUR 37651.06 plus unpriced items. Includes zero standard-software licence, reference infrastructure EUR 4749.26, operations CHF 30000.00, and BYO model usage USD 475.20. This is an assumption-based budget floor, not a vendor quote or validated capacity plan. Sources: librechat:librechat:license, librechat:librechat:cost-vm, librechat:librechat:cost-pg, librechat:librechat:cost-fx, librechat:librechat:cost-model, librechat:librechat:cost-effort. - cost_1000 — Year-one cost at 1,000 users? [partial]: ALM-14 shared cost assumptions v1.4, 2026-10-21. 1,000 users, 12 months excluding VAT: from CHF 88600.40 / EUR 95919.02 plus unpriced items. Includes zero standard-software licence, reference infrastructure EUR 12605.23, operations CHF 75000.00, and BYO model usage USD 2376.00. This is an assumption-based budget floor, not a vendor quote or validated capacity plan. Sources: librechat:librechat:license, librechat:librechat:cost-vm, librechat:librechat:cost-pg, librechat:librechat:cost-fx, librechat:librechat:cost-model, librechat:librechat:cost-effort. - cost_5000 — Year-one cost at 5,000 users? [partial]: ALM-14 shared cost assumptions v1.4, 2026-10-21. 5,000 users, 12 months excluding VAT: from CHF 189541.24 / EUR 205197.83 plus unpriced items. Includes zero standard-software licence, reference infrastructure EUR 32214.49, operations CHF 150000.00, and BYO model usage USD 11880.00. This is an assumption-based budget floor, not a vendor quote or validated capacity plan. Sources: librechat:librechat:license, librechat:librechat:cost-vm, librechat:librechat:cost-pg, librechat:librechat:cost-fx, librechat:librechat:cost-model, librechat:librechat:cost-effort. - variable_share — Which part depends on usage? [partial]: Shared mix is 60% light at 100, 30% regular at 400 and 10% power at 1,500 messages/user/month, or 330 weighted messages. Each message is 3,000 input and 600 output tokens. Direct BYO proxy is gpt-6-luna, reasoning effort none, Standard short-context uncached rates USD 0.10/0.50 per million input/output tokens. It costs USD 2.376/user/year before optional tools, embedding, caching or regional processing. This proxy is an analyst assumption, not the product default. Sources: librechat:librechat:cost-model, librechat:librechat:cost-effort. - unknown_parts — Which costs could not be priced? [partial]: Unpriced additions are file/object storage beyond the assumed 500 GB PostgreSQL storage, VM OS/data disks, backup excess, egress/load balancers, Redis or additional database services, high availability, embeddings, OCR, search, audio/images, integration work and optional commercial services. MongoDB remains the primary store, so its infrastructure, file storage and other required dependencies are additional unpriced items; PostgreSQL is only the shared RAG/reference compute assumption. The shared VM/PG sizes have not been load-tested and do not replace each product’s documented runtime dependencies. Sources: librechat:librechat:cost-vm, librechat:librechat:cost-pg, librechat:librechat:license. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:license, librechat:librechat:cost-vm, librechat:librechat:cost-pg, librechat:librechat:cost-fx, librechat:librechat:cost-model, librechat:librechat:cost-effort ### 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 #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: supported Customers can self-install without licence payment; the public demo is an evaluation-only alternative. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server, LibreChat public evaluation demo; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified. - free_tier — Is there a free tier for business use? [supported]: MIT self-installation permits organizational use without a software licence fee. Sources: librechat:librechat:license. - self_serve_trial — Is a self-serve business trial available? [supported]: Self-installation has no trial clock or software card requirement; the free hosted Demo can be tried separately under its terms. Sources: librechat:librechat:local, librechat:librechat:demo. - trial_scope — Do trials include SSO, connectors and admin features? [supported]: Self-installed instances can configure SSO, Agents, file retrieval and administration with their own service accounts. It is not evidence that every experimental add-on is enabled by default. Sources: librechat:librechat:auth, librechat:librechat:agents, librechat:librechat:rag. - sales_gate — Does meaningful evaluation require sales contact? [supported]: The documented Docker install does not require sales approval; optional third-party services have separate account requirements. Sources: librechat:librechat:local, librechat:librechat:firstchat. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:license, librechat:librechat:local, librechat:librechat:demo, librechat:librechat:auth, librechat:librechat:agents, librechat:librechat:rag, librechat:librechat:firstchat ### 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 #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: partial The MIT licence has no seat or contract-term subscription; optional service contracts are outside that licence. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified. Limitations: - cancellation: An operator can stop running the application; this does not cancel its separately purchased cloud/model services or establish deletion of all copies. - local_invoicing: Can it be invoiced in CHF or EUR from a European entity? CHF/EUR commercial invoicing from a European entity was not established for optional project services. - transparency_class: Source licensing is transparent; a complete all-in hosted/support/inference tariff is not included in this self-hosted offer. - minimum_commitment — What seat or spend minimum applies? [supported]: The MIT permission grant has no user-count or spending minimum for software use. Sources: librechat:librechat:license. - contract_length — What contract lengths are offered? [supported]: There is no monthly/annual licence subscription in the MIT permission grant. External hosting/API contracts are separate. Sources: librechat:librechat:license. - cancellation — How can the contract be cancelled or reduced? [partial]: An operator can stop running the application; this does not cancel its separately purchased cloud/model services or establish deletion of all copies. Sources: librechat:librechat:license, librechat:librechat:local. - local_invoicing — Can it be invoiced in CHF or EUR from a European entity? [unknown]: local_invoicing: Can it be invoiced in CHF or EUR from a European entity? CHF/EUR commercial invoicing from a European entity was not established for optional project services. - transparency_class — Is pricing transparent, partial, quote-only or unknown? [partial]: Source licensing is transparent; a complete all-in hosted/support/inference tariff is not included in this self-hosted offer. Sources: librechat:librechat:license, librechat:librechat:firstchat. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:license, librechat:librechat:local, librechat:librechat:firstchat ### 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 #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: partial The pinned main repository is MIT licensed; no user-count or product-branding clause appears in that licence. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified. Limitations: - enterprise_features_closed: The project documents a separate preview admin panel and optional code services. A closed enterprise-edition boundary for the main repository was not established. - licence_type — Which licence applies to each component? [supported]: The main client/server repository at v0.8.8 is MIT. Separate Code Interpreter, admin-panel, connector or hosted-service components need their own licence review. Sources: librechat:librechat:license. - branding_restrictions — Do licence terms restrict branding or user counts? [supported]: The MIT grant permits use/modification/distribution subject to retaining its copyright and permission notice; it includes no 50-user cap or mandatory UI branding clause. Sources: librechat:librechat:license. - enterprise_features_closed — Are enterprise features in a separate closed edition? [partial]: The project documents a separate preview admin panel and optional code services. A closed enterprise-edition boundary for the main repository was not established. Sources: librechat:librechat:admin, librechat:librechat:code, librechat:librechat:license. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:license, librechat:librechat:admin, librechat:librechat:code ### 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 #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: partial Users can export conversations in machine-readable formats; organization-wide Agent/knowledge exit completeness remains unverified. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified. Limitations: - chat_export: Pinned client code exports a user-selected conversation, including optional branches/options. A documented admin bulk export of every user’s chats was not established. - assistant_export: Beta management APIs expose Agent/Skill objects, but a reusable complete assistant/prompt export fixture was not verified. - knowledge_export: Can knowledge bases and their sources be exported? No admin exit fixture, knowledge-source/index portability test or commercial post-termination retrieval window was verified; infrastructure backups are operator-owned. - post_termination_window: How long can data be retrieved after termination? No admin exit fixture, knowledge-source/index portability test or commercial post-termination retrieval window was verified; infrastructure backups are operator-owned. - chat_export — Can admins export all chats? [partial]: Pinned client code exports a user-selected conversation, including optional branches/options. A documented admin bulk export of every user’s chats was not established. Sources: librechat:librechat:export-pin. - assistant_export — Can assistants and prompts be exported in a reusable format? [partial]: Beta management APIs expose Agent/Skill objects, but a reusable complete assistant/prompt export fixture was not verified. Sources: librechat:librechat:api. - knowledge_export — Can knowledge bases and their sources be exported? [unknown]: knowledge_export: Can knowledge bases and their sources be exported? No admin exit fixture, knowledge-source/index portability test or commercial post-termination retrieval window was verified; infrastructure backups are operator-owned. - export_format — Are formats documented and machine-readable? [supported]: Conversation export code supports JSON, CSV, Markdown and text. This establishes format availability, not complete organization-data portability. Sources: librechat:librechat:export-pin. - post_termination_window — How long can data be retrieved after termination? [unknown]: post_termination_window: How long can data be retrieved after termination? No admin exit fixture, knowledge-source/index portability test or commercial post-termination retrieval window was verified; infrastructure backups are operator-owned. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:export-pin, librechat:librechat:api ### 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 #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: partial Public project/community channels are available; a binding business support SLA was not established. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified. Limitations: - support_channels: Public GitHub issue reporting and community channels are documented; a supported enterprise channel/response-time matrix was not established for MIT self-hosting. - support_languages: Is support available in German, French or Italian? No DE/FR/IT support coverage, CH/DACH legal/partner presence, priced uptime credits or product-service incident-history contract was verified in the public docs, site and release pass. - regional_presence: Is there a DACH or Swiss entity, team or partner? No DE/FR/IT support coverage, CH/DACH legal/partner presence, priced uptime credits or product-service incident-history contract was verified in the public docs, site and release pass. - uptime_sla: Is there an uptime SLA with credits? No DE/FR/IT support coverage, CH/DACH legal/partner presence, priced uptime credits or product-service incident-history contract was verified in the public docs, site and release pass. - status_page: Is there a public status page with history? No DE/FR/IT support coverage, CH/DACH legal/partner presence, priced uptime credits or product-service incident-history contract was verified in the public docs, site and release pass. - support_channels — Which support channels are available on each plan? [partial]: Public GitHub issue reporting and community channels are documented; a supported enterprise channel/response-time matrix was not established for MIT self-hosting. Sources: librechat:librechat:logging, librechat:librechat:firstchat. - support_languages — Is support available in German, French or Italian? [unknown]: support_languages: Is support available in German, French or Italian? No DE/FR/IT support coverage, CH/DACH legal/partner presence, priced uptime credits or product-service incident-history contract was verified in the public docs, site and release pass. - regional_presence — Is there a DACH or Swiss entity, team or partner? [unknown]: regional_presence: Is there a DACH or Swiss entity, team or partner? No DE/FR/IT support coverage, CH/DACH legal/partner presence, priced uptime credits or product-service incident-history contract was verified in the public docs, site and release pass. - uptime_sla — Is there an uptime SLA with credits? [unknown]: uptime_sla: Is there an uptime SLA with credits? No DE/FR/IT support coverage, CH/DACH legal/partner presence, priced uptime credits or product-service incident-history contract was verified in the public docs, site and release pass. - status_page — Is there a public status page with history? [unknown]: status_page: Is there a public status page with history? No DE/FR/IT support coverage, CH/DACH legal/partner presence, priced uptime credits or product-service incident-history contract was verified in the public docs, site and release pass. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:logging, librechat:librechat:firstchat ### 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 #### LibreChat Verification status: Agent cross-checked (agent-cross-checked) Support: partial Self-hosting and Agent use have public setup guides; vendor-led training/adoption packages were not verified. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified. Limitations: - onboarding_service: Is guided onboarding included? No included guided rollout, local-language end-user training, champion programme, change-management service or professional-service price list was established from the official documentation and site. - user_training: Is end-user training offered, in which languages? No included guided rollout, local-language end-user training, champion programme, change-management service or professional-service price list was established from the official documentation and site. - use_case_library: The Agent and setup guides include examples and tutorials; a role-based enterprise training/use-case program was not established. - adoption_programme: Is there a champion or adoption programme? No included guided rollout, local-language end-user training, champion programme, change-management service or professional-service price list was established from the official documentation and site. - service_cost: Which services cost extra? No included guided rollout, local-language end-user training, champion programme, change-management service or professional-service price list was established from the official documentation and site. - onboarding_service — Is guided onboarding included? [unknown]: onboarding_service: Is guided onboarding included? No included guided rollout, local-language end-user training, champion programme, change-management service or professional-service price list was established from the official documentation and site. - user_training — Is end-user training offered, in which languages? [unknown]: user_training: Is end-user training offered, in which languages? No included guided rollout, local-language end-user training, champion programme, change-management service or professional-service price list was established from the official documentation and site. - use_case_library — Are role-based use cases and templates provided? [partial]: The Agent and setup guides include examples and tutorials; a role-based enterprise training/use-case program was not established. Sources: librechat:librechat:agents, librechat:librechat:firstchat. - adoption_programme — Is there a champion or adoption programme? [unknown]: adoption_programme: Is there a champion or adoption programme? No included guided rollout, local-language end-user training, champion programme, change-management service or professional-service price list was established from the official documentation and site. - service_cost — Which services cost extra? [unknown]: service_cost: Which services cost extra? No included guided rollout, local-language end-user training, champion programme, change-management service or professional-service price list was established from the official documentation and site. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:agents, librechat:librechat:firstchat ## 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 ### librechat:librechat:custom Custom endpoints. Operators configure compatible endpoints and customer-held keys, including local and hosted services. - URL: https://www.librechat.ai/docs/quick_start/custom_endpoints - Locator: Endpoint setup; API key; base URL; model list - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### librechat:librechat:azure Azure OpenAI configuration. Azure OpenAI uses customer deployment groups, instance names and credentials. - URL: https://www.librechat.ai/docs/configuration/librechat_yaml/ai_endpoints/azure - Locator: Deployment groups; API credentials - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### librechat:librechat:bedrock AWS Bedrock object structure. Bedrock routes use customer AWS configuration and region selection. - URL: https://www.librechat.ai/docs/configuration/librechat_yaml/object_structure/aws_bedrock - Locator: Region; credentials; model selection - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### librechat:librechat:vertex Anthropic Vertex AI configuration. Claude can run through customer Google Vertex AI credentials and regions. - URL: https://www.librechat.ai/docs/configuration/librechat_yaml/object_structure/anthropic_vertex - Locator: Project and region configuration - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### librechat:librechat:modelspec Model specifications. Administrators can enforce configured model presets and defaults; available endpoints still depend on customer credentials. - URL: https://www.librechat.ai/docs/configuration/librechat_yaml/object_structure/model_specs - Locator: enforce; preset; modelSelect; addedEndpoints - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### librechat:librechat:agents Agents. Agents combine instructions, models, files, tools, skills and sharing permissions, with visible execution and configurable approval. - URL: https://www.librechat.ai/docs/features/agents - Locator: Builder; Capabilities; Version history; Sharing; Activity; tool approval - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### librechat:librechat:ocr OCR for documents. OCR can augment text extraction, or files can be sent to compatible provider APIs; format and model limitations remain. - URL: https://www.librechat.ai/docs/features/ocr - Locator: File Context; Upload as Text; Optional OCR; Limitations - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### librechat:librechat:releases LibreChat v0.8.8 release. The stable release documents agent controls, current model updates and explicitly experimental schedules/workspaces and beta Agents API. - URL: https://github.com/LibreChat-AI/LibreChat/releases/tag/v0.8.8 - Locator: Highlights, 2026-10-01 - Evidence kind: documented - Source date: 2026-10-01 - Retrieved: 2026-10-21 ### 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 ### librechat:librechat:firstchat Your first chat. LibreChat ships without a model key; the public demo is for evaluation rather than private or durable data. - URL: https://www.librechat.ai/docs/quick_start/first_chat - Locator: Software you host yourself; endpoint credentials; public demo - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### librechat:librechat:code Code Interpreter API. A separate code execution service supports multiple languages and downloadable generated files; stateful/attached modes are experimental. - URL: https://www.librechat.ai/docs/features/code_interpreter - Locator: Setup; self-hosted service; workspace permissions; generated files - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### librechat:librechat:license LibreChat v0.8.8 MIT licence. The pinned repository is MIT licensed with copyright/permission notice preservation and an as-is disclaimer. - URL: https://raw.githubusercontent.com/LibreChat-AI/LibreChat/e8f3be08623663d4ad7f7241e693c94469b63bb0/LICENSE - Locator: LICENSE, permission grant and notice requirement - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### librechat:librechat:ragcfg RAG API configuration. OpenAI, Hugging Face and Ollama embedding configurations are documented; image choice affects local embedding support. - URL: https://www.librechat.ai/docs/configuration/rag_api - Locator: Embedding providers; lite image; full image - Evidence kind: documented - 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 ### librechat:librechat:access Granular access control. Roles, groups and resource ACLs govern features and sharing, with Entra groups synchronized at sign-in. - URL: https://www.librechat.ai/docs/features/access_control - Locator: Feature permissions; Resource ACLs; System grants; Groups - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### librechat:librechat:admin LibreChat Admin Panel. A separate browser management panel is available for testing and uses the underlying LibreChat admin APIs. - URL: