--- schema_version: 1 rubric_version: "1.1" kind: pair canonical_url: "https://onaihq.com/compare/agents/glean-vs-open-webui/" data_url: "https://onaihq.com/compare/agents/glean-vs-open-webui/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" --- # Glean vs Open WebUI > 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. This comparison has 46 criteria with sourced findings for both products, including 46 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. - Glean source checks: 2026-10-21 to 2026-10-26. - Open WebUI source checks: 2026-10-21 to 2026-10-26. - Canonical HTML: https://onaihq.com/compare/agents/glean-vs-open-webui/ - Machine-readable JSON: https://onaihq.com/compare/agents/glean-vs-open-webui/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. #### Glean Verification status: Agent cross-checked (agent-cross-checked) Support: partial Model Hub documents multi-provider choice and Auto routing. New department Auto policies require opt-in rollout as of October 21, with GA scheduled October 29. Availability: unknown Delivery: native Scope: surfaces=Glean Hosted web Assistant and Agents; version=As of 2026-10-21: established model catalog plus opt-in new Auto-policy rollout; no tenant observed; plan=Core Suite + Model Hub Usage with Universal Model Key or Customer Key; new department policies only on Glean-key deployments with rollout enabled. Enterprise Flex billing is separate.; add_ons=none stated; deployment_mode=dedicated-instance; region=Selected hosting and model-provider regions; no blanket EU or Swiss processing claim; os=not specified. Limitations: - This criterion combines established model choice with an opt-in policy rollout; no blanket current GA status is asserted for the new policies. Enabled tenant models and per-request routing were not observed. - providers — Which model providers are available? [supported]: Model Hub lists OpenAI, Anthropic, Google, Amazon, Glean and open models through Baseten/Fireworks. Availability is conditional on enabled model and route. Sources: glean:glean:models, glean:glean:r2-core-entitlements. - current_models — Which current models are selectable on this plan? [partial]: Representative listed models include GPT-6.1 Sol, GPT-6 Astra/Sol/Luna, Claude Sonnet 5.5, Opus 5.5, Gemini 3.8 Flash, Waldo and GLM 5.3. Actual tenant-enabled selections were not observed. Sources: glean:glean:models, glean:glean:r2-core-entitlements. - user_choice — Can users pick the model per chat? [supported]: With Glean Universal Model Key users can select a specific enabled model or Auto. Customer Key uses configured defaults and has separate availability constraints. Sources: glean:glean:models, glean:glean:key-matrix, glean:glean:r2-core-entitlements. - auto_routing — Does the product route between models automatically, and is the chosen model shown? [partial]: Universal Model Key Auto routes among enabled models. The new department policies require Feature rollouts opt-in from October 15 as of this October 21 check; GA is scheduled October 29. Customer Key Auto uses admin defaults. Per-request selected-model visibility was not established. Sources: glean:glean:models, glean:glean:key-matrix, glean:glean:r2-core-entitlements, glean:glean:r3-october-rollout-migration. - multimodal_input — Which models accept images, audio or files? [partial]: Uploads, image generation and real-time voice are documented; supported input types vary by model and the key-feature matrix. A complete per-model input matrix was not verified. Sources: glean:glean:uploads, glean:glean:key-matrix, glean:glean:r2-core-entitlements. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: glean:glean:models, glean:glean:r2-core-entitlements, glean:glean:key-matrix, glean:glean:r3-october-rollout-migration, glean:glean:uploads #### Open WebUI Verification status: Agent cross-checked (agent-cross-checked) Support: partial Customers connect local servers and cloud model endpoints and choose models in chat. The available catalog depends on their endpoints and credentials. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected code pinned to v0.12.3 / 91ea4e3421d1d8069f13d4a463fcb5986d94ea60; plan=Standard self-hosted with original branding intact; Enterprise only where explicitly stated; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure country; external inference, extraction, search and support locations require separate configuration and contracts; os=not specified. Limitations: - providers: Documented routes include OpenAI, Anthropic, Azure OpenAI, Mistral, DeepSeek and gateways such as OpenRouter; models must be enabled in the connected account. No endpoint was exercised. - current_models: Which current models are selectable on this plan? The provider guide contains example model names rather than an observed current endpoint catalog. Automatic routing and a current per-model modality matrix were not verified. - auto_routing: Does the product route between models automatically, and is the chosen model shown? The provider guide contains example model names rather than an observed current endpoint catalog. Automatic routing and a current per-model modality matrix were not verified. - multimodal_input: Vision and file context depend on the chosen model and configured extraction. No model-by-model audio/image acceptance matrix or fixture run was established. - providers — Which model providers are available? [partial]: Documented routes include OpenAI, Anthropic, Azure OpenAI, Mistral, DeepSeek and gateways such as OpenRouter; models must be enabled in the connected account. No endpoint was exercised. Sources: open-webui:open-webui:provider, open-webui:open-webui:compat. - current_models — Which current models are selectable on this plan? [unknown]: current_models: Which current models are selectable on this plan? The provider guide contains example model names rather than an observed current endpoint catalog. Automatic routing and a current per-model modality matrix were not verified. - user_choice — Can users pick the model per chat? [supported]: Users select connected models in the chat selector and can compare several models. Sources: open-webui:open-webui:provider. - 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? The provider guide contains example model names rather than an observed current endpoint catalog. Automatic routing and a current per-model modality matrix were not verified. - multimodal_input — Which models accept images, audio or files? [partial]: Vision and file context depend on the chosen model and configured extraction. No model-by-model audio/image acceptance matrix or fixture run was established. Sources: open-webui:open-webui:rag, open-webui:open-webui:extraction. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: open-webui:open-webui:provider, open-webui:open-webui:compat, open-webui:open-webui:rag, open-webui:open-webui:extraction ### 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. #### Glean Verification status: Agent cross-checked (agent-cross-checked) Support: partial Dated release notes and model deprecation guidance are public; comparable release-lag measurements remain unknown. Availability: generally-available Delivery: native Scope: surfaces=Glean Hosted web Assistant and Agents; version=Public documentation retrieved 2026-10-21; deployed version not observed; plan=Core Suite/Enterprise Flex Model Hub; Customer Key deprecation policy distinguished from Universal Model Key; add_ons=none stated; deployment_mode=dedicated-instance; region=Selected hosting and model-provider regions; no blanket EU or Swiss processing claim; os=not specified. Limitations: - Documented findings only; unestablished atomic questions remain explicit gaps. - 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? The release notes were checked, but provider general-release dates and scoped product-availability dates were not paired for the last three releases per provider. - changelog — Is there a dated public model changelog? [supported]: Public dated release notes include October 15, 2026 and model announcements. Sources: glean:glean:release, glean:glean:r2-core-entitlements. - deprecation_notice — How much notice is given before a model is removed? [partial]: For Customer Key Assistant, email notices are described at 60 and 15 days. The page also describes automatic migration for deprecated configurations; application to each removal needs confirmation. Sources: glean:glean:deprecation, glean:glean:r2-core-entitlements. - version_pinning — Can an admin keep an older model version? [partial]: Customer Key admins manage upgrades but deprecated models stop being usable. No indefinite version-pinning entitlement is established. Sources: glean:glean:deprecation, glean:glean:r2-core-entitlements. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: glean:glean:release, glean:glean:r2-core-entitlements, glean:glean:deprecation #### Open WebUI Verification status: Agent cross-checked (agent-cross-checked) Support: partial Dated upstream releases are public. A measured three-release availability lag and model retirement notice remain unknown. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected code pinned to v0.12.3 / 91ea4e3421d1d8069f13d4a463fcb5986d94ea60; plan=Standard self-hosted with original branding intact; Enterprise only where explicitly stated; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure country; external inference, extraction, search and support locations require separate configuration and contracts; os=not specified. Limitations: - release_lag_days: What was the lag for each of the last three major releases, per provider? No matched dates for the last three major provider releases and endpoint availability were collected; no binding model-removal notice period was found in the release and provider guides. - changelog: GitHub release notes are dated and sometimes mention model/protocol changes; they are not a complete provider model availability timeline. - deprecation_notice: How much notice is given before a model is removed? No matched dates for the last three major provider releases and endpoint availability were collected; no binding model-removal notice period was found in the release and provider guides. - version_pinning: An admin can list explicit provider model/deployment IDs and keep a chosen local model. Provider removal still controls remote model availability. - 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 matched dates for the last three major provider releases and endpoint availability were collected; no binding model-removal notice period was found in the release and provider guides. - changelog — Is there a dated public model changelog? [partial]: GitHub release notes are dated and sometimes mention model/protocol changes; they are not a complete provider model availability timeline. Sources: open-webui:open-webui: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 matched dates for the last three major provider releases and endpoint availability were collected; no binding model-removal notice period was found in the release and provider guides. - version_pinning — Can an admin keep an older model version? [partial]: An admin can list explicit provider model/deployment IDs and keep a chosen local model. Provider removal still controls remote model availability. Sources: open-webui:open-webui:openai, open-webui:open-webui:provider. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: open-webui:open-webui:releases, open-webui:open-webui:openai, open-webui:open-webui:provider ### 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. #### Glean Verification status: Agent cross-checked (agent-cross-checked) Support: partial Customer Key supports named provider accounts; it has documented feature and cloud restrictions. Availability: generally-available Delivery: native Scope: surfaces=Glean Hosted web Assistant and Agents, Customer Hosted managed GCP or AWS tenant; version=Public documentation retrieved 2026-10-21; deployed version not observed; plan=Core Suite Customer Key + Glean-family Model Hub Usage; Enterprise Flex Customer Key/private-cloud discounts are separately contractual; add_ons=none stated; deployment_mode=not specified; region=Selected hosting and model-provider regions; no blanket EU or Swiss processing claim; os=not specified. Limitations: - Documented findings only; unestablished atomic questions remain explicit gaps. - own_api_keys — Can the customer use its own provider API keys? [supported]: Customer Key supports customer provider credentials including OpenAI and direct Anthropic keys. Sources: glean:glean:models, glean:glean:r2-core-entitlements. - own_cloud_contract — Can it use its own Azure OpenAI, Bedrock or Vertex deployment? [partial]: Customer Key supports Azure OpenAI and named provider credentials. The supported-LLMs matrix permits Vertex only on GCP and Bedrock only on AWS; Configure LLMs separately says customer AWS can use Vertex, while its Vertex setup heading says GCP-only. AWS/Vertex eligibility is therefore unknown; no cross-cloud promise is made. Sources: glean:glean:models, glean:glean:key-matrix, glean:glean:r2-auto-policy-and-cloud-conflict, glean:glean:r2-core-entitlements. - custom_endpoint — Can an admin add any OpenAI-compatible endpoint? [unknown]: Can an admin add any OpenAI-compatible endpoint? The supported-provider configuration and key matrix were checked; arbitrary OpenAI-compatible customer endpoints are not established. - byo_pricing — Does BYO change the licence price? [partial]: Core Suite Customer Key limits Glean Model Hub charges to Glean-family usage; customer provider use is paid directly. Enterprise Flex says seats/credits are discounted for own-key/private-cloud customers but publishes no numeric adjustment. Sources: glean:glean:r2-core-entitlements, glean:glean:r2-flex-entitlements. - byo_restrictions — Which features stop working with BYO? [supported]: The key matrix marks Meeting Notes and podcast artifacts unsupported on Customer Key. Text defaults share one provider; image models may differ. Memory depends on deployment readiness. Sources: glean:glean:key-matrix, glean:glean:r2-core-entitlements. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: glean:glean:models, glean:glean:r2-core-entitlements, glean:glean:key-matrix, glean:glean:r2-auto-policy-and-cloud-conflict, glean:glean:r2-flex-entitlements #### Open WebUI Verification status: Agent cross-checked (agent-cross-checked) Support: partial Customer-held keys, Azure deployments and compatible endpoints are documented. The standard software licence does not include provider usage. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected code pinned to v0.12.3 / 91ea4e3421d1d8069f13d4a463fcb5986d94ea60; plan=Standard self-hosted with original branding intact; Enterprise only where explicitly stated; add_ons=Customer provider accounts or separately operated compatible gateway; deployment_mode=on-premise; region=Customer-selected infrastructure country; external inference, extraction, search and support locations require separate configuration and contracts; os=not specified. Limitations: - byo_restrictions: Compatibility and tools depend on the provider protocol and model. The sources do not promise identical functionality across all BYO endpoints. - own_api_keys — Can the customer use its own provider API keys? [supported]: Administrators supply customer provider keys in Connections. Sources: open-webui:open-webui:openai, open-webui:open-webui:compat. - own_cloud_contract — Can it use its own Azure OpenAI, Bedrock or Vertex deployment? [supported]: Azure OpenAI is documented using the customer Azure endpoint, deployment names and API key. Bedrock is also documented through a compatible route; Vertex contract behavior was not separately verified. Sources: open-webui:open-webui:openai, open-webui:open-webui:compat. - custom_endpoint — Can an admin add any OpenAI-compatible endpoint? [supported]: Administrators can set an OpenAI-compatible base URL and credentials. Sources: open-webui:open-webui:compat. - byo_pricing — Does BYO change the licence price? [supported]: Branding-intact standard use is free; external provider bills and optional Enterprise rights are separate. Sources: open-webui:open-webui:enterprise. - byo_restrictions — Which features stop working with BYO? [partial]: Compatibility and tools depend on the provider protocol and model. The sources do not promise identical functionality across all BYO endpoints. Sources: open-webui:open-webui:compat, open-webui:open-webui:models. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: open-webui:open-webui:openai, open-webui:open-webui:compat, open-webui:open-webui:enterprise, open-webui:open-webui:models ### 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. #### Glean Verification status: Agent cross-checked (agent-cross-checked) Support: partial The documented Universal Model Key open models run in the US. Supported customer-operated chat and embedding routes remain unknown. Availability: generally-available Delivery: native Scope: surfaces=Glean Hosted web Assistant and Agents; version=Public open-model guide retrieved 2026-10-26; no deployment observed; plan=Universal Model Key open-model route; current guide does not name a Core Suite/Flex entitlement for customer-operated models; add_ons=none stated; deployment_mode=dedicated-instance; region=Selected hosting and model-provider regions; no blanket EU or Swiss processing claim; os=not specified. Limitations: - The US inference finding is limited to the Universal Model Key open models described by the source. No absence of every conceivable private deployment is inferred. - self_hosted_chat — Can chat use a customer-hosted model? [unknown]: Can chat use a customer-hosted model? The public Model Hub, Customer Key matrix and deployment guides describe named hosted-provider routes. They do not establish supported vLLM/Ollama/TGI chat, customer embeddings, parity or vendor-hosted open-model inference in a named EU/CH region. Creator-region model toggles do not prove inference location. - self_hosted_embeddings — Can retrieval use customer-hosted embeddings? [unknown]: Can retrieval use customer-hosted embeddings? The public Model Hub, Customer Key matrix and deployment guides describe named hosted-provider routes. They do not establish supported vLLM/Ollama/TGI chat, customer embeddings, parity or vendor-hosted open-model inference in a named EU/CH region. Creator-region model toggles do not prove inference location. - feature_parity — Which features fail with self-hosted models? [unknown]: Which features fail with self-hosted models? The public Model Hub, Customer Key matrix and deployment guides describe named hosted-provider routes. They do not establish supported vLLM/Ollama/TGI chat, customer embeddings, parity or vendor-hosted open-model inference in a named EU/CH region. Creator-region model toggles do not prove inference location. - vendor_hosted_open_models — Does the vendor host open-weight models in EU/CH? [unsupported]: For Universal Model Key open models described in the region-control guide, inference is hosted in the US regardless of creator country. That documented route does not provide EU/CH-hosted open-model inference; other private contracts are unverified. Sources: glean:glean:r4-open-model-inference. Checked 2026-10-26; agent cross-checked 2026-10-26; check again by 2026-12-25. Sources: glean:glean:r4-open-model-inference #### Open WebUI Verification status: Agent cross-checked (agent-cross-checked) Support: partial Ollama, llama.cpp and vLLM are documented local inference routes; local retrieval requires local embedding and extraction services. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected code pinned to v0.12.3 / 91ea4e3421d1d8069f13d4a463fcb5986d94ea60; plan=Standard self-hosted with original branding intact; Enterprise only where explicitly stated; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure country; external inference, extraction, search and support locations require separate configuration and contracts; os=not specified. Limitations: - feature_parity: Local chat and RAG are possible. Tool reliability depends on model support, and online search, remote providers or cloud OCR require network access. No parity fixture was run. - vendor_hosted_open_models: Does the vendor host open-weight models in EU/CH? No first-party commitment to vendor-operated open-weight inference in EU or Switzerland was established in the deployment and provider guides. - self_hosted_chat — Can chat use a customer-hosted model? [supported]: Chat can use customer-operated Ollama, llama.cpp or vLLM endpoints. Sources: open-webui:open-webui:provider. - self_hosted_embeddings — Can retrieval use customer-hosted embeddings? [supported]: Retrieval can use local embedding models; the offline guide requires these assets to be downloaded before disconnecting. Sources: open-webui:open-webui:rag, open-webui:open-webui:offline. - feature_parity — Which features fail with self-hosted models? [partial]: Local chat and RAG are possible. Tool reliability depends on model support, and online search, remote providers or cloud OCR require network access. No parity fixture was run. Sources: open-webui:open-webui:offline, open-webui:open-webui:memory. - 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? No first-party commitment to vendor-operated open-weight inference in EU or Switzerland was established in the deployment and provider guides. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: open-webui:open-webui:provider, open-webui:open-webui:rag, open-webui:open-webui:offline, open-webui:open-webui:memory ### 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. #### Glean Verification status: Agent cross-checked (agent-cross-checked) Support: partial Model restrictions and blocking usage limits are documented; new department Auto policies remain an opt-in rollout on October 21. Availability: unknown Delivery: native Scope: surfaces=Glean Hosted web Assistant and Agents; version=As of 2026-10-21: existing controls plus opt-in Auto policies; policy GA scheduled 2026-10-29; plan=Core Suite/Enterprise Flex model governance and usage limits; new Auto policies require Glean-key deployment and Feature rollouts opt-in. Legacy Enterprise exclusions preserved.; add_ons=none stated; deployment_mode=dedicated-instance; region=Selected hosting and model-provider regions; no blanket EU or Swiss processing claim; os=not specified. Limitations: - Existing controls and the new policy rollout have different availability. No two-user enforcement test was run; hiding premium models alone does not prevent Auto from using them. - model_allowlist_by_group — Can admins limit models per group? [supported]: Eligible models can be allowed by department or synced IdP group. Default models cannot carry these restrictions; membership refresh is not immediate. Sources: glean:glean:model-controls, glean:glean:r2-core-entitlements, glean:glean:r2-flex-entitlements. - data_bound_models — Can admins restrict which models receive connector or knowledge content? [partial]: Admins can exclude connectors, folders/sites or individual documents from all LLM responses. This is an all-LLM content boundary; per-model data classification rules were not established. Sources: glean:glean:restrictions, glean:glean:r2-core-entitlements, glean:glean:r2-flex-entitlements. - default_model — Can admins set the default model? [partial]: Customer Key admins set defaults. Universal Model Key admins manage available models; the new department Auto policies require rollout opt-in on October 21, with GA scheduled October 29. They are not a verified generally available policy entitlement on the check date. Sources: glean:glean:model-config, glean:glean:key-matrix, glean:glean:r2-core-entitlements, glean:glean:r2-flex-entitlements, glean:glean:r3-october-rollout-migration. - user_limits — What per-user message or token limits apply, and are they published? [supported]: Core Suite and Enterprise Flex support configurable monthly per-user defaults and overrides. Limits reset each calendar month; legacy Enterprise lacks user/agent limits. Sources: glean:glean:limits, glean:glean:r2-core-entitlements, glean:glean:r2-flex-entitlements. - limit_behaviour — What happens when a limit is reached? [supported]: Admins select alert-only or block. An in-flight run finishes, then subsequent billable use is blocked until reset; slight overage can occur. Sources: glean:glean:limits, glean:glean:r2-core-entitlements, glean:glean:r2-flex-entitlements. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: glean:glean:model-controls, glean:glean:r2-core-entitlements, glean:glean:r2-flex-entitlements, glean:glean:restrictions, glean:glean:model-config, glean:glean:key-matrix, glean:glean:r3-october-rollout-migration, glean:glean:limits #### Open WebUI Verification status: Agent cross-checked (agent-cross-checked) Support: partial User/group model grants are documented. Optional custom filters can limit request rates; built-in recurring token/message quotas and monetary budgets remain unverified. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=New extension/locale findings inspected at v0.12.4 / 33c1978d5bad52a31df75ea55143025dfad18d16; earlier accepted documented facts retained; plan=Standard self-hosted with original branding intact; Enterprise only where explicitly stated; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure country; external inference, extraction, search and support locations require separate configuration and contracts; os=not specified. Limitations: - data_bound_models: Knowledge attached to a model scopes its retrieval, while user/resource grants control access. This does not establish a hard policy binding each source to an allowed outbound provider. - user_limits: What per-user message or token limits apply, and are they published? No configured quota or bounded two-user enforcement test was run; budget controls remain in progress on the public roadmap. - limit_behaviour: What happens when a limit is reached? No configured quota or bounded two-user enforcement test was run; budget controls remain in progress on the public roadmap. - model_allowlist_by_group — Can admins limit models per group? [supported]: Private model grants can be assigned to users and groups. Permissions accumulate, so a second group may grant access. Sources: open-webui:open-webui:groups. - data_bound_models — Can admins restrict which models receive connector or knowledge content? [partial]: Knowledge attached to a model scopes its retrieval, while user/resource grants control access. This does not establish a hard policy binding each source to an allowed outbound provider. Sources: open-webui:open-webui:knowledge, open-webui:open-webui:privacy. - default_model — Can admins set the default model? [supported]: The groups guide documents default models per group. Sources: open-webui:open-webui:groups. - user_limits — What per-user message or token limits apply, and are they published? [partial]: An optional official Filter example implements configurable requests per user per minute. It is customer-installed code with process-local counters, not an enabled recurring message/token allowance or monetary budget. No configured deployment was tested. Sources: open-webui:open-webui:r4-rate-limit-example, open-webui:open-webui:r4-filter-implementation. - limit_behaviour — What happens when a limit is reached? [partial]: The optional rate-limit example rejects an inlet request by raising an exception at its per-minute threshold; the inspected backend propagates inlet failures. Distributed enforcement, persistent quota balances and monetary overshoot behavior remain unverified. Sources: open-webui:open-webui:r4-rate-limit-example, open-webui:open-webui:r4-filter-implementation. Checked 2026-10-26; agent cross-checked 2026-10-26; check again by 2026-12-25. Sources: open-webui:open-webui:groups, open-webui:open-webui:knowledge, open-webui:open-webui:privacy, open-webui:open-webui:r4-rate-limit-example, open-webui:open-webui:r4-filter-implementation ## 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. #### Glean Verification status: Agent cross-checked (agent-cross-checked) Support: partial Chat uploads support common office formats with explicit size limits and OCR prerequisites. Availability: generally-available Delivery: native Scope: surfaces=Glean Hosted web Assistant and Agents; version=Public documentation retrieved 2026-10-21; deployed version not observed; plan=Core Suite Assistant + Model Hub Usage; Enterprise Flex doc uploads follow its named Assistant mode allowances; add_ons=none stated; deployment_mode=dedicated-instance; region=Selected hosting and model-provider regions; no blanket EU or Swiss processing claim; os=not specified. Limitations: - Shared long-PDF, scan, spreadsheet and presentation fixture was not run. - formats — Which formats are accepted? [supported]: Documented formats include PDF, DOC/DOCX, XLS/XLSX/XLSM, PPT/PPTX, text and image files; audio/video uploads are excluded. Sources: glean:glean:uploads, glean:glean:r2-core-entitlements. - limits — What size and count limits apply per file and chat? [supported]: 128K models allow 5 files at 64 MB each; 32K models 4 at 32 MB; 8K models 2 at 16 MB. Minimum file size is 1 KB. Sources: glean:glean:uploads, glean:glean:r2-core-entitlements. - ocr — Are scanned PDFs read? [supported]: Scanned PDFs require OCR enabled by an administrator or support. Sources: glean:glean:uploads, glean:glean:r2-core-entitlements. - spreadsheets — Are Excel tables read with structure intact? [partial]: Data Analysis handles uploaded spreadsheets, but merged cells, hierarchical tables, charts and complex structures have limited support. Fixture formula and structure fidelity was not tested. Sources: glean:glean:analysis, glean:glean:r2-core-entitlements. - full_vs_chunked — Is the whole file used or only retrieved parts, and does the user see which? [partial]: Uploaded analysis files expose full raw content within size limits; referenced indexed spreadsheets may be truncated. Archives are inspected on demand in Thinking mode. Complete visibility into selected chunks was not verified. Sources: glean:glean:analysis, glean:glean:uploads, glean:glean:r2-core-entitlements. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: glean:glean:uploads, glean:glean:r2-core-entitlements, glean:glean:analysis #### Open WebUI Verification status: Agent cross-checked (agent-cross-checked) Support: partial Documents can be attached and parsed for RAG or full-context injection. Scans depend on extraction configuration; spreadsheet fidelity was not tested. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected code pinned to v0.12.3 / 91ea4e3421d1d8069f13d4a463fcb5986d94ea60; plan=Standard self-hosted with original branding intact; Enterprise only where explicitly stated; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure country; external inference, extraction, search and support locations require separate configuration and contracts; os=not specified. Limitations: - formats: PDF and common text/Office documents are documented; parser choice controls formats. Temporary browser-only extraction has DOCX limitations. - ocr: Scanned PDFs can use a configured OCR-capable engine. No scanned fixture was tested. - spreadsheets: Are Excel tables read with structure intact? The shared Excel/formula, scanned contract and long-document fixtures were not uploaded, so structure preservation and observed failures are unknown. - formats — Which formats are accepted? [partial]: PDF and common text/Office documents are documented; parser choice controls formats. Temporary browser-only extraction has DOCX limitations. Sources: open-webui:open-webui:extraction, open-webui:open-webui:rag. - limits — What size and count limits apply per file and chat? [supported]: Administrators configure maximum document MB, upload count and allowed extensions with RAG_FILE_MAX_SIZE, RAG_FILE_MAX_COUNT and RAG_ALLOWED_FILE_EXTENSIONS; these are instance settings rather than a universal vendor allowance. Sources: open-webui:open-webui:env. - ocr — Are scanned PDFs read? [partial]: Scanned PDFs can use a configured OCR-capable engine. No scanned fixture was tested. Sources: open-webui:open-webui:extraction. - spreadsheets — Are Excel tables read with structure intact? [unknown]: spreadsheets: Are Excel tables read with structure intact? The shared Excel/formula, scanned contract and long-document fixtures were not uploaded, so structure preservation and observed failures are unknown. - full_vs_chunked — Is the whole file used or only retrieved parts, and does the user see which? [supported]: Users can select focused chunk retrieval or entire-document context; attached model knowledge has mode-specific behavior described in the guide. Sources: open-webui:open-webui:knowledge, open-webui:open-webui:rag. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: open-webui:open-webui:extraction, open-webui:open-webui:rag, open-webui:open-webui:env, open-webui:open-webui:knowledge ### 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. #### Glean Verification status: Agent cross-checked (agent-cross-checked) Support: partial Core Suite includes Library Collections; the replacement Projects rollout and plan entitlement remain qualified. Availability: unknown Delivery: native Scope: surfaces=Glean Hosted web Assistant and Agents; version=Public documentation retrieved 2026-10-21; deployed version not observed; plan=Core Suite Library Collections included; current Projects rollout/entitlement not separately established; add_ons=none stated; deployment_mode=dedicated-instance; region=Selected hosting and model-provider regions; no blanket EU or Swiss processing claim; os=not specified. Limitations: - Projects are rolling out gradually and may not be enabled for a given deployment. Chat and artifact sharing is separate from project membership. - Projects is documented as a gradual replacement for Collections, but its current Core Suite/Enterprise Flex entitlement and rollout were not verified. - persistent_collections — Can users keep document collections across chats? [partial]: Core Suite includes persistent Library Collections. Projects documentation describes a replacement containing chats/documents/files/artifacts, but current Core Suite/Enterprise Flex Projects entitlement and migration rollout were not verified. Sources: glean:glean:r2-core-entitlements, glean:glean:projects. - sharing_scope — Can collections be shared with users, groups or the whole organisation? [unknown]: The Projects guide describes private-by-default and people/group sharing, but current Projects rollout/entitlement under Core Suite or Enterprise Flex is not separately established. No current plan-scoped project-sharing guarantee is made. - size_limits — What are the collection limits? [unknown]: What are the collection limits? The Projects guide and agent builder were checked, but a current project size cap and direct knowledge-binding contract are not specified. - assistant_binding — Can collections be bound to an assistant? [unknown]: Projects and Agent Builder were checked; direct binding of a persistent Project or Collection to an assistant was not established. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: glean:glean:r2-core-entitlements, glean:glean:projects #### Open WebUI Verification status: Agent cross-checked (agent-cross-checked) Support: partial Knowledge bases persist across chats and can attach to a model or conversation, with user/group/public sharing. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected code pinned to v0.12.3 / 91ea4e3421d1d8069f13d4a463fcb5986d94ea60; plan=Standard self-hosted with original branding intact; Enterprise only where explicitly stated; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure country; external inference, extraction, search and support locations require separate configuration and contracts; os=not specified. Limitations: - size_limits: What are the collection limits? No fixed collection capacity was established; limits depend on operator configuration, storage and the selected database. - persistent_collections — Can users keep document collections across chats? [supported]: Knowledge bases store reusable document collections across chats. Sources: open-webui:open-webui:knowledge. - sharing_scope — Can collections be shared with users, groups or the whole organisation? [supported]: Private knowledge resources can grant read/write access to named users and groups, or be public within the instance. Sources: open-webui:open-webui:groups, open-webui:open-webui:knowledge. - size_limits — What are the collection limits? [unknown]: size_limits: What are the collection limits? No fixed collection capacity was established; limits depend on operator configuration, storage and the selected database. - assistant_binding — Can collections be bound to an assistant? [supported]: A model preset can bind one or more knowledge bases. Sources: open-webui:open-webui:models, open-webui:open-webui:knowledge. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: open-webui:open-webui:knowledge, open-webui:open-webui:groups, open-webui:open-webui:models ### 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). #### Glean Verification status: Agent cross-checked (agent-cross-checked) Support: partial Glean documents M365, Google and Atlassian connectors, with indexed and live patterns depending on source. Availability: generally-available Delivery: official-integration Scope: surfaces=Glean Hosted web Assistant and Agents; version=Public documentation retrieved 2026-10-21; deployed version not observed; plan=Core Suite native connectors included; individual connector setup/consent still required; Enterprise Flex platform connections use applicable feature allowances; add_ons=none stated; deployment_mode=dedicated-instance; region=Selected hosting and model-provider regions; no blanket EU or Swiss processing claim; os=not specified. Limitations: - Documented findings only; unestablished atomic questions remain explicit gaps. - microsoft_365 — Which M365 sources (SharePoint, OneDrive, Outlook, Teams) are connected? [supported]: SharePoint and OneDrive support indexing and live retrieval. Outlook and Teams are listed separately; Teams includes channels and opt-in private/meeting chats. M365 indexing requires application permissions and admin consent. Sources: glean:glean:sharepoint, glean:glean:onedrive, glean:glean:outlook, glean:glean:teams-connector, glean:glean:r2-core-entitlements. - google_workspace — Which Google sources are connected? [supported]: Google Drive and Gmail have official indexing documentation; Drive setup uses directory delegation. Plan-specific connector entitlements remain contractual. Sources: glean:glean:drive, glean:glean:gmail, glean:glean:r2-core-entitlements. - atlassian — Confluence and Jira? [partial]: The official catalog lists Confluence and Jira, including Cloud and Data Center documentation. Tenant setup and per-plan limits were not tested. Sources: glean:glean:connectors, glean:glean:r2-core-entitlements. - other_systems — Which other business systems? [partial]: The catalog includes Box, Salesforce, Notion, Slack, Zendesk and other systems. Individual entitlements, scopes and consent were not verified for every connector. Sources: glean:glean:connectors, glean:glean:r2-core-entitlements. - on_prem_sources — Can on-prem file shares or databases be connected? [partial]: Deployment guidance supports private connectivity for on-premise connectors. This establishes a network option, not every file share/database or a locally hosted whole platform. Sources: glean:glean:deploy, glean:glean:r2-core-entitlements. - connector_provider — Who builds and maintains each connector? [partial]: Glean publishes native connector guides; custom connectors and MCP routes are separate. Maintenance ownership for every listed third-party integration was not established. Sources: glean:glean:connectors, glean:glean:gateway, glean:glean:r2-core-entitlements. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: glean:glean:sharepoint, glean:glean:onedrive, glean:glean:outlook, glean:glean:teams-connector, glean:glean:r2-core-entitlements, glean:glean:drive, glean:glean:gmail, glean:glean:connectors, glean:glean:deploy, glean:glean:gateway #### Open WebUI Verification status: Agent cross-checked (agent-cross-checked) Support: partial Native file pickers and the separately operated official oikb companion provide different connector paths, including oikb Teams and Gmail sync. Source permission preservation remains untested. Availability: generally-available Delivery: official-integration Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected code pinned to v0.12.3 / 91ea4e3421d1d8069f13d4a463fcb5986d94ea60; plan=Standard self-hosted with original branding intact; Enterprise only where explicitly stated; add_ons=Microsoft/Google application registration for native file pickers, Separately deployed official oikb, Open WebUI 0.9.6+ and a user API key, Source credentials: Teams tenant/client/secret; Gmail Google credentials and the optional gmail extra; deployment_mode=on-premise; region=Customer-selected infrastructure country; external inference, extraction, search and support locations require separate configuration and contracts; os=not specified. Limitations: - Teams/Gmail are oikb companion connectors, not native per-user live file pickers. - Operator setup, source credentials and source-specific consent are required; permissions after indexing/revocation were not tested. - microsoft_365 — Which M365 sources (SharePoint, OneDrive, Outlook, Teams) are connected? [partial]: Native OneDrive for Business/SharePoint pickers require delegated application permissions and admin consent. Separately, oikb lists SharePoint and Teams; Teams uses TEAMS_TENANT_ID, TEAMS_CLIENT_ID and TEAMS_CLIENT_SECRET. This is a companion sync path. Outlook, exact Teams consent scopes and source-ACL preservation were not verified. Sources: open-webui:open-webui:onedrive, open-webui:open-webui:sync-connectors-r2. - google_workspace — Which Google sources are connected? [partial]: The native Drive picker imports selected files. Separately, official oikb lists Google Drive and Gmail using GOOGLE_APPLICATION_CREDENTIALS; Gmail has an optional installation extra. Mailbox delegation/consent scope and continuing source-ACL preservation were not tested. Sources: open-webui:open-webui:rag, open-webui:open-webui:sync-connectors-r2. - atlassian — Confluence and Jira? [partial]: Official companion oikb lists Confluence and Jira. Its separate credentials, runtime and source-specific configuration are required; source-permission sync was not verified. Sources: open-webui:open-webui:sync. - other_systems — Which other business systems? [partial]: oikb lists GitHub, Notion, Slack and S3 among its sources; these are copied-content integrations rather than native per-user live search. Sources: open-webui:open-webui:sync. - on_prem_sources — Can on-prem file shares or databases be connected? [supported]: A local folder can be mirrored using directory sync or the separate oikb tool. Sources: open-webui:open-webui:knowledge, open-webui:open-webui:sync. - connector_provider — Who builds and maintains each connector? [supported]: Open WebUI documents the native file pickers and maintains the official, separately installed oikb companion. MCP/OpenAPI connectors depend on their own maintainers and credentials. Sources: open-webui:open-webui:onedrive, open-webui:open-webui:rag, open-webui:open-webui:sync-connectors-r2, open-webui:open-webui:mcp. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: open-webui:open-webui:onedrive, open-webui:open-webui:sync-connectors-r2, open-webui:open-webui:rag, open-webui:open-webui:sync, open-webui:open-webui:knowledge, open-webui:open-webui: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. #### Glean Verification status: Agent cross-checked (agent-cross-checked) Support: partial Permission-aware indexed and live retrieval is documented; the restricted-document test is outstanding. Availability: generally-available Delivery: native Scope: surfaces=Glean Hosted web Assistant and Agents; version=Public documentation retrieved 2026-10-21; deployed version not observed; plan=Core Suite Protect permission enforcement and connector access; fine-grained source rules documented per connector; add_ons=Glean Protect+ and account-team enablement for O365 sensitivity-label redlisting only; deployment_mode=dedicated-instance; region=Selected hosting and model-provider regions; no blanket EU or Swiss processing claim; os=not specified. Limitations: - Permission claims are documented only; no leak-free outcome or measured propagation delay is claimed. - source_permissions_respected — Are source permissions enforced per user? [supported]: SharePoint, OneDrive and Teams docs describe per-user permissions checked at query time. This is documentary evidence, not a passed two-user test. Sources: glean:glean:sharepoint, glean:glean:onedrive, glean:glean:teams-connector, glean:glean:r2-core-entitlements. - enforcement_point — Does the source system, a mirrored index or nothing enforce them? [supported]: Indexed routes copy source ACLs into Glean and evaluate them at query time; live SharePoint/OneDrive routes avoid a stored content index. Sources: glean:glean:sharepoint, glean:glean:onedrive, glean:glean:r2-core-entitlements. - revocation_delay — How quickly does a removed permission take effect? [partial]: For indexed Drive, activity changes are checked every 10 minutes and group membership hourly. These are crawl schedules, not a measured revocation guarantee. Sources: glean:glean:drive, glean:glean:r2-core-entitlements. - admin_scope_controls — Can admins exclude sites, folders or labels? [supported]: Admins can include/exclude connectors, containers and documents from LLM access. Changes may take up to an hour. Sources: glean:glean:restrictions, glean:glean:r2-core-entitlements. - sensitivity_labels — Are Microsoft Purview or similar labels respected? [partial]: Glean Protect+ can exclude SharePoint/OneDrive files by Purview label priority after account-team enablement. It requires crawling, may need days for the first full crawl, and does not cover Teams message text. This is index exclusion, not a passed live-permission test. Sources: glean:glean:r4-purview-label-redlist. Checked 2026-10-26; agent cross-checked 2026-10-26; check again by 2026-12-25. Sources: glean:glean:sharepoint, glean:glean:onedrive, glean:glean:teams-connector, glean:glean:r2-core-entitlements, glean:glean:drive, glean:glean:restrictions, glean:glean:r4-purview-label-redlist #### Open WebUI Verification status: Agent cross-checked (agent-cross-checked) Support: partial Open WebUI knowledge-resource grants are documented. Enforcement of the original enterprise source permissions after copying has not passed the required test. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected code pinned to v0.12.3 / 91ea4e3421d1d8069f13d4a463fcb5986d94ea60; plan=Standard self-hosted with original branding intact; Enterprise only where explicitly stated; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure country; external inference, extraction, search and support locations require separate configuration and contracts; os=not specified. Limitations: - source_permissions_respected: Are source permissions enforced per user? No two-user restricted-document, grant/revoke or Purview-label fixture was run. Knowledge-resource ACLs and file-picker consent do not establish continuing source permission enforcement or revocation delay. - enforcement_point: Open WebUI resource grants govern access to its knowledge bases. Microsoft delegated permission limits the picker at import time; continuing source-system checks for the copied content were not established. - revocation_delay: How quickly does a removed permission take effect? No two-user restricted-document, grant/revoke or Purview-label fixture was run. Knowledge-resource ACLs and file-picker consent do not establish continuing source permission enforcement or revocation delay. - admin_scope_controls: Admins choose knowledge grants and which collections a model uses. Source site/folder/label exclusion and label propagation need connector-specific verification. - sensitivity_labels: Are Microsoft Purview or similar labels respected? No two-user restricted-document, grant/revoke or Purview-label fixture was run. Knowledge-resource ACLs and file-picker consent do not establish continuing source permission enforcement or revocation delay. - source_permissions_respected — Are source permissions enforced per user? [unknown]: source_permissions_respected: Are source permissions enforced per user? No two-user restricted-document, grant/revoke or Purview-label fixture was run. Knowledge-resource ACLs and file-picker consent do not establish continuing source permission enforcement or revocation delay. - enforcement_point — Does the source system, a mirrored index or nothing enforce them? [partial]: Open WebUI resource grants govern access to its knowledge bases. Microsoft delegated permission limits the picker at import time; continuing source-system checks for the copied content were not established. Sources: open-webui:open-webui:groups, open-webui:open-webui:onedrive. - revocation_delay — How quickly does a removed permission take effect? [unknown]: revocation_delay: How quickly does a removed permission take effect? No two-user restricted-document, grant/revoke or Purview-label fixture was run. Knowledge-resource ACLs and file-picker consent do not establish continuing source permission enforcement or revocation delay. - admin_scope_controls — Can admins exclude sites, folders or labels? [partial]: Admins choose knowledge grants and which collections a model uses. Source site/folder/label exclusion and label propagation need connector-specific verification. Sources: open-webui:open-webui:knowledge, open-webui:open-webui:groups. - sensitivity_labels — Are Microsoft Purview or similar labels respected? [unknown]: sensitivity_labels: Are Microsoft Purview or similar labels respected? No two-user restricted-document, grant/revoke or Purview-label fixture was run. Knowledge-resource ACLs and file-picker consent do not establish continuing source permission enforcement or revocation delay. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: open-webui:open-webui:groups, open-webui:open-webui:onedrive, open-webui:open-webui:knowledge ### 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. #### Glean Verification status: Agent cross-checked (agent-cross-checked) Support: partial Glean combines indexed and live connector routes; refresh timing is source-specific. Availability: generally-available Delivery: native Scope: surfaces=Glean Hosted web Assistant and Agents, Customer Hosted managed GCP or AWS tenant; version=Public documentation retrieved 2026-10-21; deployed version not observed; plan=Core Suite connector/index platform; Customer Hosted location/contract separately selected; add_ons=none stated; deployment_mode=not specified; region=Selected hosting and model-provider regions; no blanket EU or Swiss processing claim; os=not specified. Limitations: - Documented findings only; unestablished atomic questions remain explicit gaps. - live_or_indexed — Is content searched live or copied into an index? [supported]: SharePoint/OneDrive document indexed, live and tool routes. Indexed routes copy content; live routes do not store content in the index. Sources: glean:glean:sharepoint, glean:glean:onedrive, glean:glean:r2-core-entitlements. - sync_interval — How often does an index refresh? [supported]: Drive documents 10-minute activity crawls, hourly people/group crawls, 3-hour incremental crawls and normally 28-day full crawls. Sources: glean:glean:drive, glean:glean:r2-core-entitlements. - deletion_propagation — How quickly does a deleted document disappear? [partial]: Drive activity processing includes deletions, but no fixture deletion-to-answer interval or universal maximum was verified. Sources: glean:glean:drive, glean:glean:r2-core-entitlements. - index_location — Where is indexed content stored? [partial]: Indexes run in the selected isolated Glean Hosted or Customer Hosted environment. Exact country and any secondary log/backup locations need deployment confirmation. Sources: glean:glean:deploy, glean:glean:r2-core-entitlements. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: glean:glean:sharepoint, glean:glean:onedrive, glean:glean:r2-core-entitlements, glean:glean:drive, glean:glean:deploy #### Open WebUI Verification status: Agent cross-checked (agent-cross-checked) Support: partial Uploaded knowledge is copied into an operator-selected index. Manual directory sync or a separate daemon updates it. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected code pinned to v0.12.3 / 91ea4e3421d1d8069f13d4a463fcb5986d94ea60; plan=Standard self-hosted with original branding intact; Enterprise only where explicitly stated; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure country; external inference, extraction, search and support locations require separate configuration and contracts; os=not specified. Limitations: - sync_interval: Directory sync runs when invoked; oikb offers scheduled/on-demand synchronization. No universal connector interval or SLA applies. - deletion_propagation: Directory sync removes files missing from the local manifest during cleanup. Elapsed propagation time was not measured. - live_or_indexed — Is content searched live or copied into an index? [supported]: Uploaded documents are parsed and indexed; an experimental external-vector-source mode queries a pre-existing customer index without re-ingestion. Sources: open-webui:open-webui:rag, open-webui:open-webui:knowledge. - sync_interval — How often does an index refresh? [partial]: Directory sync runs when invoked; oikb offers scheduled/on-demand synchronization. No universal connector interval or SLA applies. Sources: open-webui:open-webui:knowledge, open-webui:open-webui:sync. - deletion_propagation — How quickly does a deleted document disappear? [partial]: Directory sync removes files missing from the local manifest during cleanup. Elapsed propagation time was not measured. Sources: open-webui:open-webui:knowledge. - index_location — Where is indexed content stored? [supported]: The operator selects the database or external vector source and its deployment location; there is no fixed vendor region for this self-hosted scope. Sources: open-webui:open-webui:rag, open-webui:open-webui:privacy. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: open-webui:open-webui:rag, open-webui:open-webui:knowledge, open-webui:open-webui:sync, open-webui:open-webui:privacy ### 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. #### Glean Verification status: Agent cross-checked (agent-cross-checked) Support: partial Linked source citations are documented; named-plan cross-language retrieval and observed grounding quality remain unknown. Availability: generally-available Delivery: native Scope: surfaces=Glean Hosted web Assistant and Agents; version=Public documentation retrieved 2026-10-21; deployed version not observed; plan=Core Suite Assistant/Deep Research with Model Hub Usage; no verified Core Suite/Enterprise Flex cross-language entitlement; add_ons=none stated; deployment_mode=dedicated-instance; region=Selected hosting and model-provider regions; no blanket EU or Swiss processing claim; os=not specified. Limitations: - Citation links do not establish citation accuracy. The Early Access language guide does not map cross-language retrieval to a verified named-plan entitlement. - citations — Are answers linked to specific sources? [supported]: Assistant documentation describes grounded answers with linked citations; Deep Research produces cited company/web reports. Sources: glean:glean:research, glean:glean:sharing, glean:glean:r2-core-entitlements. - citation_accuracy — Do the cited passages support the answer? [unknown]: Do the cited passages support the answer? No shared multilingual question set or restricted corpus was run; citation accuracy, correct-answer count and no-answer behavior remain unmeasured. - cross_language — Does a question in one language find documents in another? [unknown]: The language guide labels answering across document/query languages Early Access, but its Core Suite/Enterprise Flex entitlement and enabled rollout were not established. Cross-language retrieval for those named plans remains unknown; no multilingual fixture was run. - no_answer_behaviour — Does it say when the corpus has no answer? [unknown]: Does it say when the corpus has no answer? No shared multilingual question set or restricted corpus was run; citation accuracy, correct-answer count and no-answer behavior remain unmeasured. - observed_accuracy — How many of the question set were answered correctly? [unknown]: How many of the question set were answered correctly? No shared multilingual question set or restricted corpus was run; citation accuracy, correct-answer count and no-answer behavior remain unmeasured. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: glean:glean:research, glean:glean:sharing, glean:glean:r2-core-entitlements, glean:glean:language #### Open WebUI Verification status: Agent cross-checked (agent-cross-checked) Support: partial Citations are documented; citation accuracy and multilingual retrieval outcomes are untested. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected code pinned to v0.12.3 / 91ea4e3421d1d8069f13d4a463fcb5986d94ea60; plan=Standard self-hosted with original branding intact; Enterprise only where explicitly stated; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure country; external inference, extraction, search and support locations require separate configuration and contracts; os=not specified. Limitations: - citation_accuracy: Do the cited passages support the answer? The shared DE/FR/EN corpus and factual/no-answer question set were not run. No citation-link accuracy, cross-language result, refusal rate or numerical accuracy is claimed. - cross_language: Does a question in one language find documents in another? The shared DE/FR/EN corpus and factual/no-answer question set were not run. No citation-link accuracy, cross-language result, refusal rate or numerical accuracy is claimed. - no_answer_behaviour: Does it say when the corpus has no answer? The shared DE/FR/EN corpus and factual/no-answer question set were not run. No citation-link accuracy, cross-language result, refusal rate or numerical accuracy is claimed. - observed_accuracy: How many of the question set were answered correctly? The shared DE/FR/EN corpus and factual/no-answer question set were not run. No citation-link accuracy, cross-language result, refusal rate or numerical accuracy is claimed. - citations — Are answers linked to specific sources? [supported]: RAG answers can include source references; chunk metadata may add details such as page numbers. Sources: open-webui:open-webui:rag. - citation_accuracy — Do the cited passages support the answer? [unknown]: citation_accuracy: Do the cited passages support the answer? The shared DE/FR/EN corpus and factual/no-answer question set were not run. No citation-link accuracy, cross-language result, refusal rate or numerical accuracy is claimed. - 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 DE/FR/EN corpus and factual/no-answer question set were not run. No citation-link accuracy, cross-language result, refusal rate or numerical accuracy is claimed. - 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 DE/FR/EN corpus and factual/no-answer question set were not run. No citation-link accuracy, cross-language result, refusal rate or numerical accuracy is claimed. - 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 DE/FR/EN corpus and factual/no-answer question set were not run. No citation-link accuracy, cross-language result, refusal rate or numerical accuracy is claimed. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: open-webui:open-webui:rag ### 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. #### Glean Verification status: Agent cross-checked (agent-cross-checked) Support: partial Glean documents personal saved and learned memory with user controls and a limited admin off switch. Availability: generally-available Delivery: native Scope: surfaces=Glean Hosted web Assistant and Agents; version=Public documentation retrieved 2026-10-21; deployed version not observed; plan=Core Suite saved memory in seat and learned memory with Model Hub Usage; Enterprise Flex learned-memory rate/temporary waiver separate; add_ons=none stated; deployment_mode=dedicated-instance; region=Selected hosting and model-provider regions; no blanket EU or Swiss processing claim; os=not specified. Limitations: - Documented findings only; unestablished atomic questions remain explicit gaps. - custom_instructions — Can users set persistent instructions? [supported]: Saved preferences and explicit memories can persist across conversations. Sources: glean:glean:memory, glean:glean:r2-core-entitlements. - cross_chat_memory — Does the product remember facts across chats? [supported]: Saved and learned memories retain user work context and preferences across chats, subject to deployment availability. Sources: glean:glean:memory, glean:glean:r2-core-entitlements. - user_memory_controls — Can users view, edit and delete memories? [supported]: Users can view, edit and delete memories and control memory use in a conversation. Sources: glean:glean:memory, glean:glean:r2-core-entitlements. - admin_memory_controls — Can admins turn memory off? [partial]: Admins can disable learned memory; saved memories are user-controlled and cannot be disabled by admins through this setting. Sources: glean:glean:memory-admin, glean:glean:r2-core-entitlements. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: glean:glean:memory, glean:glean:r2-core-entitlements, glean:glean:memory-admin #### Open WebUI Verification status: Agent cross-checked (agent-cross-checked) Support: partial Users can manage persistent memory and admins can disable or group-restrict it. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected code pinned to v0.12.3 / 91ea4e3421d1d8069f13d4a463fcb5986d94ea60; plan=Standard self-hosted with original branding intact; Enterprise only where explicitly stated; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure country; external inference, extraction, search and support locations require separate configuration and contracts; os=not specified. Limitations: - custom_instructions: Model presets provide persistent system instructions and users can save instructions as memory. A separate personal-instructions setting was not inspected here. - custom_instructions — Can users set persistent instructions? [partial]: Model presets provide persistent system instructions and users can save instructions as memory. A separate personal-instructions setting was not inspected here. Sources: open-webui:open-webui:models, open-webui:open-webui:memory. - cross_chat_memory — Does the product remember facts across chats? [supported]: User-scoped memories carry facts and preferences between conversations. Sources: open-webui:open-webui:memory. - user_memory_controls — Can users view, edit and delete memories? [supported]: Settings permits adding, editing and deleting memories. Sources: open-webui:open-webui:memory. - admin_memory_controls — Can admins turn memory off? [supported]: Global and per-group switches disable memory access and server-side context use. Sources: open-webui:open-webui:memory. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: open-webui:open-webui:models, open-webui:open-webui:memory ## 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. #### Glean Verification status: Agent cross-checked (agent-cross-checked) Support: partial Custom agents combine instructions, models, knowledge and tools and have an internal library. Availability: generally-available Delivery: native Scope: surfaces=Glean Hosted web Assistant and Agents; version=Public documentation retrieved 2026-10-21; deployed version not observed; plan=Core Suite Agent Building/Governance/Sharing in seat; builder assistance/debugging/runtime use Model Hub as applicable; add_ons=none stated; deployment_mode=dedicated-instance; region=Selected hosting and model-provider regions; no blanket EU or Swiss processing claim; os=not specified. Limitations: - Documented findings only; unestablished atomic questions remain explicit gaps. - create_assistants — Can users create assistants with instructions, knowledge and tools? [supported]: Agent Builder configures instructions, model choice, knowledge and tools, with Workflow and Auto modes. Sources: glean:glean:builder, glean:glean:agents, glean:glean:r2-core-entitlements. - creator_permissions — Can admins limit who creates them? [partial]: Admin role and agent-sharing controls regulate creation and distribution; no trial creation-boundary check was performed. Sources: glean:glean:roles, glean:glean:agent-sharing, glean:glean:r2-core-entitlements. - sharing_scope — Can assistants be shared with users, groups or everyone? [supported]: Agents have controlled sharing/edit access, including department and IdP-group audiences where enabled. Sources: glean:glean:agent-sharing, glean:glean:groups, glean:glean:r2-core-entitlements. - catalogue — Is there an internal assistant directory? [supported]: The Agent library shows accessible agents for discovery and execution. Sources: glean:glean:library, glean:glean:r2-core-entitlements. - prompt_library — Are shared prompt templates available? [partial]: The former Prompt Library was retired August 5, 2025. Reusable prompts and apps moved to Agents; use current agents/templates rather than the retired interface. Sources: glean:glean:sunset, glean:glean:library, glean:glean:r2-core-entitlements. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: glean:glean:builder, glean:glean:agents, glean:glean:r2-core-entitlements, glean:glean:roles, glean:glean:agent-sharing, glean:glean:groups, glean:glean:library, glean:glean:sunset #### Open WebUI Verification status: Agent cross-checked (agent-cross-checked) Support: supported Model presets are reusable assistants combining instructions, a base model, knowledge and tools. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected code pinned to v0.12.3 / 91ea4e3421d1d8069f13d4a463fcb5986d94ea60; plan=Standard self-hosted with original branding intact; Enterprise only where explicitly stated; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure country; external inference, extraction, search and support locations require separate configuration and contracts; os=not specified. - create_assistants — Can users create assistants with instructions, knowledge and tools? [supported]: The Models workspace creates presets with instructions, knowledge, tools, skills and parameters. Sources: open-webui:open-webui:models. - creator_permissions — Can admins limit who creates them? [supported]: Workspace permission toggles control who can create resources. Sources: open-webui:open-webui:permissions. - sharing_scope — Can assistants be shared with users, groups or everyone? [supported]: Model grants may target users, groups or public instance visibility. Sources: open-webui:open-webui:groups, open-webui:open-webui:models. - catalogue — Is there an internal assistant directory? [supported]: The Models workspace lists available presets and model selectors expose those the user can access. Sources: open-webui:open-webui:models. - prompt_library — Are shared prompt templates available? [supported]: Workspace prompt permissions cover creating and sharing reusable prompt resources. Sources: open-webui:open-webui:permissions. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: open-webui:open-webui:models, open-webui:open-webui:permissions, open-webui:open-webui:groups ### 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. #### Glean Verification status: Agent cross-checked (agent-cross-checked) Support: partial Glean supports tools and external MCP with admin access controls; tool identities vary by route. Availability: generally-available Delivery: native Scope: surfaces=Glean Hosted web Assistant and Agents; version=Public documentation retrieved 2026-10-21; deployed version not observed; plan=Core Suite native tools/MCP host and Developer Tools; LLM tool/API calls incur Model Hub Usage; add_ons=none stated; deployment_mode=dedicated-instance; region=Selected hosting and model-provider regions; no blanket EU or Swiss processing claim; os=not specified. Limitations: - External-tool access boundaries were not tested. Customer Key and tool-provider contracts remain separate. - builtin_tools — Which tools are built in? [supported]: Agents can search knowledge, analyze data and read/write connected records; available tools depend on enabled connectors. Sources: glean:glean:agents, glean:glean:r2-core-entitlements. - custom_actions — Can admins add API actions? [supported]: The MCP Gateway exposes customer-built read/write tools as well as connector tools. Sources: glean:glean:gateway, glean:glean:r2-core-entitlements. - mcp_client — Can it use remote MCP servers, and with what admin control? [partial]: Admins register external remote MCP servers and apply role/group controls in Glean. This pass did not execute a server call. Sources: glean:glean:gateway, glean:glean:r2-core-entitlements. - tool_auth — Do tools act as the user or as a shared account? [partial]: OAuth integrations can use Glean-managed or customer OAuth applications; agent service credentials are a distinct route. Identity must be checked per tool. Sources: glean:glean:oauth, glean:glean:r2-core-entitlements. - tool_approval — Can admins approve or block tools, and can users confirm actions before they run? [partial]: Admins control tool exposure. The Microsoft file-creation guide instructs interactive-agent builders to disable Run without user confirmation when user approval is required. Write confirmation is configurable, not an unconditional enforced rule; a universal approval policy for unattended agents remains unknown. Sources: glean:glean:gateway, glean:glean:r3-microsoft-write-confirmation, glean:glean:r2-core-entitlements. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: glean:glean:agents, glean:glean:r2-core-entitlements, glean:glean:gateway, glean:glean:oauth, glean:glean:r3-microsoft-write-confirmation #### Open WebUI Verification status: Agent cross-checked (agent-cross-checked) Support: partial Native/custom tools and MCP are documented. The optional interactive Tool Permissions approval mode is experimental and off by default; automations and channel replies bypass it. Availability: beta Delivery: native Scope: surfaces=Customer-operated web application and server; version=Current Tools/MCP documentation retrieved 2026-10-21; beta availability qualifies the optional experimental approval mode, not all tool integrations; plan=Standard self-hosted with original branding intact; Enterprise only where explicitly stated; add_ons=Optional separately operated MCP/OpenAPI tool servers or stdio bridge; deployment_mode=on-premise; region=Customer-selected infrastructure country; external inference, extraction, search and support locations require separate configuration and contracts; os=not specified. Limitations: - The row uses beta for the experimental approval subfeature; ordinary tool integrations are documented separately. - Approval is opt-in for interactive chats and is bypassed in automations/channel replies; no mandatory side-effect policy was established. - builtin_tools — Which tools are built in? [supported]: Knowledge, memory, web and other built-in tool categories are configured per model. Sources: open-webui:open-webui:models. - custom_actions — Can admins add API actions? [supported]: Admins can install Python tools or connect OpenAPI tool servers. Sources: open-webui:open-webui:tools. - mcp_client — Can it use remote MCP servers, and with what admin control? [supported]: The dedicated current guide documents admin-configured Streamable HTTP MCP. Local stdio requires a separately deployed bridge such as mcpo. Sources: open-webui:open-webui:mcp, open-webui:open-webui:tools. - tool_auth — Do tools act as the user or as a shared account? [supported]: Configured modes include bearer credentials and user OAuth/OAuth 2.1; the resulting access depends on the server and granted scopes. Sources: open-webui:open-webui:mcp. - tool_approval — Can admins approve or block tools, and can users confirm actions before they run? [partial]: Admins control tool access and may enable experimental Tool Permissions (off by default). Interactive users can select Ask for approval with sequential Allow/Deny prompts; Full access remains the default. Automations and channel replies always use full access. A mandatory policy for every side effect and an external-call boundary fixture were not verified. Sources: open-webui:open-webui:approvals-r2, open-webui:open-webui:groups. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: open-webui:open-webui:models, open-webui:open-webui:tools, open-webui:open-webui:mcp, open-webui:open-webui:approvals-r2, open-webui:open-webui:groups ### 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. #### Glean Verification status: Agent cross-checked (agent-cross-checked) Support: partial Brave is the new web-search default; OpenAI search is a legacy route under migration. Deep Research produces cited read-only reports. Availability: generally-available Delivery: native Scope: surfaces=Glean Hosted web Assistant and Agents; version=2026-10-21, after the October 19 start of OpenAI-to-Brave migration; individual migration completion unobserved; plan=Core Suite Deep Research with Model Hub Usage; Brave for new web-search setups, configured Gemini route per setup guide, legacy OpenAI only until migrated; add_ons=none stated; deployment_mode=dedicated-instance; region=Selected hosting and model-provider regions; no blanket EU or Swiss processing claim; os=not specified. Limitations: - The dated release governs the new-versus-legacy route distinction. No per-tenant configuration, migration completion or provider-region test was performed. - web_search — Is web search available? [supported]: Brave is the default for new web-search setups. The setup guide also documents Google Gemini. OpenAI Web Search is closed to new setups; existing instances work only until Glean migrates them to Brave, beginning October 19. Sources: glean:glean:web, glean:glean:r2-core-entitlements, glean:glean:r3-october-rollout-migration. - admin_toggle — Can admins disable it per organisation or group? [partial]: Admins select enabled search tools and publication to Assistant, Agents and MCP. Universal per-group disabling was not verified. Sources: glean:glean:web, glean:glean:r2-core-entitlements. - search_provider — Which search provider handles queries, and where? [partial]: Brave is the new default and the provider named by Deep Research; Gemini is another documented configured route. OpenAI is legacy-only during the migration that began October 19. Per-tenant migration completion and query-processing countries remain unknown. Sources: glean:glean:web, glean:glean:research, glean:glean:r2-core-entitlements, glean:glean:r3-october-rollout-migration. - deep_research — Is multi-step research with a report available? [supported]: Deep Research writes cited multi-source reports from company sources and the web; it does not write to connected systems. Sources: glean:glean:research, glean:glean:r2-core-entitlements. - web_citations — Are web sources cited? [supported]: Deep Research reports contain linked web and company citations. Sources: glean:glean:research, glean:glean:r2-core-entitlements. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: glean:glean:web, glean:glean:r2-core-entitlements, glean:glean:r3-october-rollout-migration, glean:glean:research #### Open WebUI Verification status: Agent cross-checked (agent-cross-checked) Support: partial Search and multi-step page research are documented and require an external search provider or local metasearch deployment. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected code pinned to v0.12.3 / 91ea4e3421d1d8069f13d4a463fcb5986d94ea60; plan=Standard self-hosted with original branding intact; Enterprise only where explicitly stated; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure country; external inference, extraction, search and support locations require separate configuration and contracts; os=not specified. Limitations: - search_provider: Provider choice includes external search services and self-operated options. The actual provider region and query processing contract depend on the chosen service. - deep_research: Native function calling can perform repeated search and URL fetching. No bounded research-report task was exercised. - web_search — Is web search available? [supported]: Admins configure web search and users can enable it in a chat. Sources: open-webui:open-webui:web. - admin_toggle — Can admins disable it per organisation or group? [supported]: Feature permissions grant web search per group; global configuration can turn it off. Sources: open-webui:open-webui:permissions, open-webui:open-webui:web. - search_provider — Which search provider handles queries, and where? [partial]: Provider choice includes external search services and self-operated options. The actual provider region and query processing contract depend on the chosen service. Sources: open-webui:open-webui:web, open-webui:open-webui:offline. - deep_research — Is multi-step research with a report available? [partial]: Native function calling can perform repeated search and URL fetching. No bounded research-report task was exercised. Sources: open-webui:open-webui:agent-search. - web_citations — Are web sources cited? [supported]: Retrieved web sources are exposed as conversation references/citations. Sources: open-webui:open-webui:agent-search. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: open-webui:open-webui:web, open-webui:open-webui:permissions, open-webui:open-webui:offline, open-webui:open-webui:agent-search ### 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. #### Glean Verification status: Agent cross-checked (agent-cross-checked) Support: supported Workflow mode supports multi-step logic with schedule and content-event triggers. Availability: generally-available Delivery: native Scope: surfaces=Glean Hosted web Assistant and Agents; version=Public documentation retrieved 2026-10-21; deployed version not observed; plan=Core Suite Agent Building, workflow mode and triggers in seat; LLM execution incurs Model Hub Usage; add_ons=none stated; deployment_mode=dedicated-instance; region=Selected hosting and model-provider regions; no blanket EU or Swiss processing claim; os=not specified. - workflow_builder — Is there a workflow or chain builder? [supported]: Workflow mode supports explicit steps, branches, loops and hand-offs; Auto mode builds from natural-language goals. Sources: glean:glean:agents, glean:glean:r2-core-entitlements. - scheduled_tasks — Can prompts or assistants run on a schedule? [supported]: Published agents can run on schedules after admin enablement; setup differs by Auto versus Workflow mode. Sources: glean:glean:triggers, glean:glean:r2-core-entitlements. - event_triggers — Can external events start a workflow? [supported]: Content triggers run when supported connected-system content changes; chat and form triggers are separate. Sources: glean:glean:triggers, glean:glean:r2-core-entitlements. - builder_audience — Is building aimed at business users, IT or developers? [supported]: The builder supports natural-language creation and explicit workflow editing; the documentation includes self-paced Agent Builder training. Sources: glean:glean:agents, glean:glean:r2-core-entitlements. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: glean:glean:agents, glean:glean:r2-core-entitlements, glean:glean:triggers #### Open WebUI Verification status: Agent cross-checked (agent-cross-checked) Support: partial Recurring prompts execute on the operator’s server. Developer extensions can add chains; a business workflow builder was not established. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=New extension/locale findings inspected at v0.12.4 / 33c1978d5bad52a31df75ea55143025dfad18d16; earlier accepted documented facts retained; plan=Standard self-hosted with original branding intact; Enterprise only where explicitly stated; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure country; external inference, extraction, search and support locations require separate configuration and contracts; os=not specified. Limitations: - workflow_builder: Is there a workflow or chain builder? The automation, tool and webhook documentation did not establish a complete business workflow builder or incoming email/form event trigger contract. - event_triggers: Can external events start a workflow? The automation, tool and webhook documentation did not establish a complete business workflow builder or incoming email/form event trigger contract. - builder_audience: Schedules use a user-facing editor; custom Python tools and integrations require technical operators. No general no-code multi-system workflow designer was verified. - workflow_builder — Is there a workflow or chain builder? [unknown]: workflow_builder: Is there a workflow or chain builder? The automation, tool and webhook documentation did not establish a complete business workflow builder or incoming email/form event trigger contract. - scheduled_tasks — Can prompts or assistants run on a schedule? [supported]: Automations support hourly/daily/weekly/monthly and RRULE schedules, manual runs, pause and execution history. Sources: open-webui:open-webui:automation. - event_triggers — Can external events start a workflow? [partial]: A token-validated channel webhook publishes a message-created event that configured Python Event functions can handle. Developers must supply the downstream workflow logic; an incoming email/form connector or no-code multi-system workflow contract was not established. Sources: open-webui:open-webui:r4-incoming-channel-webhook, open-webui:open-webui:r4-event-dispatch. - builder_audience — Is building aimed at business users, IT or developers? [partial]: Schedules use a user-facing editor; custom Python tools and integrations require technical operators. No general no-code multi-system workflow designer was verified. Sources: open-webui:open-webui:automation, open-webui:open-webui:tools. Checked 2026-10-26; agent cross-checked 2026-10-26; check again by 2026-12-25. Sources: open-webui:open-webui:automation, open-webui:open-webui:tools, open-webui:open-webui:r4-incoming-channel-webhook, open-webui:open-webui:r4-event-dispatch ### 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. #### Glean Verification status: Agent cross-checked (agent-cross-checked) Support: partial Auto mode agents plan and use tools, but end-to-end execution safety was not tested. Availability: generally-available Delivery: native Scope: surfaces=Glean Hosted web Assistant and Agents; version=Public documentation retrieved 2026-10-21; deployed version not observed; plan=Core Suite Agent Harness/Agent Building with Model Hub Usage for LLM execution; add_ons=none stated; deployment_mode=dedicated-instance; region=Selected hosting and model-provider regions; no blanket EU or Swiss processing claim; os=not specified. Limitations: - Documented findings only; unestablished atomic questions remain explicit gaps. - agent_mode — Is there an agent mode for multi-step tasks? [supported]: Auto mode agents dynamically choose tools and delegate subtasks; Workflow mode uses explicit steps. Sources: glean:glean:agents, glean:glean:r2-core-entitlements. - visible_steps — Are steps and tool calls shown? [partial]: Workflow steps and builder preview/debugging are documented. Complete runtime visibility for every Auto action was not verified. Sources: glean:glean:builder, glean:glean:agents, glean:glean:r2-core-entitlements. - side_effect_confirmation — Must the user confirm actions with side effects? [partial]: Office creation tools describe a confirmation step before writing, without an editable inline preview. This does not establish confirmation for all scheduled operations. Sources: glean:glean:office-output, glean:glean:r2-core-entitlements. - stop_control — Can the user stop a running task? [partial]: The October 15 release documents that canceling an Assistant response terminates its tool calls and background tasks. Universal cancellation across scheduled/independent agents and every client was not verified by a fixture. Sources: glean:glean:r4-cancellation-release. Checked 2026-10-26; agent cross-checked 2026-10-26; check again by 2026-12-25. Sources: glean:glean:agents, glean:glean:r2-core-entitlements, glean:glean:builder, glean:glean:office-output, glean:glean:r4-cancellation-release #### Open WebUI Verification status: Agent cross-checked (agent-cross-checked) Support: partial Native tool calls and optional Open Terminal support agent tasks. Interactive tool approval is experimental and off by default, and never gates scheduled automations or channel replies. Availability: beta Delivery: native Scope: surfaces=Customer-operated web application and server; version=Current Tools/Open Terminal documentation retrieved 2026-10-21; beta availability qualifies optional experimental approvals; plan=Standard self-hosted with original branding intact; Enterprise only where explicitly stated; add_ons=Optional separately deployed Open Terminal; Terminals orchestration is a separate component with unverified pinned licence terms; deployment_mode=on-premise; region=Customer-selected infrastructure country; external inference, extraction, search and support locations require separate configuration and contracts; os=not specified. Limitations: - Beta availability refers to optional experimental approvals; the documented native tool mode is separate. - Automations and channel replies always use full access. - No gather-documents, draft-summary and propose-email fixture or background cancellation test was run. - agent_mode — Is there an agent mode for multi-step tasks? [supported]: Tool-capable models can use knowledge and external tools; separately connected Open Terminal adds file and command execution. Sources: open-webui:open-webui:models, open-webui:open-webui:terminal. - visible_steps — Are steps and tool calls shown? [supported]: Interactive tool calls display their results and, when experimental Ask for approval is enabled, pending/allowed/denied state. Sources: open-webui:open-webui:approvals-r2. - side_effect_confirmation — Must the user confirm actions with side effects? [partial]: Experimental Tool Permissions is disabled by default and users must select Ask for approval. Full access executes immediately; automations and channel replies always bypass approval. The documented control is not a mandatory confirmation policy for every side effect. Sources: open-webui:open-webui:approvals-r2. - stop_control — Can the user stop a running task? [partial]: In an interactive reply waiting for approval, Stop finalizes the reply and denies pending calls. This is a pending-call control; cancellation of background tasks and effects already executed was not tested. Sources: open-webui:open-webui:approvals-r2. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: open-webui:open-webui:models, open-webui:open-webui:terminal, open-webui:open-webui:approvals-r2 ### 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. #### Glean Verification status: Agent cross-checked (agent-cross-checked) Support: partial Public platform APIs and a remote MCP server are documented. Availability: generally-available Delivery: native Scope: surfaces=Glean APIs and remote MCP server; version=Public documentation retrieved 2026-10-21; deployed version not observed; plan=Core Suite Platform/Admin/Indexing/Tools APIs in seat and LLM Client APIs/MCP with Model Hub Usage; Enterprise Flex Client APIs consume FlexCredits; add_ons=none stated; deployment_mode=dedicated-instance; region=Selected hosting and model-provider regions; no blanket EU or Swiss processing claim; os=not specified. Limitations: - Documented findings only; unestablished atomic questions remain explicit gaps. - chat_api — Is there an API for chat and assistants? [supported]: Core Suite lists Chat and Agents APIs plus platform APIs and Web SDK; LLM-using calls incur Model Hub consumption. Sources: glean:glean:core-price, glean:glean:r2-core-entitlements, glean:glean:r2-flex-entitlements. - knowledge_api — Can documents be loaded through an API? [supported]: Core Suite lists the Indexing API and Tools API; document upload APIs are linked from the file-upload guide. Sources: glean:glean:core-price, glean:glean:uploads, glean:glean:r2-core-entitlements, glean:glean:r2-flex-entitlements. - api_governance — Do audit, budgets and model rules apply to API use? [partial]: Machine-scale API usage can incur extra fees, and MCP uses user permissions. Full audit/budget/model-rule parity across API credentials was not tested. Sources: glean:glean:core-price, glean:glean:mcp, glean:glean:r2-core-entitlements, glean:glean:r2-flex-entitlements. - mcp_server — Does the product expose itself to other agents over MCP? [supported]: Glean MCP exposes search, chat, document reading and other tools to external AI hosts. Sources: glean:glean:mcp, glean:glean:r2-core-entitlements, glean:glean:r2-flex-entitlements. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: glean:glean:core-price, glean:glean:r2-core-entitlements, glean:glean:r2-flex-entitlements, glean:glean:uploads, glean:glean:mcp #### Open WebUI Verification status: Agent cross-checked (agent-cross-checked) Support: partial Authenticated APIs cover chat, models and knowledge ingestion; product RBAC applies to API users. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected code pinned to v0.12.3 / 91ea4e3421d1d8069f13d4a463fcb5986d94ea60; plan=Standard self-hosted with original branding intact; Enterprise only where explicitly stated; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure country; external inference, extraction, search and support locations require separate configuration and contracts; os=not specified. Limitations: - api_governance: API users use their account permissions; optional audit capture can log requests. Enforced spend budgets and full API/UI parity were not demonstrated. - mcp_server: Does the product expose itself to other agents over MCP? No supported native MCP server exposing the whole product was established in the API and MCP-client guides. - chat_api — Is there an API for chat and assistants? [supported]: OpenAI-compatible chat completion and model management endpoints accept API keys or session JWTs. Sources: open-webui:open-webui:api. - knowledge_api — Can documents be loaded through an API? [supported]: File upload and knowledge attachment are documented APIs. Sources: open-webui:open-webui:api, open-webui:open-webui:knowledge. - api_governance — Do audit, budgets and model rules apply to API use? [partial]: API users use their account permissions; optional audit capture can log requests. Enforced spend budgets and full API/UI parity were not demonstrated. Sources: open-webui:open-webui:api, open-webui:open-webui:hardening. - 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? No supported native MCP server exposing the whole product was established in the API and MCP-client guides. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: open-webui:open-webui:api, open-webui:open-webui:knowledge, open-webui:open-webui:hardening ## 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. #### Glean Verification status: Agent cross-checked (agent-cross-checked) Support: partial Glean has web, desktop, mobile and extension access, including managed mobile controls. Availability: generally-available Delivery: native Scope: surfaces=Glean Hosted web Assistant and Agents, Glean for Desktop Windows and macOS, Glean iOS and Android, Glean browser extension and companion; version=Public documentation retrieved 2026-10-21; deployed version not observed; plan=Core Suite Glean surfaces included in seat; individual AI actions may incur Model Hub Usage; add_ons=none stated; deployment_mode=dedicated-instance; region=Selected hosting and model-provider regions; no blanket EU or Swiss processing claim; os=Windows, macOS, iOS, Android. Limitations: - Documented findings only; unestablished atomic questions remain explicit gaps. - web — Is a full web client available? [supported]: The full browser app provides chat, Library and agents. Sources: glean:glean:surfaces, glean:glean:r2-core-entitlements. - desktop_apps — Windows and macOS apps? [supported]: Windows and macOS desktop clients are documented. Sources: glean:glean:surfaces, glean:glean:r2-core-entitlements. - mobile_apps — iOS and Android apps with SSO? [supported]: iOS and Android apps require an active SSO-configured tenant. Sources: glean:glean:mobile, glean:glean:r2-core-entitlements. - browser_extension — Is there a browser extension or sidebar? [supported]: The extension supplies sidebar chat/search and a companion for selected text. Sources: glean:glean:surfaces, glean:glean:r2-core-entitlements. - managed_deployment — Can IT deploy and configure clients through MDM? [supported]: Mobile integrates with Intune App Protection. Managed desktop and extension deployment are linked in official deployment guidance. Sources: glean:glean:mobile, glean:glean:surfaces, glean:glean:r2-core-entitlements. - client_feature_gaps — Which features are missing on mobile? [partial]: Deep Research is web-only. Real-time voice supports web, desktop and mobile; other complete parity differences were not verified. Sources: glean:glean:research, glean:glean:voice, glean:glean:r2-core-entitlements. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: glean:glean:surfaces, glean:glean:r2-core-entitlements, glean:glean:mobile, glean:glean:research, glean:glean:voice #### Open WebUI Verification status: Agent cross-checked (agent-cross-checked) Support: partial The web/PWA client is complemented by a separate native Desktop distribution for macOS, Windows and Linux. Desktop is explicitly Early Alpha; SSO/MDM and cross-client parity were not tested. Availability: beta Delivery: native Scope: surfaces=Customer-operated web application and server, Open WebUI Desktop native distribution (Early Alpha); version=Web/PWA documentation retrieved 2026-10-21; Desktop v0.0.20 / 601137c5dec2967cfe173a6bf071fbbb460852be (released 2026-05-06, labelled Early Alpha); plan=Customer-operated web/PWA plus the separately packaged Open WebUI Desktop distribution; production Quick Start recommends Docker or Python; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure country; external inference, extraction, search and support locations require separate configuration and contracts; os=Windows, macOS, Linux, iOS (PWA), Android (PWA). Limitations: - Beta availability reflects the Early Alpha desktop distribution; the browser/PWA route is separate. - Native mobile clients, corporate SSO, MDM/Intune deployment and client parity were not tested. - web — Is a full web client available? [supported]: The deployed server supplies the full browser client; Quick Start also links the separate desktop distribution. Sources: open-webui:open-webui:desktop-quickstart-r2. - desktop_apps — Windows and macOS apps? [partial]: Open WebUI Desktop v0.0.20 provides native macOS (Apple Silicon/Intel), Windows (x64/ARM64) and Linux installers. It can run locally without Docker or connect to an existing server. It is labelled Early Alpha; first launch requires internet. Enterprise SSO and managed rollout were not tested. Sources: open-webui:open-webui:desktop-readme-r2, open-webui:open-webui:desktop-release-r2, open-webui:open-webui:desktop-quickstart-r2. - mobile_apps — iOS and Android apps with SSO? [partial]: Android browsers and iOS Safari can install the PWA. Native mobile app-store clients and mobile company-SSO/MDM behavior were not verified. Sources: open-webui:open-webui:pwa-r2. - browser_extension — Is there a browser extension or sidebar? [unknown]: browser_extension: Is there a browser extension or sidebar? No first-party managed MDM/Intune deployment policy or Office/browser sidebar extension was established in the client guide. - managed_deployment — Can IT deploy and configure clients through MDM? [unknown]: managed_deployment: Can IT deploy and configure clients through MDM? No first-party managed MDM/Intune deployment policy or Office/browser sidebar extension was established in the client guide. - client_feature_gaps — Which features are missing on mobile? [partial]: PWA notifications need the app to remain open. Desktop is Early Alpha and Quick Start recommends Docker/Python for production; no desktop/mobile feature-parity or enterprise SSO matrix was verified. Sources: open-webui:open-webui:pwa-r2, open-webui:open-webui:desktop-readme-r2, open-webui:open-webui:desktop-quickstart-r2. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: open-webui:open-webui:desktop-quickstart-r2, open-webui:open-webui:desktop-readme-r2, open-webui:open-webui:desktop-release-r2, open-webui:open-webui:pwa-r2 ### 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. #### Glean Verification status: Agent cross-checked (agent-cross-checked) Support: partial A Microsoft Teams app is documented; connectors and file-generation tools do not establish in-Office add-ins. Availability: generally-available Delivery: official-integration Scope: surfaces=Glean in Microsoft Teams, Glean Hosted web Assistant and Agents; version=Public documentation retrieved 2026-10-21; deployed version not observed; plan=Core Suite embedded Microsoft Teams and other listed surfaces; selected Assistant actions incur Model Hub Usage; add_ons=none stated; deployment_mode=dedicated-instance; region=Selected hosting and model-provider regions; no blanket EU or Swiss processing claim; os=not specified. Limitations: - Documented findings only; unestablished atomic questions remain explicit gaps. - word_excel_powerpoint — Does it work inside Word, Excel and PowerPoint? [unknown]: Does it work inside Word, Excel and PowerPoint? The Teams app, connector catalog and Office-output guides were checked. An assistant embedded inside Word/Excel/PowerPoint, Outlook, Docs/Sheets/Gmail was not established; remote content access is not counted as in-app presence. - outlook — Does it work inside Outlook? [unknown]: Does it work inside Outlook? The Teams app, connector catalog and Office-output guides were checked. An assistant embedded inside Word/Excel/PowerPoint, Outlook, Docs/Sheets/Gmail was not established; remote content access is not counted as in-app presence. - teams — Is there a Teams app or bot? [supported]: The Glean Teams app has an admin installation guide and tenant setup/consent requirements. Sources: glean:glean:teams-app, glean:glean:r2-core-entitlements. - google_workspace_apps — Does it work inside Docs, Sheets or Gmail? [unknown]: Does it work inside Docs, Sheets or Gmail? The Teams app, connector catalog and Office-output guides were checked. An assistant embedded inside Word/Excel/PowerPoint, Outlook, Docs/Sheets/Gmail was not established; remote content access is not counted as in-app presence. - licence_prerequisites — Which licences or consents are needed? [partial]: Teams requires admin deployment in a configured Glean tenant and Microsoft permissions. Extra licence charges are not numerically specified in the guide. Sources: glean:glean:teams-app, glean:glean:r2-core-entitlements. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: glean:glean:teams-app, glean:glean:r2-core-entitlements #### Open WebUI 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. #### Glean Verification status: Agent cross-checked (agent-cross-checked) Support: partial Browser companion translation and general writing are documented; layout-preserving document translation is unverified. Availability: generally-available Delivery: native Scope: surfaces=Glean browser extension and companion, Glean Hosted web Assistant and Agents; version=Public documentation retrieved 2026-10-21; deployed version not observed; plan=Core Suite browser Companion/Sidebar surfaces included; LLM writing/translation uses configured model usage; add_ons=none stated; deployment_mode=dedicated-instance; region=Selected hosting and model-provider regions; no blanket EU or Swiss processing claim; os=not specified. Limitations: - Documented findings only; unestablished atomic questions remain explicit gaps. - document_translation — Can whole documents be translated with formatting kept? [unknown]: Can whole documents be translated with formatting kept? The companion, file-upload and Office-generation guides were checked. No whole-document layout-preserving translation, company glossary, formality/de-CH control or DE-to-FR/IT fixture result was established. - translation_engine — Which engine translates? [partial]: The browser companion translates selected text through Glean. A dedicated translation service or exact translation-model route is not named here. Sources: glean:glean:surfaces, glean:glean:r2-core-entitlements. - glossaries — Are company glossaries supported? [unknown]: Are company glossaries supported? The companion, file-upload and Office-generation guides were checked. No whole-document layout-preserving translation, company glossary, formality/de-CH control or DE-to-FR/IT fixture result was established. - formality_and_variants — Can formality and regional variants (de-CH) be set? [unknown]: Can formality and regional variants (de-CH) be set? The companion, file-upload and Office-generation guides were checked. No whole-document layout-preserving translation, company glossary, formality/de-CH control or DE-to-FR/IT fixture result was established. - writing_tools — Are dedicated rewrite and proofreading tools available? [partial]: Configured agents support drafting; the browser companion explains, summarizes and translates selected text. Dedicated proofreading behavior was not verified. Sources: glean:glean:surfaces, glean:glean:agents, glean:glean:r2-core-entitlements. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: glean:glean:surfaces, glean:glean:r2-core-entitlements, glean:glean:agents #### Open WebUI Verification status: Agent cross-checked (agent-cross-checked) Support: partial AI editing is documented in Notes. Dedicated layout-preserving translation and glossary behavior remain unknown. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected code pinned to v0.12.3 / 91ea4e3421d1d8069f13d4a463fcb5986d94ea60; plan=Standard self-hosted with original branding intact; Enterprise only where explicitly stated; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure country; external inference, extraction, search and support locations require separate configuration and contracts; os=not specified. Limitations: - document_translation: Can whole documents be translated with formatting kept? No DE-to-FR/IT contract translation fixture, de-CH/formality acceptance test, company glossary or layout-preserving translator was verified in the Notes and document guides. - translation_engine: Notes sends rewrite requests to the selected model. A dedicated translation service or whole-document translation workflow was not established. - glossaries: Are company glossaries supported? No DE-to-FR/IT contract translation fixture, de-CH/formality acceptance test, company glossary or layout-preserving translator was verified in the Notes and document guides. - formality_and_variants: Can formality and regional variants (de-CH) be set? No DE-to-FR/IT contract translation fixture, de-CH/formality acceptance test, company glossary or layout-preserving translator was verified in the Notes and document guides. - document_translation — Can whole documents be translated with formatting kept? [unknown]: document_translation: Can whole documents be translated with formatting kept? No DE-to-FR/IT contract translation fixture, de-CH/formality acceptance test, company glossary or layout-preserving translator was verified in the Notes and document guides. - translation_engine — Which engine translates? [partial]: Notes sends rewrite requests to the selected model. A dedicated translation service or whole-document translation workflow was not established. Sources: open-webui:open-webui:notes. - glossaries — Are company glossaries supported? [unknown]: glossaries: Are company glossaries supported? No DE-to-FR/IT contract translation fixture, de-CH/formality acceptance test, company glossary or layout-preserving translator was verified in the Notes and document guides. - formality_and_variants — Can formality and regional variants (de-CH) be set? [unknown]: formality_and_variants: Can formality and regional variants (de-CH) be set? No DE-to-FR/IT contract translation fixture, de-CH/formality acceptance test, company glossary or layout-preserving translator was verified in the Notes and document guides. - writing_tools — Are dedicated rewrite and proofreading tools available? [supported]: The Notes editor supports AI rewriting and improving selected text. Sources: open-webui:open-webui:notes. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: open-webui:open-webui:notes ### 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. #### Glean Verification status: Agent cross-checked (agent-cross-checked) Support: partial Glean can generate and edit images using enabled image models. Availability: generally-available Delivery: native Scope: surfaces=Glean Hosted web Assistant and Agents; version=Public documentation retrieved 2026-10-21; deployed version not observed; plan=Core Suite image generation/editing with Model Hub Usage; provider/key availability remains conditional; add_ons=none stated; deployment_mode=dedicated-instance; region=Selected hosting and model-provider regions; no blanket EU or Swiss processing claim; os=not specified. Limitations: - Documented findings only; unestablished atomic questions remain explicit gaps. - image_generation — Can users generate images, with which models? [supported]: Universal Model Key uses the managed GPT Image 2.5 or GPT Image 2 default; Customer Key admins select image models and Agents can select enabled models. Sources: glean:glean:images, glean:glean:r2-core-entitlements. - image_editing — Can users edit uploaded images? [supported]: The image guide documents editing uploaded images. Sources: glean:glean:images, glean:glean:r2-core-entitlements. - admin_control — Can admins restrict image generation? [supported]: An administrator must enable image generation and a supported image model. Sources: glean:glean:images, glean:glean:r2-core-entitlements. - usage_terms — What usage rights apply to output? [partial]: Customer rights in outputs are governed by the Terms and AI Addendum together with model-provider terms; no unique or exclusive image-output guarantee was verified. Sources: glean:glean:terms, glean:glean:ai-addendum, glean:glean:r2-core-entitlements. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: glean:glean:images, glean:glean:r2-core-entitlements, glean:glean:terms, glean:glean:ai-addendum #### Open WebUI Verification status: Agent cross-checked (agent-cross-checked) Support: partial Configured image engines generate and edit uploaded images, subject to feature permissions. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected code pinned to v0.12.3 / 91ea4e3421d1d8069f13d4a463fcb5986d94ea60; plan=Standard self-hosted with original branding intact; Enterprise only where explicitly stated; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure country; external inference, extraction, search and support locations require separate configuration and contracts; os=not specified. Limitations: - usage_terms: What usage rights apply to output? Output rights and actual per-image costs depend on the chosen image service and were not established as a single Open WebUI entitlement. - image_generation — Can users generate images, with which models? [supported]: OpenAI, Gemini, ComfyUI and AUTOMATIC1111 are documented engine routes; exact models are operator-configured. Sources: open-webui:open-webui:images. - image_editing — Can users edit uploaded images? [supported]: The usage guide documents uploaded-image edits and multi-image compositing with an enabled editing engine. Sources: open-webui:open-webui:image-usage. - admin_control — Can admins restrict image generation? [supported]: Global image configuration, feature permission and model capability govern availability. Sources: open-webui:open-webui:image-usage. - usage_terms — What usage rights apply to output? [unknown]: usage_terms: What usage rights apply to output? Output rights and actual per-image costs depend on the chosen image service and were not established as a single Open WebUI entitlement. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: open-webui:open-webui:images, open-webui:open-webui:image-usage ### 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. #### Glean Verification status: Agent cross-checked (agent-cross-checked) Support: partial Real-time voice is available with provider streaming; meeting functionality depends on key mode. Availability: generally-available Delivery: native Scope: surfaces=Glean Hosted web Assistant and Agents, Glean for Desktop Windows and macOS, Glean iOS and Android; version=Public documentation retrieved 2026-10-21; deployed version not observed; plan=Core Suite real-time voice/Meeting Notes with Model Hub Usage; Meeting Notes requires Universal Model Key per feature matrix; add_ons=none stated; deployment_mode=dedicated-instance; region=Selected hosting and model-provider regions; no blanket EU or Swiss processing claim; os=not specified. Limitations: - Raw voice audio streams to the configured model provider and is not stored according to the voice guide; transcripts follow chat retention. - dictation — Can users dictate prompts? [unknown]: Can users dictate prompts? The voice guide and key-mode matrix were checked; separate dictation and Swiss German recognition were not established or tested. - read_aloud — Can answers be read aloud? [partial]: Real-time voice speaks its responses; a separate read-aloud control for arbitrary text responses was not established. Sources: glean:glean:voice, glean:glean:r2-core-entitlements. - voice_conversation — Is a live voice mode available? [supported]: Interactive voice supports web, desktop and mobile, with interruptible spoken replies and a chat transcript. It does not invoke a chosen published agent. Sources: glean:glean:voice, glean:glean:r2-core-entitlements. - meeting_summaries — Are meetings transcribed and summarised? [partial]: The key matrix lists Meeting Notes as generally available with Universal Model Key and unsupported with Customer Key. Recording/language behavior was not tested. Sources: glean:glean:key-matrix, glean:glean:r2-core-entitlements. - swiss_german_speech — Is Swiss German speech recognised? [unknown]: Is Swiss German speech recognised? The voice guide and key-mode matrix were checked; separate dictation and Swiss German recognition were not established or tested. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: glean:glean:voice, glean:glean:r2-core-entitlements, glean:glean:key-matrix #### Open WebUI Verification status: Agent cross-checked (agent-cross-checked) Support: partial Dictation, read-aloud and voice conversation use configured audio services. Swiss German recognition and a meeting workflow were not tested. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected code pinned to v0.12.3 / 91ea4e3421d1d8069f13d4a463fcb5986d94ea60; plan=Standard self-hosted with original branding intact; Enterprise only where explicitly stated; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure country; external inference, extraction, search and support locations require separate configuration and contracts; os=not specified. Limitations: - meeting_summaries: Are meetings transcribed and summarised? No meeting-transcription fixture or Swiss German speech evaluation was run. Audio location depends on the chosen browser, local, Azure or other provider engine. - swiss_german_speech: Is Swiss German speech recognised? No meeting-transcription fixture or Swiss German speech evaluation was run. Audio location depends on the chosen browser, local, Azure or other provider engine. - dictation — Can users dictate prompts? [supported]: Audio configuration supports speech-to-text for prompts. Sources: open-webui:open-webui:env. - read_aloud — Can answers be read aloud? [supported]: Standard voice reads replies using the configured TTS engine, including browser options. Sources: open-webui:open-webui:voice. - voice_conversation — Is a live voice mode available? [supported]: Standard STT/TTS voice mode and separately configured realtime API calls are documented. Sources: open-webui:open-webui:voice. - meeting_summaries — Are meetings transcribed and summarised? [unknown]: meeting_summaries: Are meetings transcribed and summarised? No meeting-transcription fixture or Swiss German speech evaluation was run. Audio location depends on the chosen browser, local, Azure or other provider engine. - swiss_german_speech — Is Swiss German speech recognised? [unknown]: swiss_german_speech: Is Swiss German speech recognised? No meeting-transcription fixture or Swiss German speech evaluation was run. Audio location depends on the chosen browser, local, Azure or other provider engine. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: open-webui:open-webui:env, open-webui:open-webui:voice ### 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. #### Glean Verification status: Agent cross-checked (agent-cross-checked) Support: partial Data analysis and Office file output are documented, with spreadsheet and template limitations. Availability: generally-available Delivery: native Scope: surfaces=Glean Hosted web Assistant and Agents; version=Public documentation retrieved 2026-10-21; deployed version not observed; plan=Core Suite Assistant/Canvas/document output with Model Hub Usage; provider/tool prerequisites apply; add_ons=none stated; deployment_mode=dedicated-instance; region=Selected hosting and model-provider regions; no blanket EU or Swiss processing claim; os=not specified. Limitations: - No fixture analysis or output-file inspection. Code-interpreter provider and retention differ by route. - data_analysis — Can it analyse spreadsheets with executed code? [supported]: Thinking-mode uploaded spreadsheets can use a per-user/session sandbox. Indexed spreadsheets may be truncated and cross-indexed-file numeric aggregation is not supported by the documented Data Analysis route. Sources: glean:glean:analysis, glean:glean:r2-core-entitlements. - charts — Can it produce charts? [unknown]: The Data Analysis and Office-output guides were checked, but chart generation and chart-file fidelity were not established or observed in this pass. - office_file_output — Can it create Word, Excel or PowerPoint files? [supported]: Enabled tools create Word documents, Excel workbooks and PowerPoint decks, saved/downloaded through the documented route. Arbitrary Word/Excel template population is not supported by create tools. Sources: glean:glean:office-output, glean:glean:r2-core-entitlements. - canvas_editing — Is there a document or canvas editor for iterating on output? [supported]: Slide generation creates decks in Canvas for refinement and export; exact themes and embedded elements are not guaranteed. Sources: glean:glean:office-output, glean:glean:r2-core-entitlements. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: glean:glean:analysis, glean:glean:r2-core-entitlements, glean:glean:office-output #### Open WebUI Verification status: Agent cross-checked (agent-cross-checked) Support: partial Optional Open Terminal runs analysis code and creates artifacts; Notes provides document editing. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected code pinned to v0.12.3 / 91ea4e3421d1d8069f13d4a463fcb5986d94ea60; plan=Standard self-hosted with original branding intact; Enterprise only where explicitly stated; add_ons=Separately operated Open Terminal and document libraries; Enterprise Terminals optional; deployment_mode=on-premise; region=Customer-selected infrastructure country; external inference, extraction, search and support locations require separate configuration and contracts; os=not specified. Limitations: - office_file_output: The runtime can process Office files and create downloadable files through code and installed packages. Editable DOCX/XLSX/PPTX output was not verified with the shared fixture. - data_analysis — Can it analyse spreadsheets with executed code? [supported]: Open Terminal documents spreadsheet/CSV inspection and code-based data analysis on the separately deployed runtime. Sources: open-webui:open-webui:terminal. - charts — Can it produce charts? [supported]: Its data-analysis workflow includes generated charts and report artifacts. Sources: open-webui:open-webui:terminal. - office_file_output — Can it create Word, Excel or PowerPoint files? [partial]: The runtime can process Office files and create downloadable files through code and installed packages. Editable DOCX/XLSX/PPTX output was not verified with the shared fixture. Sources: open-webui:open-webui:terminal. - canvas_editing — Is there a document or canvas editor for iterating on output? [supported]: Notes offers a rich text and Markdown editor with AI rewrites. Sources: open-webui:open-webui:notes. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: open-webui:open-webui:terminal, open-webui:open-webui:notes ### 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. #### Glean Verification status: Agent cross-checked (agent-cross-checked) Support: partial Viewer chat sharing documents recipient-source redaction; current Projects and group-chat plan entitlements remain unknown. Availability: beta Delivery: native Scope: surfaces=Glean Hosted web Assistant and Agents; version=Public documentation retrieved 2026-10-21; deployed version not observed; plan=Core Suite Assistant Viewer sharing; current Projects and Team-chat Editor entitlement under Core Suite/Enterprise Flex unverified; add_ons=none stated; deployment_mode=dedicated-instance; region=Selected hosting and model-provider regions; no blanket EU or Swiss processing claim; os=not specified. Limitations: - Viewer redaction must not be generalized to Team-chat Editors. Projects and Team-chat commercial/rollout entitlements remain unknown; no two-user fixture was run. - share_chats — Can chats be shared inside the organisation? [supported]: Users can share chats with users, departments or the organization, with Viewer read-only access. Sources: glean:glean:sharing, glean:glean:r2-core-entitlements. - team_spaces — Are shared projects or workspaces available? [unknown]: The Projects guide describes gradual enablement but does not establish a current named Core Suite/Enterprise Flex entitlement. Shared-project availability remains unknown. - group_chat — Can several people chat together with the AI? [unknown]: The Team chat guide describes a beta enabled for selected users, but its current Core Suite/Enterprise Flex entitlement was not established. Multi-user AI chat availability for a named plan remains unknown. - share_permission_boundary — Does sharing respect the recipient's access to sources? [partial]: For Viewer chat sharing, the guide documents redaction of inaccessible citations and content. That finding does not establish the distinct Team-chat Editor entitlement or its availability for a Core Suite/Enterprise Flex tenant. No cross-group sharing test was run. Sources: glean:glean:sharing, glean:glean:r2-core-entitlements. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: glean:glean:sharing, glean:glean:r2-core-entitlements, glean:glean:projects, glean:glean:team-chat #### Open WebUI Verification status: Agent cross-checked (agent-cross-checked) Support: partial Chats, shared resources and multi-person channels are documented. Recipient source-access boundaries were not tested. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected code pinned to v0.12.3 / 91ea4e3421d1d8069f13d4a463fcb5986d94ea60; plan=Standard self-hosted with original branding intact; Enterprise only where explicitly stated; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure country; external inference, extraction, search and support locations require separate configuration and contracts; os=not specified. Limitations: - team_spaces: Groups organize shared models/knowledge and channels organize collaboration. This is not evidence of separate legal-entity tenancy. - share_permission_boundary: Does sharing respect the recipient's access to sources? No colleague-in-another-group chat-sharing fixture was run; transcript sharing may reveal already included content independently of original source access. - share_chats — Can chats be shared inside the organisation? [supported]: Chat sharing is a configurable permission and users can manage shared chats. Sources: open-webui:open-webui:permissions, open-webui:open-webui:export. - team_spaces — Are shared projects or workspaces available? [partial]: Groups organize shared models/knowledge and channels organize collaboration. This is not evidence of separate legal-entity tenancy. Sources: open-webui:open-webui:groups, open-webui:open-webui:channels. - group_chat — Can several people chat together with the AI? [supported]: Channels support multiple members and AI participation. Sources: open-webui:open-webui:channels. - share_permission_boundary — Does sharing respect the recipient's access to sources? [unknown]: share_permission_boundary: Does sharing respect the recipient's access to sources? No colleague-in-another-group chat-sharing fixture was run; transcript sharing may reveal already included content independently of original source access. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: open-webui:open-webui:permissions, open-webui:open-webui:export, open-webui:open-webui:groups, open-webui:open-webui:channels ### 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. #### Glean Verification status: Agent cross-checked (agent-cross-checked) Support: partial German, French, Italian and English end-user UIs are documented; admin setup is not localized. Availability: generally-available Delivery: native Scope: surfaces=Glean Hosted web Assistant and Agents; version=Public documentation retrieved 2026-10-21; deployed version not observed; plan=Core Suite client surfaces; detailed language/localization entitlements not separately mapped by plan; add_ons=none stated; deployment_mode=dedicated-instance; region=Selected hosting and model-provider regions; no blanket EU or Swiss processing claim; os=not specified. Limitations: - Documented findings only; unestablished atomic questions remain explicit gaps. - The language/accessibility pages describe the common product, without a separate Core Suite/Enterprise Flex localization entitlement matrix. - ui_languages — Which UI languages are offered? [supported]: The support matrix lists English, German, French and Italian UI among other locales. Sources: glean:glean:language, glean:glean:r2-core-entitlements. - dach_language_quality — Are German, French and Italian UIs complete and natural? [unknown]: Are German, French and Italian UIs complete and natural? The locale matrix and accessibility statement were checked, but translation completeness and naturalness were not observed in a logged-in German/French/Italian UI. - accessibility_statement — Is there a WCAG conformance statement? [partial]: Glean maintains a VPAT 2.5 ACR covering WCAG 2.0/2.1/2.2 A and AA, obtainable through the Trust Center; the report was not reviewed. Sources: glean:glean:accessibility, glean:glean:r2-core-entitlements. - admin_ui_languages — Is the admin interface available in German? [unsupported]: The language guide explicitly says external help documentation and admin workspace setup are not yet localized. Sources: glean:glean:language, glean:glean:r2-core-entitlements. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: glean:glean:language, glean:glean:r2-core-entitlements, glean:glean:accessibility #### Open WebUI Verification status: Agent cross-checked (agent-cross-checked) Support: partial English, German, French and Italian locales are present in the pinned client. Completeness, naturalness and WCAG conformance are unknown. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=New extension/locale findings inspected at v0.12.4 / 33c1978d5bad52a31df75ea55143025dfad18d16; earlier accepted documented facts retained; plan=Standard self-hosted with original branding intact; Enterprise only where explicitly stated; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure country; external inference, extraction, search and support locations require separate configuration and contracts; os=not specified. Limitations: - dach_language_quality: Are German, French and Italian UIs complete and natural? Locale registration is not a UI-quality test. No full German admin-screen walkthrough or WCAG conformance report was reviewed; broader i18n and accessibility remain roadmap topics. - accessibility_statement: Is there a WCAG conformance statement? Locale registration is not a UI-quality test. No full German admin-screen walkthrough or WCAG conformance report was reviewed; broader i18n and accessibility remain roadmap topics. - admin_ui_languages: Is the admin interface available in German? Locale registration is not a UI-quality test. No full German admin-screen walkthrough or WCAG conformance report was reviewed; broader i18n and accessibility remain roadmap topics. - ui_languages — Which UI languages are offered? [supported]: The locale registry includes en-US/en-GB, de-DE, fr-FR and it-IT among other languages. Sources: open-webui:open-webui: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? Locale registration is not a UI-quality test. No full German admin-screen walkthrough or WCAG conformance report was reviewed; broader i18n and accessibility remain roadmap topics. - accessibility_statement — Is there a WCAG conformance statement? [unknown]: accessibility_statement: Is there a WCAG conformance statement? Locale registration is not a UI-quality test. No full German admin-screen walkthrough or WCAG conformance report was reviewed; broader i18n and accessibility remain roadmap topics. - admin_ui_languages — Is the admin interface available in German? [partial]: The pinned German locale includes Admin Panel, user-management and settings labels. Full admin-screen translation coverage and naturalness were not observed; the public roadmap still lists full internationalization as planned. Sources: open-webui:open-webui:r4-german-admin-translations. Checked 2026-10-26; agent cross-checked 2026-10-26; check again by 2026-12-25. Sources: open-webui:open-webui:i18n-pin, open-webui:open-webui:r4-german-admin-translations ## 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. #### Glean Verification status: Agent cross-checked (agent-cross-checked) Support: partial SSO is mandatory with OIDC/SAML and identity-provider MFA and conditional access. Availability: generally-available Delivery: native Scope: surfaces=Glean Hosted web Assistant and Agents; version=Public documentation retrieved 2026-10-21; deployed version not observed; plan=Core Suite Protect includes SSO and role access; detailed IdP policy setup is separately documented; add_ons=none stated; deployment_mode=dedicated-instance; region=Selected hosting and model-provider regions; no blanket EU or Swiss processing claim; os=not specified. Limitations: - No SSO trial login was performed. - sso_protocols — Which SSO protocols and identity providers work? [supported]: OIDC and SAML work with Entra ID, Google, Okta, OneLogin and generic SAML providers as documented. Sources: glean:glean:sso, glean:glean:r2-core-entitlements. - sso_plan — Which plan includes SSO? [partial]: SSO is mandatory during deployment setup; no separate SSO price or plan gate is given in this guide. Sources: glean:glean:sso, glean:glean:r2-core-entitlements. - mfa — Can MFA be enforced? [supported]: Glean recommends enforcing MFA through the configured identity provider. Sources: glean:glean:sso, glean:glean:r2-core-entitlements. - conditional_access — Do Entra conditional-access policies apply? [supported]: Glean recommends appropriately secure IdP conditional-access policies; mobile documents Intune-compatible sign-in. Sources: glean:glean:sso, glean:glean:mobile, glean:glean:r2-core-entitlements. - domain_capture — Can the company claim its email domain? [partial]: Glean checks the user email domain against the expected customer domain before issuing a login cookie; broader domain-capture/migration semantics were not established. Sources: glean:glean:sso, glean:glean:r2-core-entitlements. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: glean:glean:sso, glean:glean:r2-core-entitlements, glean:glean:mobile #### Open WebUI Verification status: Agent cross-checked (agent-cross-checked) Support: partial OAuth/OIDC, trusted-header and directory authentication are documented; standard self-hosting includes configuration access. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected code pinned to v0.12.3 / 91ea4e3421d1d8069f13d4a463fcb5986d94ea60; plan=Standard self-hosted with original branding intact; Enterprise only where explicitly stated; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure country; external inference, extraction, search and support locations require separate configuration and contracts; os=not specified. Limitations: - conditional_access: The privacy guide recommends enforcing MFA, conditional access and device posture at the identity provider. No Entra sign-in fixture was run. - domain_capture: Can the company claim its email domain? Email-domain filtering settings do not establish enterprise domain ownership capture; this was not verified. - sso_protocols — Which SSO protocols and identity providers work? [supported]: OAuth/OIDC includes Microsoft, Google and generic providers; trusted-header proxies and LDAP are documented. Direct SAML was not established. Sources: open-webui:open-webui:sso, open-webui:open-webui:roles. - sso_plan — Which plan includes SSO? [supported]: The public self-hosted authentication configuration is available under standard use, with no separately listed SSO charge. Sources: open-webui:open-webui:sso, open-webui:open-webui:enterprise. - mfa — Can MFA be enforced? [supported]: Admins can enable built-in authenticator-based MFA and choose whether OAuth may bypass it. Sources: open-webui:open-webui:mfa. - conditional_access — Do Entra conditional-access policies apply? [partial]: The privacy guide recommends enforcing MFA, conditional access and device posture at the identity provider. No Entra sign-in fixture was run. Sources: open-webui:open-webui:privacy. - domain_capture — Can the company claim its email domain? [unknown]: domain_capture: Can the company claim its email domain? Email-domain filtering settings do not establish enterprise domain ownership capture; this was not verified. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: open-webui:open-webui:sso, open-webui:open-webui:roles, open-webui:open-webui:enterprise, open-webui:open-webui:mfa, open-webui:open-webui:privacy ### 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. #### Glean 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. #### Open WebUI Verification status: Agent cross-checked (agent-cross-checked) Support: partial SCIM and login-time identity groups are documented; content ownership after removing a user needs further verification. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=SCIM bearer-token authentication rechecked at v0.12.4 / 33c1978d5bad52a31df75ea55143025dfad18d16 and current guide on 2026-10-26; other accepted identity facts retain their own cited versions; plan=Standard self-hosted with original branding intact; Enterprise only where explicitly stated; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure country; external inference, extraction, search and support locations require separate configuration and contracts; os=not specified. Limitations: - deprovisioning: SCIM active=false maps ordinary users to pending and disconnects live sessions. Asset transfer and retained shared content were not fixture-tested. - seat_assignment: Administrators control user accounts and roles. Standard use has no paid per-seat licence assignment mechanism to price; Enterprise entitlements were not reviewed. - No user-selectable token-scope control was established from the current SCIM guide or pinned authentication path. - scim — Is SCIM provisioning supported? [supported]: SCIM 2.0 provisions/deactivates users and manages groups when enabled through SCIM_ENABLED and authenticated with the configured SCIM_TOKEN bearer token. The documented configuration does not expose user-selectable token scopes. Sources: open-webui:open-webui:r7-scim-bearer-doc, open-webui:open-webui:r7-scim-bearer-code. - group_sync — Are identity-provider groups synced? [supported]: OAuth group management syncs claims at sign-in; SCIM also manages memberships. Sources: open-webui:open-webui:sso, open-webui:open-webui:scim. - jit_provisioning — Are users created at first login? [supported]: OAuth account creation and optional JIT group creation can be enabled. Sources: open-webui:open-webui:sso. - deprovisioning — What happens to a removed user's data and shared assets? [partial]: SCIM active=false maps ordinary users to pending and disconnects live sessions. Asset transfer and retained shared content were not fixture-tested. Sources: open-webui:open-webui:scim. - seat_assignment — Can admins assign and reclaim seats? [partial]: Administrators control user accounts and roles. Standard use has no paid per-seat licence assignment mechanism to price; Enterprise entitlements were not reviewed. Sources: open-webui:open-webui:roles, open-webui:open-webui:enterprise. Checked 2026-10-26; agent cross-checked 2026-10-26; check again by 2026-12-25. Sources: open-webui:open-webui:scim, open-webui:open-webui:sso, open-webui:open-webui:roles, open-webui:open-webui:enterprise, open-webui:open-webui:r7-scim-bearer-doc, open-webui:open-webui:r7-scim-bearer-code ### 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. #### Glean Verification status: Agent cross-checked (agent-cross-checked) Support: partial Glean has delegated admin roles, IdP-group permissions and feature access controls. Availability: generally-available Delivery: native Scope: surfaces=Glean Hosted web Assistant and Agents; version=Public documentation retrieved 2026-10-21; deployed version not observed; plan=Core Suite Protect/Agent Governance role controls; department and IdP group policy configuration as documented; add_ons=none stated; deployment_mode=dedicated-instance; region=Selected hosting and model-provider regions; no blanket EU or Swiss processing claim; os=not specified. Limitations: - No two-group restriction-enforcement test. - admin_roles — Which admin roles exist, and can admin rights be delegated? [supported]: Setup Admin, Admin, Super Admin and specialist moderators have documented scopes; only Super Admin can assign certain privileges. Sources: glean:glean:roles, glean:glean:r2-core-entitlements. - groups — Can permissions be set per group? [supported]: Direct and IdP-group roles combine, with highest-precedence primary roles and union of secondary roles. Group permission behavior is feature-flag dependent. Sources: glean:glean:groups, glean:glean:r2-core-entitlements. - feature_toggles — Which features can be switched on or off per group? [partial]: Member permissions include content and agent creation; model access, scheduled triggers and beta features have specific controls. Every feature/group combination was not verified. Sources: glean:glean:users, glean:glean:groups, glean:glean:r2-core-entitlements. - multi_entity — Can subsidiaries or departments be separated within one contract? [partial]: Terms permit affiliates to use or order the service, while separate subsidiary data partitions within one contract were not established. Sources: glean:glean:terms, glean:glean:r2-core-entitlements. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: glean:glean:roles, glean:glean:r2-core-entitlements, glean:glean:groups, glean:glean:users, glean:glean:terms #### Open WebUI Verification status: Agent cross-checked (agent-cross-checked) Support: partial Roles and additive groups provide feature and resource permissions; separate instances remain the documented stronger trust boundary. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected code pinned to v0.12.3 / 91ea4e3421d1d8069f13d4a463fcb5986d94ea60; plan=Standard self-hosted with original branding intact; Enterprise only where explicitly stated; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure country; external inference, extraction, search and support locations require separate configuration and contracts; os=not specified. Limitations: - admin_roles: Admin, User and Pending are system roles. Admin access can be reduced by product flags, but a least-privilege delegated-admin role matrix was not established. - multi_entity: Groups can organize departments; the privacy guide recommends separate instances/databases/operators for distinct trust boundaries. A multi-entity commercial contract was not reviewed. - admin_roles — Which admin roles exist, and can admin rights be delegated? [partial]: Admin, User and Pending are system roles. Admin access can be reduced by product flags, but a least-privilege delegated-admin role matrix was not established. Sources: open-webui:open-webui:roles. - groups — Can permissions be set per group? [supported]: User/group resource grants and additive feature permissions are documented. Sources: open-webui:open-webui:groups. - feature_toggles — Which features can be switched on or off per group? [supported]: Permissions cover web search, images, files, model creation, tools, knowledge, memories and other features. Sources: open-webui:open-webui:permissions. - multi_entity — Can subsidiaries or departments be separated within one contract? [partial]: Groups can organize departments; the privacy guide recommends separate instances/databases/operators for distinct trust boundaries. A multi-entity commercial contract was not reviewed. Sources: open-webui:open-webui:groups, open-webui:open-webui:privacy. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: open-webui:open-webui:roles, open-webui:open-webui:groups, open-webui:open-webui:permissions, open-webui:open-webui:privacy ### 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. #### Glean Verification status: Agent cross-checked (agent-cross-checked) Support: partial Insights provides adoption and individual activity reporting with CSV export. Availability: generally-available Delivery: native Scope: surfaces=Glean Hosted web Assistant and Agents; version=Public documentation retrieved 2026-10-21; deployed version not observed; plan=Core Suite Billing & Insights included in seat; Enterprise Flex Admin console/Insights platform separate from usage rates; add_ons=none stated; deployment_mode=dedicated-instance; region=Selected hosting and model-provider regions; no blanket EU or Swiss processing claim; os=not specified. Limitations: - Documented findings only; unestablished atomic questions remain explicit gaps. - adoption_dashboard — Is there an adoption dashboard? [supported]: Insights includes daily, weekly and monthly active users and adoption metrics. Sources: glean:glean:insights, glean:glean:r2-core-entitlements. - breakdowns — Can usage be broken down by group, model, feature and assistant? [partial]: Department filters and per-person Assistant, search, agent and MCP activity are documented. Model usage is a separate dashboard; a unified breakdown by every requested dimension was not verified. Sources: glean:glean:insights, glean:glean:core-price, glean:glean:r2-core-entitlements. - export — Can usage data be exported? [supported]: The All signed up users table exports CSV; customer event delivery supports downstream analysis. Sources: glean:glean:insights, glean:glean:events, glean:glean:r2-core-entitlements. - privacy_modes — Can per-person reporting be limited or pseudonymised? [partial]: Departments under five users are grouped. The same guide documents named user activity; an organization-wide pseudonymous mode was not established. Sources: glean:glean:insights, glean:glean:r2-core-entitlements. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: glean:glean:insights, glean:glean:r2-core-entitlements, glean:glean:core-price, glean:glean:events #### Open WebUI Verification status: Agent cross-checked (agent-cross-checked) Support: partial Admin analytics provides user/model/group activity and token reports, with API export. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected code pinned to v0.12.3 / 91ea4e3421d1d8069f13d4a463fcb5986d94ea60; plan=Standard self-hosted with original branding intact; Enterprise only where explicitly stated; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure country; external inference, extraction, search and support locations require separate configuration and contracts; os=not specified. Limitations: - breakdowns: User, model and group views are documented. Complete feature/assistant breakdowns were not established. - privacy_modes: Admins can disable analytics and product-level chat access. Pseudonymized reporting was not established; the default user table identifies users. - adoption_dashboard — Is there an adoption dashboard? [supported]: The dashboard reports messages, chats, token usage and user activity by date range. Sources: open-webui:open-webui:analytics. - breakdowns — Can usage be broken down by group, model, feature and assistant? [partial]: User, model and group views are documented. Complete feature/assistant breakdowns were not established. Sources: open-webui:open-webui:analytics. - export — Can usage data be exported? [supported]: Analytics API endpoints can be exported into JSON or external BI tooling. Sources: open-webui:open-webui:analytics. - privacy_modes — Can per-person reporting be limited or pseudonymised? [partial]: Admins can disable analytics and product-level chat access. Pseudonymized reporting was not established; the default user table identifies users. Sources: open-webui:open-webui:analytics, open-webui:open-webui:privacy. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: open-webui:open-webui:analytics, open-webui:open-webui:privacy ### 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. #### Glean Verification status: Agent cross-checked (agent-cross-checked) Support: partial Usage limits can alert or block; team limits are per-member defaults rather than pooled team budgets. Availability: generally-available Delivery: native Scope: surfaces=Glean Hosted web Assistant and Agents; version=Public documentation retrieved 2026-10-21; deployed version not observed; plan=Core Suite / Enterprise Flex; legacy Enterprise exclusions stated; add_ons=none stated; deployment_mode=dedicated-instance; region=Selected hosting and model-provider regions; no blanket EU or Swiss processing claim; os=not specified. Limitations: - Documented findings only; unestablished atomic questions remain explicit gaps. - cost_visibility — Can admins see cost or consumption per user and group? [supported]: Usage dashboards expose user/team/agent consumption in dollars or FlexCredits depending on plan. Sources: glean:glean:limits. - budgets — Can budgets be set per user or group? [supported]: Organization, user, department/IdP-group and agent monthly limits are documented for Core Suite/Enterprise Flex; legacy Enterprise lacks user/agent limits. Sources: glean:glean:limits. - budget_enforcement — Does reaching a budget alert, block or downgrade? [supported]: An optional block stops later billable requests after the running action completes. Alert-only is also available; some overage can occur. Sources: glean:glean:limits. - chargeback — Can costs be exported per cost centre? [unknown]: Can costs be exported per cost centre? The usage-limit and pricing guides were checked; cost-center chargeback export and cost allocation outside current department/group metadata were not established. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: glean:glean:limits #### Open WebUI Verification status: Agent cross-checked (agent-cross-checked) Support: partial Token usage supports cost estimation; enforced monetary budgets and cost-centre exports remain unverified. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected code pinned to v0.12.3 / 91ea4e3421d1d8069f13d4a463fcb5986d94ea60; plan=Standard self-hosted with original branding intact; Enterprise only where explicitly stated; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure country; external inference, extraction, search and support locations require separate configuration and contracts; os=not specified. Limitations: - cost_visibility: Analytics exposes provider-reported input/output tokens by user/model/group; billed currency requires multiplying by external provider prices. - budgets: Can budgets be set per user or group? The analytics and roadmap sources were checked. Numeric user/group budgets, block/downgrade behavior and cost-centre chargeback exports were not established; a low-budget test was not run. - budget_enforcement: Does reaching a budget alert, block or downgrade? The analytics and roadmap sources were checked. Numeric user/group budgets, block/downgrade behavior and cost-centre chargeback exports were not established; a low-budget test was not run. - chargeback: Can costs be exported per cost centre? The analytics and roadmap sources were checked. Numeric user/group budgets, block/downgrade behavior and cost-centre chargeback exports were not established; a low-budget test was not run. - cost_visibility — Can admins see cost or consumption per user and group? [partial]: Analytics exposes provider-reported input/output tokens by user/model/group; billed currency requires multiplying by external provider prices. Sources: open-webui:open-webui:analytics. - budgets — Can budgets be set per user or group? [unknown]: budgets: Can budgets be set per user or group? The analytics and roadmap sources were checked. Numeric user/group budgets, block/downgrade behavior and cost-centre chargeback exports were not established; a low-budget test was not run. - budget_enforcement — Does reaching a budget alert, block or downgrade? [unknown]: budget_enforcement: Does reaching a budget alert, block or downgrade? The analytics and roadmap sources were checked. Numeric user/group budgets, block/downgrade behavior and cost-centre chargeback exports were not established; a low-budget test was not run. - chargeback — Can costs be exported per cost centre? [unknown]: chargeback: Can costs be exported per cost centre? The analytics and roadmap sources were checked. Numeric user/group budgets, block/downgrade behavior and cost-centre chargeback exports were not established; a low-budget test was not run. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: open-webui:open-webui:analytics ### 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. #### Glean Verification status: Agent cross-checked (agent-cross-checked) Support: partial Administrative change logs have documented CSV export and retention. Prompt/response compliance logging remains unknown because source scopes conflict. Availability: generally-available Delivery: native Scope: surfaces=Glean Hosted web Assistant and Agents; version=Public documentation retrieved 2026-10-21; deployed version not observed; plan=Core Suite Protect administrative audit logs; no verified prompt/response compliance-logging finding; add_ons=none stated; deployment_mode=dedicated-instance; region=Selected hosting and model-provider regions; no blanket EU or Swiss processing claim; os=not specified. Limitations: - Only administrative/configuration events, their export and their stated retention are positive findings. Content logging, its compliance integrity model, eDiscovery and legal hold remain unverified. - admin_events — Are admin and security events logged? [supported]: Admin Audit Logs record configuration changes by admins and Glean support, excluding end-user events. Default retention is 30 days. Sources: glean:glean:audit, glean:glean:r2-core-entitlements. - content_logging — Can prompts and answers be retained for compliance, and is it configurable? [unknown]: Prompt/response retention and its configuration remain unknown. The deployment comparison says individual queries/responses are not logged, while Customer Event documentation describes CHAT response content and the history guide separates that logging from history. Their deployment/system scopes were not reconciled. - siem_export — Can logs stream to a SIEM or be exported? [partial]: The administrative audit-log guide documents self-serve CSV export. For Glean-hosted deployments, ongoing delivery of administrative logs can be configured by the account team and is not enabled by default or self-serve. This finding makes no prompt/response or Customer Event export guarantee. Sources: glean:glean:audit, glean:glean:r2-core-entitlements. - ediscovery — Are eDiscovery and legal hold supported? [unknown]: Are eDiscovery and legal hold supported? Administrative and Customer Event documentation was checked. eDiscovery/legal-hold behavior, integrity guarantees and per-destination content-log retention were not established. - log_retention — How long are logs kept? [partial]: Administrative audit logs have a documented 30-day default; extended periods require arrangement. Customer Event/content-log retention is unknown and no common retention term for all logs is inferred. Sources: glean:glean:audit, glean:glean:r2-core-entitlements. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: glean:glean:audit, glean:glean:r2-core-entitlements, glean:glean:deploy, glean:glean:events, glean:glean:history #### Open WebUI Verification status: Agent cross-checked (agent-cross-checked) Support: partial Optional request logging can capture metadata or content and stream to operator log infrastructure. It is not a verified immutable compliance archive. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected code pinned to v0.12.3 / 91ea4e3421d1d8069f13d4a463fcb5986d94ea60; plan=Standard self-hosted with original branding intact; Enterprise only where explicitly stated; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure country; external inference, extraction, search and support locations require separate configuration and contracts; os=not specified. Limitations: - ediscovery: Are eDiscovery and legal hold supported? No eDiscovery/legal-hold contract or immutable retention/integrity model was verified. - log_retention: File rotation is configurable and operators own log storage and retention. No universal retention period or tamper-evident archive was established. - admin_events — Are admin and security events logged? [supported]: Configured request logging can include authentication and administrative API paths. Sources: open-webui:open-webui:hardening. - content_logging — Can prompts and answers be retained for compliance, and is it configurable? [supported]: REQUEST and REQUEST_RESPONSE levels add bodies, subject to path exclusions and a body-size cap; metadata-only capture is also available. Sources: open-webui:open-webui:hardening. - siem_export — Can logs stream to a SIEM or be exported? [supported]: File or stdout output can feed an operator-managed log collector. Sources: open-webui:open-webui:hardening. - ediscovery — Are eDiscovery and legal hold supported? [unknown]: ediscovery: Are eDiscovery and legal hold supported? No eDiscovery/legal-hold contract or immutable retention/integrity model was verified. - log_retention — How long are logs kept? [partial]: File rotation is configurable and operators own log storage and retention. No universal retention period or tamper-evident archive was established. Sources: open-webui:open-webui:hardening, open-webui:open-webui:security. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: open-webui:open-webui:hardening, open-webui:open-webui:security ### 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. #### Glean Verification status: Agent cross-checked (agent-cross-checked) Support: partial Protect+ can flag or block configured sensitive patterns in prompts; file coverage and Swiss-fixture outcomes are unknown. Availability: generally-available Delivery: native Scope: surfaces=Glean Hosted web Assistant and Agents; version=Public documentation retrieved 2026-10-21; deployed version not observed; plan=Enterprise Flex + Protect+ site-wide annual add-on; basic Core Suite CSV protection is a different mechanism; add_ons=Glean Protect+ AI security; deployment_mode=dedicated-instance; region=Selected hosting and model-provider regions; no blanket EU or Swiss processing claim; os=not specified. Limitations: - Prompt-only pattern policy is not evidence that file contents are filtered before every model call. No personal-data fixture was run. - pii_detection — Is personal data detected in prompts and files? [partial]: Prompt-only regex policy covers configured PII, credentials, IBAN and government-ID patterns. Templates start disabled; this policy excludes retrieved data and generated responses. Sources: glean:glean:pii, glean:glean:r2-core-entitlements, glean:glean:r2-flex-entitlements. - pii_action — Is it redacted, masked, blocked or only warned? [supported]: Admins choose monitoring with findings or immediate blocking of the run; the guide does not promise automatic redaction for this policy. Sources: glean:glean:pii, glean:glean:r2-core-entitlements, glean:glean:r2-flex-entitlements. - custom_patterns — Can admins add custom patterns or terms? [supported]: Admins can define RE2 pattern groups and test patterns before enabling them. Sources: glean:glean:pii, glean:glean:r2-core-entitlements, glean:glean:r2-flex-entitlements. - dlp_integration — Does it integrate with an existing DLP product? [partial]: Protect+ documents AI security integrations including Palo Alto Networks in the product/security material. Purview/Netskope integration and exact enterprise entitlement were not verified. Sources: glean:glean:protect, glean:glean:subprocessors, glean:glean:r2-core-entitlements, glean:glean:r2-flex-entitlements. - filter_location — Where does filtering run? [unknown]: Where does filtering run? Protect+ and prompt-policy guides were checked. Filtering location, upload scanning by this policy and Swiss AHV/IBAN behavior were not observed. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: glean:glean:pii, glean:glean:r2-core-entitlements, glean:glean:r2-flex-entitlements, glean:glean:protect, glean:glean:subprocessors #### Open WebUI Verification status: Agent cross-checked (agent-cross-checked) Support: partial Custom request filters provide an extension point for PII policies; a configured detection/redaction product and Swiss fixture result were not established. Availability: generally-available Delivery: manual-workaround Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected code pinned to v0.12.3 / 91ea4e3421d1d8069f13d4a463fcb5986d94ea60; plan=Standard self-hosted with original branding intact; Enterprise only where explicitly stated; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure country; external inference, extraction, search and support locations require separate configuration and contracts; os=not specified. Limitations: - pii_detection: Is personal data detected in prompts and files? The filter framework was reviewed, not a configured PII/DLP deployment. No AHV/IBAN/file fixture, Purview/Netskope connector or default detection coverage was verified. - pii_action: An installed custom Python filter can modify or reject requests before model processing. No built-in AHV/IBAN policy is claimed. - custom_patterns: Custom filter code can implement customer rules; ready-made managed pattern libraries were not verified. - dlp_integration: Does it integrate with an existing DLP product? The filter framework was reviewed, not a configured PII/DLP deployment. No AHV/IBAN/file fixture, Purview/Netskope connector or default detection coverage was verified. - pii_detection — Is personal data detected in prompts and files? [unknown]: pii_detection: Is personal data detected in prompts and files? The filter framework was reviewed, not a configured PII/DLP deployment. No AHV/IBAN/file fixture, Purview/Netskope connector or default detection coverage was verified. - pii_action — Is it redacted, masked, blocked or only warned? [partial]: An installed custom Python filter can modify or reject requests before model processing. No built-in AHV/IBAN policy is claimed. Sources: open-webui:open-webui:filter. - custom_patterns — Can admins add custom patterns or terms? [partial]: Custom filter code can implement customer rules; ready-made managed pattern libraries were not verified. Sources: open-webui:open-webui:filter. - dlp_integration — Does it integrate with an existing DLP product? [unknown]: dlp_integration: Does it integrate with an existing DLP product? The filter framework was reviewed, not a configured PII/DLP deployment. No AHV/IBAN/file fixture, Purview/Netskope connector or default detection coverage was verified. - filter_location — Where does filtering run? [supported]: Python filters execute in the customer-operated backend unless their implementation calls an external service. Sources: open-webui:open-webui:filter. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: open-webui:open-webui:filter ### 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. #### Glean Verification status: Agent cross-checked (agent-cross-checked) Support: partial Enterprise instructions and configurable AI security policies are documented. Availability: generally-available Delivery: native Scope: surfaces=Glean Hosted web Assistant and Agents; version=Public documentation retrieved 2026-10-21; deployed version not observed; plan=Enterprise Flex Assistant instructions; Protect+ site-wide annual add-on for security monitoring/blocking; add_ons=Protect+ for AI security findings; not required for basic custom instructions; deployment_mode=dedicated-instance; region=Selected hosting and model-provider regions; no blanket EU or Swiss processing claim; os=not specified. Limitations: - Model-followed instructions are distinct from policy enforcement. - org_instructions — Can admins set organisation-wide instructions? [supported]: Admins can configure up to five enterprise custom instructions for Assistant. Sources: glean:glean:org-instructions, glean:glean:r2-core-entitlements, glean:glean:r2-flex-entitlements. - usage_notice — Can users be required to accept a usage policy? [unknown]: Can users be required to accept a usage policy? The custom-instruction and AI security guides were checked; a mandatory acceptable-use acknowledgement flow was not established. - content_filters — Are content filters configurable? [supported]: Protect+ policies can monitor/block configured sensitive prompts and restrict topics; enforcement depends on enabled policy. Sources: glean:glean:pii, glean:glean:protect, glean:glean:r2-core-entitlements, glean:glean:r2-flex-entitlements. - violation_reporting — Are policy hits visible to admins? [supported]: Monitoring creates admin findings with matched patterns, snippets and conversation links. Sources: glean:glean:pii, glean:glean:r2-core-entitlements, glean:glean:r2-flex-entitlements. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: glean:glean:org-instructions, glean:glean:r2-core-entitlements, glean:glean:r2-flex-entitlements, glean:glean:pii, glean:glean:protect #### Open WebUI Verification status: Agent cross-checked (agent-cross-checked) Support: partial Model defaults, prompts, banners and custom filters can express policy. Recorded acceptance and violation reporting remain unknown. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected code pinned to v0.12.3 / 91ea4e3421d1d8069f13d4a463fcb5986d94ea60; plan=Standard self-hosted with original branding intact; Enterprise only where explicitly stated; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure country; external inference, extraction, search and support locations require separate configuration and contracts; os=not specified. Limitations: - org_instructions: Admins can configure model/default system prompts; sources explicitly warn that instructions do not guarantee model behavior. - usage_notice: Banners can display policy text, but a required recorded acknowledgement was not established. - content_filters: Operators can install custom request/response filters. Actual policy enforcement depends on that code and configuration. - violation_reporting: Are policy hits visible to admins? The models, banner and filter guides did not establish an organization-wide violation dashboard or mandatory acceptable-use acknowledgement. - org_instructions — Can admins set organisation-wide instructions? [partial]: Admins can configure model/default system prompts; sources explicitly warn that instructions do not guarantee model behavior. Sources: open-webui:open-webui:models, open-webui:open-webui:env. - usage_notice — Can users be required to accept a usage policy? [partial]: Banners can display policy text, but a required recorded acknowledgement was not established. Sources: open-webui:open-webui:banners. - content_filters — Are content filters configurable? [partial]: Operators can install custom request/response filters. Actual policy enforcement depends on that code and configuration. Sources: open-webui:open-webui:filter. - violation_reporting — Are policy hits visible to admins? [unknown]: violation_reporting: Are policy hits visible to admins? The models, banner and filter guides did not establish an organization-wide violation dashboard or mandatory acceptable-use acknowledgement. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: open-webui:open-webui:models, open-webui:open-webui:env, open-webui:open-webui:banners, open-webui:open-webui:filter ## 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. #### Glean Verification status: Agent cross-checked (agent-cross-checked) Support: partial Hosting is region-selectable, but storage, model processing and remote support must be scoped separately. Availability: generally-available Delivery: native Scope: surfaces=Glean Hosted web Assistant and Agents, Customer Hosted managed GCP or AWS tenant; version=Public documentation retrieved 2026-10-21; deployed version not observed; plan=Core Suite Glean Hosted regional single-tenant hosting included; Customer Hosted and provider regions remain contract/key choices; add_ons=none stated; deployment_mode=not specified; region=Selected hosting and model-provider regions; no blanket EU or Swiss processing claim; os=not specified. Limitations: - Documented findings only; unestablished atomic questions remain explicit gaps. - storage_region — Where are chats, files and indexes stored? [partial]: Tenant storage and index follow the selected isolated GCP/AWS deployment; the public GCP list includes Netherlands, Belgium and Frankfurt. Actual contracted country was not selected. Sources: glean:glean:deploy, glean:glean:regions, glean:glean:r2-core-entitlements. - inference_region — Where do model calls run, per provider? [partial]: Model routes depend on cloud and key mode; GCP/AWS Customer Key has cross-cloud restrictions. The subprocessor list allows customer-selected provider locations but does not establish every model remains in EU/CH. Sources: glean:glean:models, glean:glean:subprocessors, glean:glean:r2-core-entitlements. - backups_logs_region — Where are backups, logs and telemetry? [partial]: Deployment documentation lists backups up to seven days but no full country map for backups, telemetry and central services was established. Sources: glean:glean:deploy, glean:glean:r2-core-entitlements. - support_access_region — From where can vendor staff access data? [supported]: The subprocessor list names the Indian affiliate for remote support/security/debugging; the SLA names California and Bangalore support locations. Sources: glean:glean:subprocessors, glean:glean:sla, glean:glean:r2-core-entitlements. - swiss_hosting — Is Swiss hosting available? [unknown]: Is Swiss hosting available? Region and deployment pages were checked; Swiss hosting, exact backup/log/telemetry geography and all model-provider regional exceptions were not established. - residency_plan — Which plan or option provides residency? [partial]: Both vendor-hosted and customer-cloud modes offer region selection. Prices, thresholds and per-model regional conditions remain contractual. Sources: glean:glean:deploy, glean:glean:terms, glean:glean:r2-core-entitlements. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: glean:glean:deploy, glean:glean:regions, glean:glean:r2-core-entitlements, glean:glean:models, glean:glean:subprocessors, glean:glean:sla, glean:glean:terms #### Open WebUI Verification status: Agent cross-checked (agent-cross-checked) Support: partial The operator chooses data locations; external services can receive prompts or documents independently of where Open WebUI is hosted. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected code pinned to v0.12.3 / 91ea4e3421d1d8069f13d4a463fcb5986d94ea60; plan=Standard self-hosted with original branding intact; Enterprise only where explicitly stated; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure country; external inference, extraction, search and support locations require separate configuration and contracts; os=not specified. Limitations: - backups_logs_region: The operator controls backups and logging locations. A concrete installation and its telemetry/egress were not audited. - support_access_region: Operators and support recipients with host/database access can read data; there is no reviewed geographic enterprise support-access commitment. - swiss_hosting: An organization can deploy the self-hosted stack on Swiss infrastructure. This is not a bundled vendor-managed Swiss service or guaranteed Swiss inference. - storage_region — Where are chats, files and indexes stored? [supported]: Chats, files and indexes reside in configured customer storage/database locations. No vendor-chosen region applies to this self-hosted instance. Sources: open-webui:open-webui:privacy. - inference_region — Where do model calls run, per provider? [supported]: The selected provider endpoint runs inference; local, private or external endpoints must be scoped separately. Sources: open-webui:open-webui:provider, open-webui:open-webui:privacy. - backups_logs_region — Where are backups, logs and telemetry? [partial]: The operator controls backups and logging locations. A concrete installation and its telemetry/egress were not audited. Sources: open-webui:open-webui:privacy. - support_access_region — From where can vendor staff access data? [partial]: Operators and support recipients with host/database access can read data; there is no reviewed geographic enterprise support-access commitment. Sources: open-webui:open-webui:privacy. - swiss_hosting — Is Swiss hosting available? [partial]: An organization can deploy the self-hosted stack on Swiss infrastructure. This is not a bundled vendor-managed Swiss service or guaranteed Swiss inference. Sources: open-webui:open-webui:privacy, open-webui:open-webui:quickstart. - residency_plan — Which plan or option provides residency? [supported]: Self-hosting gives the operator infrastructure placement control under standard use; provider contracts and optional enterprise services are separate. Sources: open-webui:open-webui:privacy, open-webui:open-webui:enterprise. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: open-webui:open-webui:privacy, open-webui:open-webui:provider, open-webui:open-webui:quickstart, open-webui:open-webui:enterprise ### 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. #### Glean Verification status: Agent cross-checked (agent-cross-checked) Support: partial Glean documents dedicated vendor hosting and Glean-operated deployment in customer cloud accounts. Availability: generally-available Delivery: native Scope: surfaces=Glean Hosted web Assistant and Agents, Customer Hosted managed GCP or AWS tenant; version=Public documentation retrieved 2026-10-21; deployed version not observed; plan=Core Suite Glean Hosted single tenant; separately contracted Customer Hosted private-cloud configuration under Core Suite/Enterprise Flex; add_ons=none stated; deployment_mode=not specified; region=Selected hosting and model-provider regions; no blanket EU or Swiss processing claim; os=not specified. Limitations: - Documented findings only; unestablished atomic questions remain explicit gaps. - multi_tenant_saas — Is a shared SaaS offered? [unsupported]: Deployment documentation explicitly says Glean uses single-tenant infrastructure in both supported modes. This is not a shared tenant offer. Sources: glean:glean:deploy, glean:glean:r2-core-entitlements, glean:glean:r2-flex-entitlements. - dedicated_instance — Is a dedicated single-tenant instance offered, from what size? [supported]: Glean Hosted runs isolated customer infrastructure in Glean cloud accounts; the public guide gives no numerical seat threshold. Sources: glean:glean:deploy, glean:glean:r2-core-entitlements, glean:glean:r2-flex-entitlements. - customer_cloud — Can it run in the customer's own cloud account, from what size? [supported]: Customer Hosted, formerly Cloud-Prem, runs a Glean-managed tenant in customer GCP or AWS. Glean handles upgrades and keeps support access; seat/contract minimum is not published. Sources: glean:glean:deploy, glean:glean:r2-core-entitlements, glean:glean:r2-flex-entitlements. - 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? The deployment guide and terms describe supported cloud accounts, not a whole-platform on-premises or air-gapped entitlement. Numerical minimums for each mode were not found. - air_gapped — Can it run without internet access? [unknown]: Can it run without internet access? The deployment guide and terms describe supported cloud accounts, not a whole-platform on-premises or air-gapped entitlement. Numerical minimums for each mode were not found. - mode_feature_gaps — Which features are missing outside SaaS? [partial]: The guide describes the same product in both modes, but key/provider matrices document cloud and feature differences. Customer Hosted cannot be independently patched or re-architected by the customer. Sources: glean:glean:deploy, glean:glean:key-matrix, glean:glean:r2-core-entitlements, glean:glean:r2-flex-entitlements. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: glean:glean:deploy, glean:glean:r2-core-entitlements, glean:glean:r2-flex-entitlements, glean:glean:key-matrix #### Open WebUI Verification status: Agent cross-checked (agent-cross-checked) Support: partial Customer-operated cloud and on-premise installs are documented, with offline operation requiring all dependencies to be local. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected code pinned to v0.12.3 / 91ea4e3421d1d8069f13d4a463fcb5986d94ea60; plan=Standard self-hosted with original branding intact; Enterprise only where explicitly stated; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure country; external inference, extraction, search and support locations require separate configuration and contracts; os=not specified. Limitations: - multi_tenant_saas: Is a shared SaaS offered? A vendor-operated shared SaaS, dedicated managed instance and contractual minimum for managed service were not established in the enterprise and installation sources. - dedicated_instance: Is a dedicated single-tenant instance offered, from what size? A vendor-operated shared SaaS, dedicated managed instance and contractual minimum for managed service were not established in the enterprise and installation sources. - multi_tenant_saas — Is a shared SaaS offered? [unknown]: multi_tenant_saas: Is a shared SaaS offered? A vendor-operated shared SaaS, dedicated managed instance and contractual minimum for managed service were not established in the enterprise and installation sources. - 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 shared SaaS, dedicated managed instance and contractual minimum for managed service were not established in the enterprise and installation sources. - customer_cloud — Can it run in the customer's own cloud account, from what size? [supported]: Docker/Python installs can run in customer infrastructure; no standard-use seat minimum is stated. Sources: open-webui:open-webui:quickstart, open-webui:open-webui:enterprise. - on_premise — Can the whole platform run on customer infrastructure, from what size? [supported]: The complete application can run on customer servers with local inference/extraction services. Sources: open-webui:open-webui:quickstart, open-webui:open-webui:offline. - air_gapped — Can it run without internet access? [supported]: The offline guide describes preparing cached models/assets and local services before disconnecting. Sources: open-webui:open-webui:offline. - mode_feature_gaps — Which features are missing outside SaaS? [supported]: External model APIs, internet search, remote extraction and other online tools require network access; they are not made local by self-hosting the UI. Sources: open-webui:open-webui:offline. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: open-webui:open-webui:quickstart, open-webui:open-webui:enterprise, open-webui:open-webui:offline ### 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. #### Glean Verification status: Agent cross-checked (agent-cross-checked) Support: partial The AI Addendum prohibits model training and scopes provider retention commitments to Glean-key use, with exceptions. Availability: generally-available Delivery: native Scope: surfaces=Glean Hosted web Assistant and Agents; version=Public documentation retrieved 2026-10-21; deployed version not observed; plan=Any contracted plan incorporating the AI Addendum; Glean model key unless Customer Key explicitly discussed; add_ons=none stated; deployment_mode=dedicated-instance; region=Selected hosting and model-provider regions; no blanket EU or Swiss processing claim; os=not specified. Limitations: - Documented findings only; unestablished atomic questions remain explicit gaps. - vendor_training — Does the vendor train on customer content? [supported]: AI Addendum section 3(a)(i) prohibits Glean from using Customer Data to train, retrain, improve or fine-tune AI Models. Sources: glean:glean:ai-addendum. - provider_training — Do model providers train on it under this product's contracts? [supported]: For Glean model-key service, Glean contracts with providers to prohibit that training. Customer Key access remains the customer responsibility under section 4. Sources: glean:glean:ai-addendum. - provider_retention — How long do model providers keep prompts, including for abuse monitoring? [partial]: Glean-key section 3(b) prohibits stored/logged inputs and outputs except legal or trust-and-safety necessity. The Data Analysis guide also describes up to 30-day retention for abuse-flagged files. Sources: glean:glean:ai-addendum, glean:glean:analysis. - zero_retention — Is zero data retention available, and on which plan? [partial]: Zero-day retention is a contractual Glean-key commitment subject to law and trust/safety exceptions; it is not a blanket guarantee for Customer Key or every file-processing tool. Sources: glean:glean:ai-addendum, glean:glean:analysis. - human_review — Can provider staff review content? [unknown]: Can provider staff review content? The AI Addendum and Data Analysis security text were checked; provider human-review access under each exception was not established. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: glean:glean:ai-addendum, glean:glean:analysis #### Open WebUI Verification status: Agent cross-checked (agent-cross-checked) Support: partial Self-hosting controls the application data path; training and retention obligations depend on the chosen external model contract. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected code pinned to v0.12.3 / 91ea4e3421d1d8069f13d4a463fcb5986d94ea60; plan=Standard self-hosted with original branding intact; Enterprise only where explicitly stated; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure country; external inference, extraction, search and support locations require separate configuration and contracts; os=not specified. Limitations: - vendor_training: The self-hosted data path runs on customer infrastructure; this is architecture evidence, not a reviewed contractual no-training promise covering support or optional services. - provider_training: Do model providers train on it under this product's contracts? No executed provider agreement, abuse-monitoring retention, zero-retention entitlement or human-review policy was verified for a configured endpoint. Local inference is a separate deployment choice, not a blanket promise for cloud-connected use. - provider_retention: How long do model providers keep prompts, including for abuse monitoring? No executed provider agreement, abuse-monitoring retention, zero-retention entitlement or human-review policy was verified for a configured endpoint. Local inference is a separate deployment choice, not a blanket promise for cloud-connected use. - zero_retention: Is zero data retention available, and on which plan? No executed provider agreement, abuse-monitoring retention, zero-retention entitlement or human-review policy was verified for a configured endpoint. Local inference is a separate deployment choice, not a blanket promise for cloud-connected use. - human_review: Can provider staff review content? No executed provider agreement, abuse-monitoring retention, zero-retention entitlement or human-review policy was verified for a configured endpoint. Local inference is a separate deployment choice, not a blanket promise for cloud-connected use. - vendor_training — Does the vendor train on customer content? [partial]: The self-hosted data path runs on customer infrastructure; this is architecture evidence, not a reviewed contractual no-training promise covering support or optional services. Sources: open-webui:open-webui:privacy, open-webui:open-webui:offline. - 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 executed provider agreement, abuse-monitoring retention, zero-retention entitlement or human-review policy was verified for a configured endpoint. Local inference is a separate deployment choice, not a blanket promise for cloud-connected use. - 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 executed provider agreement, abuse-monitoring retention, zero-retention entitlement or human-review policy was verified for a configured endpoint. Local inference is a separate deployment choice, not a blanket promise for cloud-connected use. - zero_retention — Is zero data retention available, and on which plan? [unknown]: zero_retention: Is zero data retention available, and on which plan? No executed provider agreement, abuse-monitoring retention, zero-retention entitlement or human-review policy was verified for a configured endpoint. Local inference is a separate deployment choice, not a blanket promise for cloud-connected use. - human_review — Can provider staff review content? [unknown]: human_review: Can provider staff review content? No executed provider agreement, abuse-monitoring retention, zero-retention entitlement or human-review policy was verified for a configured endpoint. Local inference is a separate deployment choice, not a blanket promise for cloud-connected use. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: open-webui:open-webui:privacy, open-webui:open-webui:offline ### 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. #### Glean Verification status: Agent cross-checked (agent-cross-checked) Support: partial User-facing chat/file deletion and contract-end obligations are documented; default and effective admin retention remain unknown. Availability: generally-available Delivery: native Scope: surfaces=Glean Hosted web Assistant and Agents; version=Public documentation retrieved 2026-10-21; deployed version not observed; plan=Core Suite/Enterprise Flex user history controls and applicable Terms/DPA; default/effective configured retention and shared-link lifetime unverified; add_ons=none stated; deployment_mode=dedicated-instance; region=Selected hosting and model-provider regions; no blanket EU or Swiss processing claim; os=not specified. Limitations: - User-facing deletion does not establish erasure from every retained copy. Default/effective configured retention, shared-link lifetime and contract-end completion timing remain unknown. - default_retention — What is retained and for how long by default? [unknown]: Default content retention is unknown. Chat Sharing states a fixed 30-day conversation/link lifetime, while Chat History describes organization-configured periods. The relationship between shared links, stored chats, uploads and other retained copies was not reconciled; no universal default is inferred. - admin_retention — Can admins set retention periods? [unknown]: The history guide lists Off, 30, 90, 180 and 365 days, but the sharing guide states a fixed 30-day conversation/link lifetime. The effective scope of admin settings versus shared-link/stored-chat retention remains unresolved, so a verified configurable retention entitlement is not asserted. - user_deletion — Can users delete their chats and files permanently? [partial]: The history guide lets users remove chats from their history; the upload guide allows file removal before the first query or by deleting the chat afterward. Permanent removal from every copy, backup or event log was not established. Sources: glean:glean:history, glean:glean:uploads, glean:glean:r2-core-entitlements. - contract_end_deletion — What is deleted at contract end, and when? [partial]: Terms section 12.3 and DPA section 7 require deletion at termination subject to legal retention. No fixed completion interval or destruction certificate was established. Sources: glean:glean:terms, glean:glean:dpa, glean:glean:r2-core-entitlements. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: glean:glean:history, glean:glean:uploads, glean:glean:r2-core-entitlements, glean:glean:terms, glean:glean:dpa, glean:glean:sharing #### Open WebUI Verification status: Agent cross-checked (agent-cross-checked) Support: partial Users can remove chats/files subject to permissions, and temporary-chat enforcement can avoid saving new conversations. Complete purge and contract-end schedules remain unverified. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected code pinned to v0.12.3 / 91ea4e3421d1d8069f13d4a463fcb5986d94ea60; plan=Standard self-hosted with original branding intact; Enterprise only where explicitly stated; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure country; external inference, extraction, search and support locations require separate configuration and contracts; os=not specified. Limitations: - default_retention: Normal history persists in the operator’s database; temporary chats reduce saved history. A uniform default duration across chats, files, indexes, logs and backups was not established. - admin_retention: Operators control database and backup retention; enforced temporary-chat permissions stop saving new chats. A general time-based retention scheduler was not established. - user_deletion: Permissions allow chat deletion and file management removes files and related embeddings. Backup purge and irreversible-deletion timing were not verified. - contract_end_deletion: What is deleted at contract end, and when? No enterprise termination deletion deadline or deletion confirmation was reviewed. - default_retention — What is retained and for how long by default? [partial]: Normal history persists in the operator’s database; temporary chats reduce saved history. A uniform default duration across chats, files, indexes, logs and backups was not established. Sources: open-webui:open-webui:privacy, open-webui:open-webui:quickstart. - admin_retention — Can admins set retention periods? [partial]: Operators control database and backup retention; enforced temporary-chat permissions stop saving new chats. A general time-based retention scheduler was not established. Sources: open-webui:open-webui:privacy. - user_deletion — Can users delete their chats and files permanently? [partial]: Permissions allow chat deletion and file management removes files and related embeddings. Backup purge and irreversible-deletion timing were not verified. Sources: open-webui:open-webui:permissions, open-webui:open-webui:rag. - contract_end_deletion — What is deleted at contract end, and when? [unknown]: contract_end_deletion: What is deleted at contract end, and when? No enterprise termination deletion deadline or deletion confirmation was reviewed. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: open-webui:open-webui:privacy, open-webui:open-webui:quickstart, open-webui:open-webui:permissions, open-webui:open-webui:rag ### 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. #### Glean Verification status: Agent cross-checked (agent-cross-checked) Support: partial A dated processor list includes US providers and Indian remote support, with DPA transfer and change terms. Availability: generally-available Delivery: native Scope: surfaces=Glean Hosted web Assistant and Agents; version=Public documentation retrieved 2026-10-21; deployed version not observed; plan=Core Suite/Enterprise Flex under applicable public Terms, signed DPA and Order Form; no bespoke contract examined; add_ons=none stated; deployment_mode=dedicated-instance; region=Selected hosting and model-provider regions; no blanket EU or Swiss processing claim; os=not specified. Limitations: - Documented findings only; unestablished atomic questions remain explicit gaps. - subprocessor_list — Is a dated sub-processor list published? [supported]: Public list last updated July 28, 2026 identifies infrastructure, model, support and search subprocessors. Sources: glean:glean:subprocessors, glean:glean:r2-core-entitlements. - subprocessor_countries — Which countries do sub-processors operate in? [supported]: The table lists US provider entities and India for Glean Search Technologies remote support; selected cloud/provider processing locations can differ. Sources: glean:glean:subprocessors, glean:glean:r2-core-entitlements. - change_notification — Are customers notified of sub-processor changes? [supported]: DPA section 9 specifies at least 30 days notice before a new processor and a 30-day objection period, with a scoped termination remedy if unresolved. Sources: glean:glean:dpa, glean:glean:r2-core-entitlements. - parent_jurisdiction — Which jurisdiction governs the vendor and its parent? [partial]: The Terms identify Glean Technologies, Inc. as a Delaware corporation. A separate parent entity was not established. Sources: glean:glean:terms, glean:glean:r2-core-entitlements. - transfer_mechanism — Which transfer mechanism applies to non-EU/CH processing? [supported]: The DPA incorporates EU SCCs, Swiss-recognized clauses and the UK Addendum for applicable transfers; SCC law/jurisdiction is Ireland. Sources: glean:glean:dpa, glean:glean:r2-core-entitlements. - government_access_policy — Is there a published government-access or transparency policy? [unknown]: Is there a published government-access or transparency policy? DPA, processor list and privacy page were checked. A separate government-access/transparency-request policy was not established; no legal exposure verdict is made. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: glean:glean:subprocessors, glean:glean:r2-core-entitlements, glean:glean:dpa, glean:glean:terms #### Open WebUI 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-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. #### Glean Verification status: Agent cross-checked (agent-cross-checked) Support: partial Public contractual and AI-law materials are available, with Swiss/EU data-law scope. Availability: generally-available Delivery: native Scope: surfaces=Glean Hosted web Assistant and Agents; version=Public documentation retrieved 2026-10-21; deployed version not observed; plan=Core Suite/Enterprise Flex applicable public Terms/DPA/AI Addendum; signed Order Form controls actual coverage; add_ons=none stated; deployment_mode=dedicated-instance; region=Selected hosting and model-provider regions; no blanket EU or Swiss processing claim; os=not specified. Limitations: - Documented findings only; unestablished atomic questions remain explicit gaps. - dpa — Is a DPA available, and is it negotiable? [supported]: A public DPA form takes effect when signed and can sit under a mutually accepted agreement; negotiability was not tested. Sources: glean:glean:dpa, glean:glean:r2-core-entitlements. - revdsg_gdpr — Does the DPA cover revDSG and GDPR? [supported]: The DPA defines applicable data-protection law to include Switzerland and GDPR and describes Swiss transfer clauses. Applicability depends on the processing. Sources: glean:glean:dpa, glean:glean:r2-core-entitlements. - governing_law — Which law and court govern the contract? [partial]: Main Terms section 13.1 specifies New York and US law; SCCs select Ireland for their own governing law/jurisdiction. A specific court for the main contract was not established. Sources: glean:glean:terms, glean:glean:dpa, glean:glean:r2-core-entitlements. - ai_act_materials — Is EU AI Act documentation provided? [partial]: The AI Addendum includes applicable EU AI Act commitments and allocation of customer/provider responsibilities; a full procurement technical file was not retrieved. Sources: glean:glean:ai-addendum, glean:glean:r2-core-entitlements. - sector_materials — Are FINMA or other sector materials provided? [partial]: The public legal index links HIPAA BAA forms for Glean as Business Associate and as Subcontractor; actual coverage depends on the applicable agreement. The AI Addendum describes assurance commitments. FINMA/banking-secrecy outsourcing materials were not established. Sources: glean:glean:r3-legal-index, glean:glean:ai-addendum, glean:glean:r2-core-entitlements. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: glean:glean:dpa, glean:glean:r2-core-entitlements, glean:glean:terms, glean:glean:ai-addendum, glean:glean:r3-legal-index #### Open WebUI 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. #### Glean Verification status: Agent cross-checked (agent-cross-checked) Support: partial SOC 2 and ISO badges are vendor claims; issuer, report scope and validity were not independently checked. Availability: generally-available Delivery: native Scope: surfaces=Glean Hosted web Assistant and Agents; version=Public documentation retrieved 2026-10-21; deployed version not observed; plan=Core Suite Protect compliance material; vendor badges only, certificate/report scope and validity unverified; add_ons=none stated; deployment_mode=dedicated-instance; region=Selected hosting and model-provider regions; no blanket EU or Swiss processing claim; os=not specified. Limitations: - No evidence is certificate-verified. Cloud-provider certificates are not treated as Glean certificates. - iso_27001 — ISO 27001 with scope and validity? [partial]: Glean claims ISO 27001 on its security page. The actual certificate, issuer, service scope and validity dates were not obtained. Sources: glean:glean:security-page, glean:glean:r2-core-entitlements. - soc2 — SOC 2 type, period and covered service? [partial]: Glean claims SOC 2 Type II, but auditor, examination period and exact covered service were not verified from a report. Sources: glean:glean:security-page, glean:glean:r2-core-entitlements. - c5 — BSI C5 attestation? [unknown]: BSI C5 attestation? The public security page and trust.glean.com were checked; trust report content was inaccessible. BSI C5, independent pentest summaries and certificate/report validity were not established. - other_certifications — Which other certificates (27701, 42001, TISAX)? [partial]: The security page lists ISO 42001, HIPAA and TX-RAMP Level 2. These are vendor assertions, not verified certificates in this profile. Sources: glean:glean:security-page, glean:glean:r2-core-entitlements. - report_access — How can customers obtain reports? [partial]: Security and accessibility material direct evaluators to the public Trust Center, whose report content was not readable without further access. Sources: glean:glean:security-page, glean:glean:accessibility, glean:glean:r2-core-entitlements. - pentest — Are independent penetration test summaries available? [unknown]: Are independent penetration test summaries available? The public security page and trust.glean.com were checked; trust report content was inaccessible. BSI C5, independent pentest summaries and certificate/report validity were not established. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: glean:glean:security-page, glean:glean:r2-core-entitlements, glean:glean:accessibility #### Open WebUI 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). #### Glean Verification status: Agent cross-checked (agent-cross-checked) Support: partial Encryption, isolation and network controls are documented. Customer-managed keys are supported for Customer Hosted AWS; other key-custody scopes remain unverified. Availability: generally-available Delivery: native Scope: surfaces=Glean Hosted web Assistant and Agents, Customer Hosted managed GCP or AWS tenant; version=Public documentation retrieved 2026-10-21; deployed version not observed; plan=Core Suite Protect encryption and single-tenant Glean Hosted; separately contracted Customer Hosted network configuration; add_ons=none stated; deployment_mode=not specified; region=Selected hosting and model-provider regions; no blanket EU or Swiss processing claim; os=not specified. Limitations: - Documented findings only; unestablished atomic questions remain explicit gaps. - encryption_at_rest — Is data encrypted at rest? [supported]: Deployment comparison documents AES-256 at rest and TLS in transit for both deployment modes. Sources: glean:glean:deploy, glean:glean:r2-core-entitlements. - customer_managed_keys — Can the customer manage or hold the keys? [supported]: For Customer Hosted AWS, Glean supports KMS customer-managed encryption keys owned and controlled by the customer. The FAQ recommends default managed keys; Glean Hosted/GCP key custody and commercial prerequisites were not established. Sources: glean:glean:r4-aws-cmk-faq, glean:glean:r4-aws-key-control. - private_networking — Is private connectivity or IP restriction available? [supported]: IP-based access controls and private connectivity for on-prem connectors are documented; customer AWS supports local VPC endpoints. Sources: glean:glean:deploy, glean:glean:r2-core-entitlements. - tenant_isolation — How are customers separated in shared SaaS? [supported]: Each deployment uses isolated single-tenant infrastructure, including the Glean-managed customer-cloud option. Sources: glean:glean:deploy, glean:glean:r2-core-entitlements. Checked 2026-10-26; agent cross-checked 2026-10-26; check again by 2026-12-25. Sources: glean:glean:deploy, glean:glean:r2-core-entitlements, glean:glean:r4-aws-cmk-faq, glean:glean:r4-aws-key-control #### Open WebUI Verification status: Agent cross-checked (agent-cross-checked) Support: partial Encryption and private networking are operator responsibilities; product flags do not remove host-operator access. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected code pinned to v0.12.3 / 91ea4e3421d1d8069f13d4a463fcb5986d94ea60; plan=Standard self-hosted with original branding intact; Enterprise only where explicitly stated; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure country; external inference, extraction, search and support locations require separate configuration and contracts; os=not specified. Limitations: - encryption_at_rest: The privacy guide recommends encrypted PostgreSQL volumes/backups or encrypted SQLite filesystems. SQLCipher is explicitly unsupported since v0.9.0. It is not automatic application-level encryption of all content. - customer_managed_keys: The customer can operate infrastructure encryption keys. A product HYOK/key-escrow protocol was not established. - tenant_isolation: How are customers separated in shared SaaS? Shared vendor SaaS tenant isolation was not established for the scoped customer-operated product. - encryption_at_rest — Is data encrypted at rest? [partial]: The privacy guide recommends encrypted PostgreSQL volumes/backups or encrypted SQLite filesystems. SQLCipher is explicitly unsupported since v0.9.0. It is not automatic application-level encryption of all content. Sources: open-webui:open-webui:privacy. - customer_managed_keys — Can the customer manage or hold the keys? [partial]: The customer can operate infrastructure encryption keys. A product HYOK/key-escrow protocol was not established. Sources: open-webui:open-webui:privacy. - private_networking — Is private connectivity or IP restriction available? [supported]: The application and local services can run inside customer networks and disconnected environments; TLS/reverse-proxy setup remains operator work. Sources: open-webui:open-webui:privacy, open-webui:open-webui:offline. - tenant_isolation — How are customers separated in shared SaaS? [unknown]: tenant_isolation: How are customers separated in shared SaaS? Shared vendor SaaS tenant isolation was not established for the scoped customer-operated product. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: open-webui:open-webui:privacy, open-webui:open-webui:offline ### 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. #### Glean Verification status: Agent cross-checked (agent-cross-checked) Support: partial General DPA confidentiality and provider/support access are documented; a specific German or Swiss professional-secrecy undertaking remains unverified. Availability: generally-available Delivery: native Scope: surfaces=Glean Hosted web Assistant and Agents, Customer Hosted managed GCP or AWS tenant; version=Public documentation retrieved 2026-10-21; deployed version not observed; plan=Core Suite/Enterprise Flex public Terms/DPA confidentiality; no verified professional-secrecy-specific package; add_ons=none stated; deployment_mode=not specified; region=Selected hosting/provider regions; listed India support affiliate; no DE/CH-specific undertaking verified; os=not specified. Limitations: - DPA confidentiality and no-training provisions alone do not establish a professional-secrecy undertaking. - No legal suitability or compliance conclusion. - secrecy_undertaking — Does the vendor sign a secrecy undertaking or § 203 StGB / Art. 321 StGB agreement covering its own staff? [unknown]: Glean DPA section4 binds authorized personnel to confidentiality or statutory duties, but no signed/signon German §203 StGB or Swiss Art321 StGB professional-secrecy undertaking was retrieved. General DPA confidentiality is not treated as that undertaking. - subprocessor_coverage — Does the undertaking extend to its sub-processors, and is that documented? [unknown]: DPA section9 requires no-less-protective written subprocessor obligations and necessary access. No flow-down of a specific §203/Art321 professional-secrecy undertaking was established. - secrecy_offering — Is it a dedicated offering or add-on, and on which plan? [unknown]: No publicly documented professional-secrecy-specific plan, dedicated package, paid add-on, minimum or regional contract entitlement was established in legal pages, administration docs, pricing or targeted first-party search. - content_access — Who can access content in plain text: vendor staff, sub-processors, model providers? [partial]: Contractually authorized Glean personnel and necessary subprocessors may process customer personal data; the processor list names India remote support/security/debugging and model/hosting providers. Model routes receive prompts/context for inference. Exact plaintext privileges, exceptional support approval, provider human-access rights and their differences by key/deployment mode are not fully established. Sources: glean:glean:dpa-confidentiality, glean:glean:subprocessors, glean:glean:key-matrix, glean:glean:ai-addendum, glean:glean:r2-core-entitlements. - secrecy_documentation — Is the offering publicly documented (contract template, data-flow description, professional-body guidance)? [unknown]: A public DPA, AI Addendum, deployment docs and processor list were retrieved. No public §203/Art321 contract template, dedicated professional-secrecy data-flow statement or professional-body guidance for this offer was established. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: glean:glean:dpa-confidentiality, glean:glean:subprocessors, glean:glean:key-matrix, glean:glean:ai-addendum, glean:glean:r2-core-entitlements #### Open WebUI Verification status: Agent cross-checked (agent-cross-checked) Support: partial The self-hosted content-access boundary is documented. A vendor secrecy undertaking under § 203 StGB or Art. 321 StGB, its staff/sub-processor coverage and any plan-specific offering remain unverified. Availability: unknown Delivery: unknown Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; standard self-hosted server and separately described Enterprise support; plan=Standard branded self-hosted use; Enterprise licensing/support checked separately, with no professional-secrecy contract or add-on verified; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected application/model infrastructure; no DE/CH secrecy-contract variant or vendor/support access jurisdiction verified; os=not specified. Limitations: - The secrecy undertaking, sub-processor coverage, offering and professional-secrecy-specific documentation remain unknown. - content_access: A concrete deployment, support-access grant, sub-processor permissions and model-provider staff access were not audited. - 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]: The public Enterprise, support, security and law-firm pages did not establish a signed or signable professional-secrecy undertaking binding Open WebUI staff. No § 203 StGB / Art. 321 StGB agreement was obtained; informational security guidance is not recorded as one. Sources: open-webui:open-webui:enterprise, open-webui:open-webui:secrecy-support. - subprocessor_coverage — Does the undertaking extend to its sub-processors, and is that documented? [unknown]: No professional-secrecy undertaking or annex identifying covered sub-processors and their secrecy obligations was found in the reviewed public materials. Customer-selected hosting, model and support arrangements need their own document review. - secrecy_offering — Is it a dedicated offering or add-on, and on which plan? [unknown]: Enterprise licensing and advisory support are documented, but their public descriptions did not establish a professional-secrecy package, paid add-on, eligible plan or contractual scope. No sales contact was made. Sources: open-webui:open-webui:enterprise, open-webui:open-webui:secrecy-support. - content_access — Who can access content in plain text: vendor staff, sub-processors, model providers? [partial]: For self-hosted AI chats, Open WebUI documents the running application, live-query database administrators, host/backup operators and configured external model providers as part of the content-access boundary. Admin UI restrictions and at-rest encryption do not exclude those operators. The law-firm page says self-hosted data is not sent to Open WebUI as a managed service; vendor support grants, sub-processor staff permissions and provider human access were not verified for a concrete deployment. Sources: open-webui:open-webui:secrecy-access, open-webui:open-webui:secrecy-legal. - secrecy_documentation — Is the offering publicly documented (contract template, data-flow description, professional-body guidance)? [unknown]: The law-firm page provides general deployment/privacy guidance and links US ABA materials. No product-scoped DE/CH secrecy contract template, staff/sub-processor annex or professional-body confirmation was located in the reviewed public pages or targeted searches. Sources: open-webui:open-webui:secrecy-legal. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: open-webui:open-webui:enterprise, open-webui:open-webui:secrecy-support, open-webui:open-webui:secrecy-access, open-webui:open-webui:secrecy-legal ## 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. #### Glean Verification status: Agent cross-checked (agent-cross-checked) Support: partial Glean publishes pricing mechanics and usage tables, while contracted seat fees remain quote-only. Availability: generally-available Delivery: native Scope: surfaces=Glean Hosted web Assistant and Agents; version=Public documentation retrieved 2026-10-21; deployed version not observed; plan=Unspecified contracted plan unless Core Suite, Enterprise Flex, key mode or add-on is named below; add_ons=none stated; deployment_mode=dedicated-instance; region=Selected hosting and model-provider regions; no blanket EU or Swiss processing claim; os=not specified. Limitations: - Documented findings only; unestablished atomic questions remain explicit gaps. - pricing_unit — What is the pricing unit? [supported]: Core Suite is per user/month plus committed Model Hub Usage. Enterprise Flex combines seats with pooled FlexCredits; legacy Enterprise terms differ. Sources: glean:glean:core-price, glean:glean:flex-price. - list_prices — What are list prices per plan, with date and currency? [partial]: On 2026-10-21 no numerical Core Suite/Enterprise Flex seat or platform fee was established. Public model token-rate and credit-consumption tables are available; they are not a complete subscription quote. Sources: glean:glean:core-price, glean:glean:flex-price. - included_usage — What usage is included? [partial]: Core Suite includes platform/search and human-scale APIs in seats; LLM APIs and advanced work consume model usage. Flex uses plan-specific included capabilities and shared credits. Sources: glean:glean:core-price, glean:glean:flex-price. - add_ons — Which features cost extra? [partial]: Protect+ is an add-on and Premium Support is paid; Model Hub usage is separate. Public add-on seat/contract fees were not established. Sources: glean:glean:protect, glean:glean:sla. - overage — What do usage beyond limits and premium models cost? [partial]: Core Suite usage follows provider/model API rates with an upfront commitment; machine-scale API use may cost extra. Flex uses credit rate cards. Currency price per contracted FlexCredit is unverified. Sources: glean:glean:core-price, glean:glean:flex-price. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: glean:glean:core-price, glean:glean:flex-price, glean:glean:protect, glean:glean:sla #### Open WebUI Verification status: Agent cross-checked (agent-cross-checked) Support: partial Branding-intact standard use is free; Enterprise and external infrastructure/model services cost separately. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected code pinned to v0.12.3 / 91ea4e3421d1d8069f13d4a463fcb5986d94ea60; plan=Standard self-hosted with original branding intact; Enterprise only where explicitly stated; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure country; external inference, extraction, search and support locations require separate configuration and contracts; os=not specified. Limitations: - list_prices: Standard internal use is listed as Free on 2026-10-21. No numeric Enterprise tariff was published in the reviewed offer. - add_ons: Branding changes outside licence exceptions and enterprise-exclusive offerings such as Terminals require Enterprise rights; service rates were not established. - overage: External providers charge under their own accounts; no universal Open WebUI inference overage tariff applies to standard self-hosting. - pricing_unit — What is the pricing unit? [supported]: Standard software use has no per-seat fee with original branding intact. Enterprise rights/support are separately licensed. Sources: open-webui:open-webui:enterprise. - list_prices — What are list prices per plan, with date and currency? [partial]: Standard internal use is listed as Free on 2026-10-21. No numeric Enterprise tariff was published in the reviewed offer. Sources: open-webui:open-webui:enterprise. - included_usage — What usage is included? [supported]: A software licence does not supply model inference or hosting; customers configure those services. Sources: open-webui:open-webui:enterprise, open-webui:open-webui:provider. - add_ons — Which features cost extra? [partial]: Branding changes outside licence exceptions and enterprise-exclusive offerings such as Terminals require Enterprise rights; service rates were not established. Sources: open-webui:open-webui:enterprise, open-webui:open-webui:terms. - overage — What do usage beyond limits and premium models cost? [partial]: External providers charge under their own accounts; no universal Open WebUI inference overage tariff applies to standard self-hosting. Sources: open-webui:open-webui:provider, open-webui:open-webui:enterprise. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: open-webui:open-webui:enterprise, open-webui:open-webui:provider, open-webui:open-webui:terms ### 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. #### Glean Verification status: Agent cross-checked (agent-cross-checked) Support: partial Core Suite publishes model tariffs, but no public unique routine Auto model or fixed fee; a separate direct-provider Customer Key component is calculable. Availability: generally-available Delivery: native Scope: surfaces=Glean Hosted web Assistant and Agents, Customer Hosted managed GCP or AWS tenant; version=Public documentation retrieved 2026-10-21; deployed version not observed; plan=Core Suite Universal Model Key usage unpriced without a fixed/recommended routine model; separate Customer Key direct-API proxy; Enterprise Flex quote/pool unknown; add_ons=none stated; deployment_mode=not specified; region=Selected hosting and model-provider regions; no blanket EU or Swiss processing claim; os=not specified. Limitations: - The priced Customer Key component is an assumption for direct provider payment, not a complete Glean price or a forecast of Auto routing. - No signed order, fixed fee, actual tenant defaults or task usage fixture. - cost_200 — Year-one cost at 200 users? [partial]: ALM-14 shared cost assumptions v1.4,2026-10-21:12 months exVAT,list prices,no invented discounts;60% light100/30% regular400/10% power1500 messages/user/month =>330;3000 input+600 output tokens/message. ECB2026-10-20 EUR1=USD1.1215=CHF0.9237. Direct-provider Customer Key comparison uses gpt-6-luna effort none atUSD0.10 input/USD0.50 output per1M,no cache =>USD2.376/user/year. This proxy is not a Glean Universal Model Key tariff/default. For200 Customer Key users: identified direct-model component USD475.20/EUR423.72/CHF391.39 + unknown Core Suite seat fee, Glean-family usage, support/cloud costs. Universal Model Key total and Enterprise Flex total remain unknown. Sources: glean:glean:r2-core-entitlements, glean:glean:r2-auto-policy-and-cloud-conflict, glean:glean:r2-customer-default-example, glean:glean:r2-direct-provider-proxy, glean:glean:r2-proxy-lowest-effort, glean:glean:fx-ecb. - cost_1000 — Year-one cost at 1,000 users? [partial]: Same v1.4 assumptions:1000 Customer Key users, identified direct-model component USD2376/EUR2118.59/CHF1956.94 + unknown seat/Glean-family/support/cloud costs. Not an enterprise quote; Universal Model Key and Flex totals remain unknown. Sources: glean:glean:r2-core-entitlements, glean:glean:r2-direct-provider-proxy, glean:glean:r2-proxy-lowest-effort, glean:glean:fx-ecb. - cost_5000 — Year-one cost at 5,000 users? [partial]: Same v1.4 assumptions:5000 Customer Key users, identified direct-model component USD11880/EUR10592.96/CHF9784.71 + unknown seat/Glean-family/support/cloud costs. Not an enterprise quote; Universal Model Key and Flex totals remain unknown. Sources: glean:glean:r2-core-entitlements, glean:glean:r2-direct-provider-proxy, glean:glean:r2-proxy-lowest-effort, glean:glean:fx-ecb. - variable_share — Which part depends on usage? [partial]: Core Suite publishes input/output tariffs. Universal Model Key defaults to Balanced Auto, a policy choosing model and effort per request; recommendations are shown in the admin UI, not as a unique public routine model. The Customer Key guide calls GPT5.6 Luna an example, not a recommendation. Under v1.4, vendor-billed usage remains unknown; only the separate direct-API proxy is costed. Enterprise Flex has different mode/credit accounting. Sources: glean:glean:r2-core-entitlements, glean:glean:r2-auto-policy-and-cloud-conflict, glean:glean:r2-customer-default-example, glean:glean:r2-flex-entitlements, glean:glean:r2-direct-provider-proxy, glean:glean:r2-proxy-lowest-effort. - unknown_parts — Which costs could not be priced? [supported]: Unknown: seat/platform quotes, Universal Model Key realized model mix and Auto/tool overhead, FlexCredit purchase price and task consumption, Glean-family calls on Customer Key, Protect+/support fees, cloud operations and implementation. No zero fixed fee, fictitious discount or vendor-billed proxy substitution. Exchange rate is known and explicitly stated; quote-only total is not calculated. Sources: glean:glean:r2-core-entitlements, glean:glean:r2-flex-entitlements, glean:glean:deploy, glean:glean:fx-ecb. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: glean:glean:r2-core-entitlements, glean:glean:r2-auto-policy-and-cloud-conflict, glean:glean:r2-customer-default-example, glean:glean:r2-direct-provider-proxy, glean:glean:r2-proxy-lowest-effort, glean:glean:fx-ecb, glean:glean:r2-flex-entitlements, glean:glean:deploy #### Open WebUI 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 code pinned to v0.12.3 / 91ea4e3421d1d8069f13d4a463fcb5986d94ea60; plan=Standard self-hosted with original branding intact; Enterprise only where explicitly stated; 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: open-webui:open-webui:enterprise, open-webui:open-webui:cost-vm, open-webui:open-webui:cost-pg, open-webui:open-webui:cost-fx, open-webui:open-webui:cost-model, open-webui:open-webui: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: open-webui:open-webui:enterprise, open-webui:open-webui:cost-vm, open-webui:open-webui:cost-pg, open-webui:open-webui:cost-fx, open-webui:open-webui:cost-model, open-webui:open-webui: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: open-webui:open-webui:enterprise, open-webui:open-webui:cost-vm, open-webui:open-webui:cost-pg, open-webui:open-webui:cost-fx, open-webui:open-webui:cost-model, open-webui:open-webui: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: open-webui:open-webui:cost-model, open-webui:open-webui: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. Open WebUI Enterprise, branding rights outside standard exceptions and Terminals production licences are quote-only. The shared VM/PG sizes have not been load-tested and do not replace each product’s documented runtime dependencies. Sources: open-webui:open-webui:cost-vm, open-webui:open-webui:cost-pg, open-webui:open-webui:enterprise. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: open-webui:open-webui:enterprise, open-webui:open-webui:cost-vm, open-webui:open-webui:cost-pg, open-webui:open-webui:cost-fx, open-webui:open-webui:cost-model, open-webui:open-webui: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. #### Glean Verification status: Agent cross-checked (agent-cross-checked) Support: partial Public material supports product evaluation, but no unassisted business trial was established. Availability: generally-available Delivery: native Scope: surfaces=Glean Hosted web Assistant and Agents; version=Public documentation retrieved 2026-10-21; deployed version not observed; plan=Core Suite/Enterprise Flex prospective customer evaluation; public demo path, no verified self-serve trial entitlement; add_ons=none stated; deployment_mode=dedicated-instance; region=Selected hosting and model-provider regions; no blanket EU or Swiss processing claim; os=not specified. Limitations: - Documented findings only; unestablished atomic questions remain explicit gaps. - Core Suite/Enterprise Flex trial and evaluation entitlements were not publicly verified; a demo CTA is not proof of a mandatory sales gate. - free_tier — Is there a free tier for business use? [unknown]: Is there a free tier for business use? The live product/security site, documentation setup and pricing guides were checked. No public business free-tier entitlement, self-serve trial terms, card/duration/seat limits or SSO/connector trial scope was established. No sales contact or account registration was attempted. - self_serve_trial — Is a self-serve business trial available? [unknown]: Is a self-serve business trial available? The live product/security site, documentation setup and pricing guides were checked. No public business free-tier entitlement, self-serve trial terms, card/duration/seat limits or SSO/connector trial scope was established. No sales contact or account registration was attempted. - trial_scope — Do trials include SSO, connectors and admin features? [unknown]: Do trials include SSO, connectors and admin features? The live product/security site, documentation setup and pricing guides were checked. No public business free-tier entitlement, self-serve trial terms, card/duration/seat limits or SSO/connector trial scope was established. No sales contact or account registration was attempted. - sales_gate — Does meaningful evaluation require sales contact? [partial]: Public Glean pages route prospective customers to Get a demo; meaningful tenant provisioning may require commercial access. This is not proof that every trial is sales-only. Sources: glean:glean:security-page, glean:glean:r2-core-entitlements. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: glean:glean:security-page, glean:glean:r2-core-entitlements #### Open WebUI Verification status: Agent cross-checked (agent-cross-checked) Support: partial Standard self-installation permits evaluation without sales contact; Enterprise rights and services have a separate sales path. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected code pinned to v0.12.3 / 91ea4e3421d1d8069f13d4a463fcb5986d94ea60; plan=Standard self-hosted with original branding intact; Enterprise only where explicitly stated; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure country; external inference, extraction, search and support locations require separate configuration and contracts; os=not specified. Limitations: - self_serve_trial: Docker/Python self-installation is available without a licence payment or trial clock; it is an install path rather than a vendor-operated business trial. - sales_gate: Standard self-install evaluation is possible without sales. Enterprise licensing is offered to registered entities via the sales path. - free_tier — Is there a free tier for business use? [supported]: The current enterprise page permits free standard use with branding intact, including organizations. Sources: open-webui:open-webui:enterprise. - self_serve_trial — Is a self-serve business trial available? [partial]: Docker/Python self-installation is available without a licence payment or trial clock; it is an install path rather than a vendor-operated business trial. Sources: open-webui:open-webui:quickstart, open-webui:open-webui:enterprise. - trial_scope — Do trials include SSO, connectors and admin features? [supported]: Self-hosted authentication, administration and knowledge features can be configured for evaluation with the customer’s own infrastructure and credentials. Sources: open-webui:open-webui:quickstart, open-webui:open-webui:sso, open-webui:open-webui:knowledge. - sales_gate — Does meaningful evaluation require sales contact? [partial]: Standard self-install evaluation is possible without sales. Enterprise licensing is offered to registered entities via the sales path. Sources: open-webui:open-webui:enterprise. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: open-webui:open-webui:enterprise, open-webui:open-webui:quickstart, open-webui:open-webui:sso, open-webui:open-webui:knowledge ### 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. #### Glean Verification status: Agent cross-checked (agent-cross-checked) Support: partial Contract periods and fees depend on orders, with cancellation restricted during the subscription term. Availability: generally-available Delivery: native Scope: surfaces=Glean Hosted web Assistant and Agents; version=Public documentation retrieved 2026-10-21; deployed version not observed; plan=Core Suite/Enterprise Flex under Order Form and public Terms; seat commitments/prices and selected currency contractual; add_ons=none stated; deployment_mode=dedicated-instance; region=Selected hosting and model-provider regions; no blanket EU or Swiss processing claim; os=not specified. Limitations: - Documented findings only; unestablished atomic questions remain explicit gaps. - minimum_commitment — What seat or spend minimum applies? [unknown]: What seat or spend minimum applies? Terms and pricing guides were checked; minimum seat/spend commitment and plan-specific currency invoicing remain unpriced. - contract_length — What contract lengths are offered? [partial]: Terms define Subscription Term through the Order Form. No universal monthly or annual term is specified. Sources: glean:glean:terms, glean:glean:r2-core-entitlements. - cancellation — How can the contract be cancelled or reduced? [supported]: Except contractual causes and remedies, customers cannot cancel during the subscription term; each order ends at expiry unless otherwise stated. Sources: glean:glean:terms, glean:glean:r2-core-entitlements. - local_invoicing — Can it be invoiced in CHF or EUR from a European entity? [partial]: Terms default to USD or the currency in the order and allow Glean affiliates/resellers. CHF/EUR invoicing by a European entity was not confirmed. Sources: glean:glean:terms, glean:glean:r2-core-entitlements. - transparency_class — Is pricing transparent, partial, quote-only or unknown? [supported]: Partially specified: public pricing units and consumption tables, but subscription fees, minimum commitments and purchased-credit prices need an order/quote. Sources: glean:glean:core-price, glean:glean:flex-price, glean:glean:terms, glean:glean:r2-core-entitlements. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: glean:glean:terms, glean:glean:r2-core-entitlements, glean:glean:core-price, glean:glean:flex-price #### Open WebUI Verification status: Agent cross-checked (agent-cross-checked) Support: partial Standard-use licence terms are public; Enterprise pricing and negotiated contract details remain quote-only. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected code pinned to v0.12.3 / 91ea4e3421d1d8069f13d4a463fcb5986d94ea60; plan=Standard self-hosted with original branding intact; Enterprise only where explicitly stated; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure country; external inference, extraction, search and support locations require separate configuration and contracts; os=not specified. Limitations: - minimum_commitment: No paid standard-use seat commitment is listed. The 50-user rolling window is a branding exception, not a cap on branded deployment size; Enterprise is available to registered entities. - contract_length: What contract lengths are offered? Enterprise duration, monthly/annual billing, cancellation, price-change clauses and CHF/EUR invoicing from a European entity were not established. - cancellation: How can the contract be cancelled or reduced? Enterprise duration, monthly/annual billing, cancellation, price-change clauses and CHF/EUR invoicing from a European entity were not established. - local_invoicing: Can it be invoiced in CHF or EUR from a European entity? Enterprise duration, monthly/annual billing, cancellation, price-change clauses and CHF/EUR invoicing from a European entity were not established. - minimum_commitment — What seat or spend minimum applies? [partial]: No paid standard-use seat commitment is listed. The 50-user rolling window is a branding exception, not a cap on branded deployment size; Enterprise is available to registered entities. Sources: open-webui:open-webui:license-pin, open-webui:open-webui:enterprise. - contract_length — What contract lengths are offered? [unknown]: contract_length: What contract lengths are offered? Enterprise duration, monthly/annual billing, cancellation, price-change clauses and CHF/EUR invoicing from a European entity were not established. - cancellation — How can the contract be cancelled or reduced? [unknown]: cancellation: How can the contract be cancelled or reduced? Enterprise duration, monthly/annual billing, cancellation, price-change clauses and CHF/EUR invoicing from a European entity were not established. - 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? Enterprise duration, monthly/annual billing, cancellation, price-change clauses and CHF/EUR invoicing from a European entity were not established. - transparency_class — Is pricing transparent, partial, quote-only or unknown? [supported]: Standard-use licence is disclosed; Enterprise price and service terms are quote-only in the reviewed public offer. Sources: open-webui:open-webui:enterprise. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: open-webui:open-webui:license-pin, open-webui:open-webui:enterprise ### 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. #### Glean Verification status: Agent cross-checked (agent-cross-checked) Support: partial The hosted platform is provided under restricted commercial terms; public SDK licences are separate. Availability: generally-available Delivery: native Scope: surfaces=Glean Hosted web Assistant and Agents; version=Public documentation retrieved 2026-10-21; deployed version not observed; plan=Core Suite/Enterprise Flex proprietary hosted/managed Service under Terms; no public core-source licence inferred; add_ons=none stated; deployment_mode=dedicated-instance; region=Selected hosting and model-provider regions; no blanket EU or Swiss processing claim; os=not specified. Limitations: - Documented findings only; unestablished atomic questions remain explicit gaps. - licence_type — Which licence applies to each component? [supported]: Terms grant subscription access and prohibit deriving source code, modifying or redistributing the Service. This establishes a proprietary service contract, not an OSI licence for the platform. Sources: glean:glean:terms, glean:glean:r2-core-entitlements. - branding_restrictions — Do licence terms restrict branding or user counts? [supported]: Terms prohibit removing proprietary notices and limit use to licensed users/orders; no numerical standard user cap is given. Sources: glean:glean:terms, glean:glean:r2-core-entitlements. - enterprise_features_closed — Are enterprise features in a separate closed edition? [unknown]: Are enterprise features in a separate closed edition? Platform terms and the public gleanwork organization were checked; a complete component licence inventory or separate open/closed enterprise edition split was not established. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: glean:glean:terms, glean:glean:r2-core-entitlements #### Open WebUI Verification status: Agent cross-checked (agent-cross-checked) Support: partial The core server at v0.12.3 uses a licence with branding restrictions. The separate Desktop v0.0.20 repository distributes GNU AGPL v3. Terminals and proprietary Enterprise component terms remain unverified. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server, Open WebUI Desktop native distribution (Early Alpha); version=Core v0.12.3 / 91ea4e3421d1d8069f13d4a463fcb5986d94ea60; Desktop v0.0.20 / 601137c5dec2967cfe173a6bf071fbbb460852be; plan=Pinned core server and Desktop component licences only; no executed Enterprise agreement or pinned Terminals licence verified; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure country; external inference, extraction, search and support locations require separate configuration and contracts; os=not specified. Limitations: - The claim follows pinned component licence texts and excludes unverified Enterprise/Terminals feature-licensing assertions. - No executed branding exception or proprietary Enterprise agreement was reviewed. - licence_type — Which licence applies to each component? [partial]: Core v0.12.3 is distributed under the Open WebUI License with branding conditions, so its source availability has restrictions. The separate Desktop v0.0.20 LICENSE is GNU AGPL version 3. Other component licences were not established by these two texts. Sources: open-webui:open-webui:license-pin, open-webui:open-webui:desktop-license-r2. - branding_restrictions — Do licence terms restrict branding or user counts? [supported]: Core LICENSE clause 4 restricts branding changes, with exceptions for no more than 50 natural-person users in a rolling 30 days, specific prior written permission, or an executed Enterprise licence expressly permitting changes. It does not impose a 50-user cap on branded use. This answer follows that pinned text, not the FAQ contribution qualifier. Sources: open-webui:open-webui:license-pin. - enterprise_features_closed — Are enterprise features in a separate closed edition? [unknown]: The core text mentions an Enterprise branding-permission exception but does not establish a separate closed edition or Terminals production terms. No relevant pinned Terminals component licence or executed Enterprise contract was reviewed; those details remain unknown. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: open-webui:open-webui:license-pin, open-webui:open-webui:desktop-license-r2 ### 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. #### Glean Verification status: Agent cross-checked (agent-cross-checked) Support: partial Workflow agent configurations are portable as JSON; full tenant chat/knowledge export remains unverified. Availability: generally-available Delivery: native Scope: surfaces=Glean Hosted web Assistant and Agents; version=Public documentation retrieved 2026-10-21; deployed version not observed; plan=Core Suite Agent Governance import/export in seat; limited Auto ZIP export and complete organization exit separately unverified; add_ons=none stated; deployment_mode=dedicated-instance; region=Selected hosting and model-provider regions; no blanket EU or Swiss processing claim; os=not specified. Limitations: - Documented findings only; unestablished atomic questions remain explicit gaps. - Core Suite includes agent import/export, but limited Auto ZIP rollout and complete tenant-export entitlements remain unverified. - chat_export — Can admins export all chats? [unknown]: Can admins export all chats? Agent export and contractual termination pages were checked. No trial admin export was run; all-chat export, knowledge/source completeness and a post-termination retrieval window were not established. - assistant_export — Can assistants and prompts be exported in a reusable format? [supported]: Workflow-mode agent configuration exports to JSON and imports into another deployment; missing target tools must be reconfigured. Auto-mode ZIP export is limited availability for admins. Sources: glean:glean:builder, glean:glean:r2-core-entitlements. - knowledge_export — Can knowledge bases and their sources be exported? [unknown]: Can knowledge bases and their sources be exported? Agent export and contractual termination pages were checked. No trial admin export was run; all-chat export, knowledge/source completeness and a post-termination retrieval window were not established. - export_format — Are formats documented and machine-readable? [supported]: Workflow exports use JSON; limited Auto exports contain spec.yaml and instructions.md in ZIP. Admin logs have CSV export. Sources: glean:glean:builder, glean:glean:audit, glean:glean:r2-core-entitlements. - post_termination_window — How long can data be retrieved after termination? [unknown]: How long can data be retrieved after termination? Agent export and contractual termination pages were checked. No trial admin export was run; all-chat export, knowledge/source completeness and a post-termination retrieval window were not established. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: glean:glean:builder, glean:glean:r2-core-entitlements, glean:glean:audit #### Open WebUI Verification status: Agent cross-checked (agent-cross-checked) Support: partial User chats, admin chat records and model definitions have machine-readable export paths. Knowledge ZIP export converts source files to text. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected code pinned to v0.12.3 / 91ea4e3421d1d8069f13d4a463fcb5986d94ea60; plan=Standard self-hosted with original branding intact; Enterprise only where explicitly stated; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure country; external inference, extraction, search and support locations require separate configuration and contracts; os=not specified. Limitations: - assistant_export: Models have JSON export/import and sync APIs. Full portability of all bound tools, skills, external secrets and shared prompts was not tested. - knowledge_export: Admins can export a knowledge base as ZIP containing .txt conversions. Original binary fidelity and full index/configuration restoration were not established. - post_termination_window: How long can data be retrieved after termination? No admin export fixture or Enterprise post-termination retrieval period was tested/reviewed; customer-owned backups remain the operator’s responsibility. - chat_export — Can admins export all chats? [supported]: Users export their history as JSON. The pinned admin all/db route returns database chat records if ENABLE_ADMIN_EXPORT is enabled. Sources: open-webui:open-webui:export, open-webui:open-webui:chats-pin. - assistant_export — Can assistants and prompts be exported in a reusable format? [partial]: Models have JSON export/import and sync APIs. Full portability of all bound tools, skills, external secrets and shared prompts was not tested. Sources: open-webui:open-webui:api. - knowledge_export — Can knowledge bases and their sources be exported? [partial]: Admins can export a knowledge base as ZIP containing .txt conversions. Original binary fidelity and full index/configuration restoration were not established. Sources: open-webui:open-webui:knowledge. - export_format — Are formats documented and machine-readable? [supported]: Chat/model JSON schemas and APIs and knowledge text ZIP output are documented. Sources: open-webui:open-webui:export, open-webui:open-webui:api, open-webui:open-webui:knowledge. - 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 export fixture or Enterprise post-termination retrieval period was tested/reviewed; customer-owned backups remain the operator’s responsibility. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: open-webui:open-webui:export, open-webui:open-webui:chats-pin, open-webui:open-webui:api, open-webui:open-webui:knowledge ### 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. #### Glean Verification status: Agent cross-checked (agent-cross-checked) Support: partial Support tiers are documented; a credited 99.9% SLA applies only to paid Premium Support. Availability: generally-available Delivery: native Scope: surfaces=Glean Hosted web Assistant and Agents; version=Public documentation retrieved 2026-10-21; deployed version not observed; plan=Unspecified contracted plan unless Core Suite, Enterprise Flex, key mode or add-on is named below; add_ons=none stated; deployment_mode=dedicated-instance; region=Selected hosting and model-provider regions; no blanket EU or Swiss processing claim; os=not specified. Limitations: - Documented findings only; unestablished atomic questions remain explicit gaps. - support_channels — Which support channels are available on each plan? [supported]: The support portal is the channel eligible for response targets; Standard Support is included and Premium paid. Other channels do not have trackable SLA response times. Sources: glean:glean:sla. - support_languages — Is support available in German, French or Italian? [partial]: The SLA explicitly provides a Japanese support option for Japan and names California/Bangalore operations; German/French/Italian language commitments were not established. Sources: glean:glean:sla. - regional_presence — Is there a DACH or Swiss entity, team or partner? [unknown]: Is there a DACH or Swiss entity, team or partner? The SLA, site and status.glean.com were checked. The status URL returned HTTP 403, so incident history was not verified; DACH/Swiss support presence was not established. - uptime_sla — Is there an uptime SLA with credits? [supported]: Paid Premium Support has 99.9% monthly uptime. Credits are 10% below 99.9% down to 99.0%, and 20% below 99.0%, subject to exclusions and claim deadlines. Sources: glean:glean:sla. - status_page — Is there a public status page with history? [unknown]: Is there a public status page with history? The SLA, site and status.glean.com were checked. The status URL returned HTTP 403, so incident history was not verified; DACH/Swiss support presence was not established. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: glean:glean:sla #### Open WebUI Verification status: Agent cross-checked (agent-cross-checked) Support: partial Enterprise support advertises dedicated channels, account management and engineering office hours; public response/credit terms were not established. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected code pinned to v0.12.3 / 91ea4e3421d1d8069f13d4a463fcb5986d94ea60; plan=Standard self-hosted with original branding intact; Enterprise only where explicitly stated; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure country; external inference, extraction, search and support locations require separate configuration and contracts; os=not specified. Limitations: - support_languages: Is support available in German, French or Italian? DE/FR/IT support coverage, support hours/time zone, CH/DACH contracting/partner presence and a product status-history page were not established in the support/enterprise and roadmap pass. - regional_presence: Is there a DACH or Swiss entity, team or partner? DE/FR/IT support coverage, support hours/time zone, CH/DACH contracting/partner presence and a product status-history page were not established in the support/enterprise and roadmap pass. - uptime_sla: The support page refers to negotiated SLAs, but publishes no reviewed uptime percentage, response commitment or service-credit schedule. - status_page: Is there a public status page with history? DE/FR/IT support coverage, support hours/time zone, CH/DACH contracting/partner presence and a product status-history page were not established in the support/enterprise and roadmap pass. - support_channels — Which support channels are available on each plan? [supported]: Enterprise customers can obtain dedicated support channels and an account manager; community development/support uses public GitHub and community channels. Sources: open-webui:open-webui:support, open-webui:open-webui:roadmap. - support_languages — Is support available in German, French or Italian? [unknown]: support_languages: Is support available in German, French or Italian? DE/FR/IT support coverage, support hours/time zone, CH/DACH contracting/partner presence and a product status-history page were not established in the support/enterprise and roadmap 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? DE/FR/IT support coverage, support hours/time zone, CH/DACH contracting/partner presence and a product status-history page were not established in the support/enterprise and roadmap pass. - uptime_sla — Is there an uptime SLA with credits? [partial]: The support page refers to negotiated SLAs, but publishes no reviewed uptime percentage, response commitment or service-credit schedule. Sources: open-webui:open-webui:support. - status_page — Is there a public status page with history? [unknown]: status