https://www.librechat.ai/docs/features/admin_panel - Locator: Status Preview; separate service; admin APIs - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### librechat:librechat:balance Balance configuration. Optional token-credit balances initialize and refill user credits; tracking is disabled by default. - URL: https://www.librechat.ai/docs/configuration/librechat_yaml/object_structure/balance - Locator: enabled; startBalance; refill configuration - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### librechat:librechat:mod Automated moderation. Moderation scores abusive login/registration/message activity and may ban users; it is not a documented content DLP classifier. - URL: https://www.librechat.ai/docs/features/mod_system - Locator: Violation scoring and limits - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### librechat:librechat:balance-pin LibreChat balance admission implementation. The pinned middleware reserves user credits and throws a TOKEN_BALANCE error when the reservation cannot be admitted. - URL: https://raw.githubusercontent.com/LibreChat-AI/LibreChat/e8f3be08623663d4ad7f7241e693c94469b63bb0/packages/api/src/middleware/checkBalance.ts - Locator: packages/api/src/middleware/checkBalance.ts, checkBalance - Evidence kind: source-inspected - Source date: Not stated - Retrieved: 2026-10-21 - Commit: e8f3be08623663d4ad7f7241e693c94469b63bb0 - Path: packages/api/src/middleware/checkBalance.ts ### 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 ### librechat:librechat:rag RAG API. A separate RAG API indexes uploaded content in PostgreSQL/PGVector for retrieval. - URL: https://www.librechat.ai/docs/features/rag_api - Locator: Architecture; document indexing; embeddings; semantic search - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### librechat:librechat:text Upload files as text. Text upload injects extracted file content rather than relying only on vector retrieval. - URL: https://www.librechat.ai/docs/features/upload_as_text - Locator: Full text extraction and context - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### librechat:librechat:filecfg File configuration. File limits and formats are configurable by endpoint and file processing route. - URL: https://www.librechat.ai/docs/configuration/librechat_yaml/object_structure/file_config - Locator: File limits; MIME patterns; provider routes - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### librechat:librechat:r4-spreadsheet-parser LibreChat spreadsheet text parser. The built-in parser accepts XLSX/XLS/ODS and serializes each sheet as its name followed by CSV values. It does not establish preserved workbook layout, recalculated formulas or fixture accuracy. - URL: https://github.com/LibreChat-AI/LibreChat/blob/a378657583567310c841d652b0f6b00c83e2bd6b/packages/api/src/files/documents/crud.ts - Locator: getParserForMimeType; excelSheetToText, lines 109-129 - Evidence kind: source-inspected - Source date: 2026-10-24 - Retrieved: 2026-10-26 - Commit: a378657583567310c841d652b0f6b00c83e2bd6b - Path: packages/api/src/files/documents/crud.ts ### librechat:librechat:r4-text-current LibreChat current Upload as Text guide. The development guide lists XLSX/XLS/ODS parsing up to 15 MB and token-bounded text injection, not a formatted spreadsheet editor. - URL: https://www.librechat.ai/docs/features/upload_as_text - Locator: Built-in parser; supported documents; truncation - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-26 ### 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 ### librechat:librechat:projects Projects. Projects persist files and instructions across a user’s chats but cannot be shared or transferred. - URL: https://www.librechat.ai/docs/features/projects - Locator: Availability; personal scope; files and instructions - 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 ### librechat:librechat:sharepoint SharePoint and OneDrive integration. The Microsoft file picker uses Entra token reuse and delegated on-behalf-of downloads to attach files. - URL: https://www.librechat.ai/docs/configuration/sharepoint - Locator: Prerequisites; delegated permissions; admin consent - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### librechat:librechat:mcp MCP. MCP servers can be configured through YAML or the permission-gated UI, including per-user OAuth. - URL: https://www.librechat.ai/docs/features/mcp - Locator: YAML/UI setup; authentication; ownership and selection - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### librechat:librechat:mcpcfg MCP server configuration. Configuration includes stdio, SSE and Streamable HTTP transports and server-specific credentials. - URL: https://www.librechat.ai/docs/configuration/librechat_yaml/object_structure/mcp_servers - Locator: Transport examples; headers; OAuth - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### 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 ### 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 ### librechat:librechat:compose-pin LibreChat Docker service configuration. The pinned example runs a MongoDB primary store and a separate PGVector/RAG service with customer-mounted data. - URL: https://raw.githubusercontent.com/LibreChat-AI/LibreChat/e8f3be08623663d4ad7f7241e693c94469b63bb0/docker-compose.yml - Locator: docker-compose.yml, api/mongodb/vectordb/rag_api services - Evidence kind: source-inspected - Source date: Not stated - Retrieved: 2026-10-21 - Commit: e8f3be08623663d4ad7f7241e693c94469b63bb0 - Path: docker-compose.yml ### 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 ### librechat:librechat:memory User memory. Configured user memory stores cross-chat key/value context with user editing controls; it does not index all past chats. - URL: https://www.librechat.ai/docs/features/memory - Locator: Key/value store; controls; disabled by default - 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 ### 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 ### librechat:librechat:images Image generation and editing. Agents can use configured image tools for generation/editing; provider credentials and model parameters are separate. - URL: https://www.librechat.ai/docs/features/image_gen - Locator: OpenAI Image Tools; provider setup; admin configuration - 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 ### librechat:librechat:web Web search. Search can use Serper, SearXNG, Tavily or Keenable, with independently configured scraping and optional reranking. - URL: https://www.librechat.ai/docs/features/web_search - Locator: Provider, scraper and reranker configuration - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### librechat:librechat:schedule Scheduled Chats. Opt-in experimental schedules execute saved Agents with cron/time zones and recheck access and balance before running. - URL: https://www.librechat.ai/docs/features/scheduled_chats - Locator: Experimental and disabled by default; runtime and permissions - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### librechat:librechat:api Agents API beta. The beta API exposes chat/Responses inference, Agent/Skill management and authenticated event delivery. - URL: https://www.librechat.ai/docs/features/agents_api - Locator: Inference; management; Agent Events; authentication - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### 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 ### 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 ### librechat:librechat:retention Temporary chat and data retention. Operators configure expiry for chats/messages/files/shared links; normal chats do not expire by default and memories are excluded. - URL: https://www.librechat.ai/docs/features/temporary_chat - Locator: Default 30-day temporary retention; all/ephemeral; deadlines; memories - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### librechat:librechat:insights Admin Insights. Insights reports persisted MongoDB activity and identifiable recent conversations; it is not monetary billing analytics. - URL: https://www.librechat.ai/docs/features/insights - Locator: Opt-in; capabilities; metrics; tenant scope - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### librechat:librechat:local Docker installation. Docker self-installation runs LibreChat with its configured service dependencies. - URL: https://www.librechat.ai/docs/local/docker - Locator: Installation; configuration; updating - 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 ### 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 ### 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 ### librechat:librechat:speech Speech configuration. Administrators configure audio provider engines and models separately from text generation. - URL: https://www.librechat.ai/docs/configuration/librechat_yaml/object_structure/speech - Locator: Speech-to-text and text-to-speech engines - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### librechat:librechat:speech-conversation-r2 LibreChat conversation-mode speech settings. Conversation mode chains transcription, auto-send and TTS playback for hands-free turns after microphone activation; engines and audio routing are separately configured. - URL: https://www.librechat.ai/docs/configuration/stt_tts - Locator: Speech Tab: conversationMode, autoTranscribeAudio, autoSendText, automaticPlayback; engine and allowedAddresses settings - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### 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 ### librechat:librechat:artifacts Artifacts. Artifacts render generated React, HTML and Mermaid content in the chat interface. - URL: https://www.librechat.ai/docs/features/artifacts - Locator: React, HTML and Mermaid previews - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### librechat:librechat:share Shareable links. Shared links publish a transcript branch and optional file snapshots independently of the owner’s live file ACL. - URL: https://www.librechat.ai/docs/features/shareable_links - Locator: Authentication defaults; file snapshots; continuation - 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 ### librechat:librechat:i18n-pin LibreChat locale registration. The pinned client registers English, German, French and Italian translations among its supported locales. - URL: https://raw.githubusercontent.com/LibreChat-AI/LibreChat/e8f3be08623663d4ad7f7241e693c94469b63bb0/client/src/locales/i18n.ts - Locator: client/src/locales/i18n.ts, language resources - Evidence kind: source-inspected - Source date: Not stated - Retrieved: 2026-10-21 - Commit: e8f3be08623663d4ad7f7241e693c94469b63bb0 - Path: client/src/locales/i18n.ts ### 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 ### librechat:librechat:auth Authentication system. Local/LDAP accounts can be required to use TOTP; federated MFA belongs to the identity provider and account creation/deletion scripts are documented. - URL: https://www.librechat.ai/docs/configuration/authentication - Locator: Required two-factor authentication; Registration; User scripts - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### librechat:librechat:openid OAuth2 and OIDC. LibreChat documents OAuth2/OIDC providers including Microsoft Entra, Google, Keycloak and Auth0. - URL: https://www.librechat.ai/docs/configuration/authentication/OAuth2-OIDC - Locator: Supported providers; setup - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### librechat:librechat:saml SAML authentication. SAML is a documented authentication option for the self-hosted application. - URL: https://www.librechat.ai/docs/configuration/authentication/SAML - Locator: Overview and requirements - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### librechat:librechat:entra Azure Entra authentication. Entra OIDC supports group-based admission and Graph integration using configured scopes and token reuse. - URL: https://www.librechat.ai/docs/configuration/authentication/OAuth2-OIDC/azure - Locator: Group claims; token reuse; Microsoft Graph integration - 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 ### 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 ### librechat:librechat:tokens Token usage. Usage and estimated costs use recorded tokens and configured provider rates; transactions are distinct from balance enforcement. - URL: https://www.librechat.ai/docs/configuration/token_usage - Locator: Context cost; transactions; per-endpoint token rates - 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 ### librechat:librechat:logging Logging. Backend operational logs are written to customer files and can feed external tools; the guide describes 14-day rotation rather than a compliance archive. - URL: https://www.librechat.ai/docs/configuration/logging - Locator: Error/debug logs; rotation; external tools - 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 ### librechat:librechat:r4-content-filter LibreChat development content-filter configuration. Opt-in base-YAML policies inspect selected message/file content; block and audit differ from limited Agent text redaction. This is development documentation, not a hosted DLP assurance. - URL: https://www.librechat.ai/docs/configuration/librechat_yaml/object_structure/message_filter - Locator: Source-Aware Filters; Pattern Configuration; Redaction; File Fields - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-26 ### librechat:librechat:r4-pii-runtime LibreChat content-inspection runtime. Source-aware configured inspection executes in the LibreChat API. Missing policy disables that scope; configured actions and fields bound inspection. - URL: https://github.com/LibreChat-AI/LibreChat/blob/a378657583567310c841d652b0f6b00c83e2bd6b/packages/api/src/protection/runtime.ts - Locator: createConfiguredContentInspector; source rule configuration - Evidence kind: source-inspected - Source date: 2026-10-24 - Retrieved: 2026-10-26 - Commit: a378657583567310c841d652b0f6b00c83e2bd6b - Path: packages/api/src/protection/runtime.ts ### librechat:librechat:r4-patterns LibreChat pattern detector. Default starter patterns detect credential-shaped tokens/headers. Operator custom patterns use bounded regular expressions; a generic comprehensive PII classifier is not established. - URL: https://github.com/LibreChat-AI/LibreChat/blob/a378657583567310c841d652b0f6b00c83e2bd6b/packages/api/src/protection/detectors/pattern.ts - Locator: STARTER_PATTERNS; configured RE2JS rules - Evidence kind: source-inspected - Source date: 2026-10-24 - Retrieved: 2026-10-26 - Commit: a378657583567310c841d652b0f6b00c83e2bd6b - Path: packages/api/src/protection/detectors/pattern.ts ### librechat:librechat:r4-private-submission LibreChat private text submission. The private text ingress permits configured redaction only on eligible fresh interactive Agent text. Original content is encrypted; edit/resume/file paths do not gain blanket redaction. - URL: https://github.com/LibreChat-AI/LibreChat/blob/a378657583567310c841d652b0f6b00c83e2bd6b/packages/api/src/protection/private/submission.ts - Locator: createPrivateTextIngress; fresh Agent text and clientRequestId checks - Evidence kind: source-inspected - Source date: 2026-10-24 - Retrieved: 2026-10-26 - Commit: a378657583567310c841d652b0f6b00c83e2bd6b - Path: packages/api/src/protection/private/submission.ts ### librechat:librechat:r4-filter-middleware LibreChat API content-filter middleware. The server middleware applies configured inspection and rejects blocked/uninspectable requests with HTTP 400. No deployment or detection fixture was run. - URL: https://github.com/LibreChat-AI/LibreChat/blob/a378657583567310c841d652b0f6b00c83e2bd6b/packages/api/src/middleware/messageFilterPii.ts - Locator: createMessageFilterPii; contentFilterBlockResponse; uninspectable response - Evidence kind: source-inspected - Source date: 2026-10-24 - Retrieved: 2026-10-26 - Commit: a378657583567310c841d652b0f6b00c83e2bd6b - Path: packages/api/src/middleware/messageFilterPii.ts ### librechat:librechat:r4-config-1318 LibreChat config v1.3.18 changelog. Dated development config changes add limited Agent text redaction and ephemeral retention mode. These are not a promise of universal redaction or a vendor zero-retention contract. - URL: https://www.librechat.ai/changelog/config_v1.3.18 - Locator: October 22, 2026; opt-in PII redaction; retention mode - Evidence kind: documented - Source date: 2026-10-22 - Retrieved: 2026-10-26 ### librechat:librechat:interface Interface configuration. Administrators configure UI feature permissions and usage terms in the self-hosted deployment. - URL: https://www.librechat.ai/docs/configuration/librechat_yaml/object_structure/interface - Locator: Feature permissions; custom welcome and terms - 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 ### librechat:librechat:remote Remote hosting. The application can be deployed on customer-selected remote servers with operator-managed security. - URL: https://www.librechat.ai/docs/remote - Locator: Hosting options; security considerations - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### librechat:librechat:demo LibreChat Demo terms. The free hosted Demo is offered as-is with possible data cleanups and no durable business-service guarantee. - URL: https://www.librechat.ai/demo/terms - Locator: Evaluation scope; retention; disclaimer - Evidence kind: documented - Source date: 2026-03-12 - 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 ### 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 ### librechat:librechat:settings Personal settings. Users configure interface language, audio and personal data controls. - URL: https://www.librechat.ai/docs/features/settings - Locator: Language; speech; data controls - 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 ### librechat:librechat:owner ClickHouse acquisition of LibreChat. ClickHouse announced the acquisition of LibreChat and that Danny Avila and the team joined ClickHouse. - URL: https://clickhouse.com/blog/clickhouse-acquires-librechat - Locator: Announcement, November 4, 2025 - Evidence kind: documented - Source date: 2025-11-04 - 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 ### 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 ### librechat:librechat:siteprivacy LibreChat website privacy policy. Website, demo and self-hosted software are distinct privacy scopes; website terms do not establish a customer deployment DPA. - URL: https://www.librechat.ai/privacy - Locator: Scope and exclusions - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### librechat:librechat:secrecy-message-pin LibreChat v0.8.8 message storage schema. The pinned Mongoose schema declares message text as a String and content as mixed fields; this source does not establish operator exclusion from live content. - URL: https://raw.githubusercontent.com/LibreChat-AI/LibreChat/e8f3be08623663d4ad7f7241e693c94469b63bb0/packages/data-schemas/src/schema/message.ts - Locator: packages/data-schemas/src/schema/message.ts, text at lines 55-58 and content at lines 139-143 - Evidence kind: source-inspected - Source date: Not stated - Retrieved: 2026-10-21 - Commit: e8f3be08623663d4ad7f7241e693c94469b63bb0 - Path: packages/data-schemas/src/schema/message.ts ### librechat:librechat:secrecy-demo-policy LibreChat Demo privacy policy. The Demo policy describes model-provider transmission and contractual processor instruction/security duties for the Demo; it does not cover a customer self-hosted deployment. - URL: https://www.librechat.ai/demo/privacy - Locator: Scope; section 4 Third-Party AI Model Providers; section 6 Data Sharing and Sub-Processors - Evidence kind: documented - Source date: 2026-03-12 - 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 ### librechat:librechat:cost-vm Azure Retail Prices, Switzerland North Linux VMs. EUR hourly PAYG rates retrieved 2026-10-21 are 0.2226, 0.4453 and 0.8905 for D4s, D8s and D16s v5 respectively. - URL: https://prices.azure.com/api/retail/prices?currencyCode=EUR&%24filter=armRegionName+eq+%27switzerlandnorth%27+and+serviceName+eq+%27Virtual+Machines%27+and+%28armSkuName+eq+%27Standard_D4s_v5%27+or+armSkuName+eq+%27Standard_D8s_v5%27+or+armSkuName+eq+%27Standard_D16s_v5%27%29+and+priceType+eq+%27Consumption%27 - Locator: Consumption; Virtual Machines Dsv5 Series; Standard_D4s_v5/D8s_v5/D16s_v5 - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### librechat:librechat:cost-pg Azure Retail Prices, PostgreSQL Flexible Server. EUR hourly PAYG GP compute is 0.2288, 0.4576 and 0.9152 for 2/4/8 vCore; storage is EUR 0.1325 per GB-month. - URL: https://prices.azure.com/api/retail/prices?currencyCode=EUR&%24filter=armRegionName+eq+%27switzerlandnorth%27+and+serviceName+eq+%27Azure+Database+for+PostgreSQL%27+and+priceType+eq+%27Consumption%27 - Locator: General Purpose Ddsv5 Series Compute, 2/4/8 vCore; Flex Server Storage - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### librechat:librechat:cost-fx ECB euro reference rate history. The 2026-10-20 reference rates are EUR 1 = USD 1.1215 and 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 ### librechat:librechat:cost-model OpenAI API pricing. Standard gpt-6-luna API price is USD 0.10 per million input tokens and USD 0.50 per million output tokens; caching, batch and regional premiums are separate. - URL: https://developers.openai.com/api/docs/pricing - Locator: Standard, short-context gpt-6-luna row - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### librechat:librechat:cost-effort GPT-6 Luna model documentation. The model accepts reasoning effort none, the lowest documented effort, and lists the same standard text-token rates. - URL: https://developers.openai.com/api/docs/models/gpt-6-luna - Locator: Reasoning effort and text-token pricing - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### librechat:librechat:export-pin LibreChat conversation export implementation. The pinned user conversation exporter supports JSON, CSV, Markdown and text, plus screenshot export. - URL: https://raw.githubusercontent.com/LibreChat-AI/LibreChat/e8f3be08623663d4ad7f7241e693c94469b63bb0/client/src/hooks/Conversations/useExportConversation.ts - Locator: client/src/hooks/Conversations/useExportConversation.ts, export dispatch - Evidence kind: source-inspected - Source date: Not stated - Retrieved: 2026-10-21 - Commit: e8f3be08623663d4ad7f7241e693c94469b63bb0 - Path: client/src/hooks/Conversations/useExportConversation.ts ### 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 ### 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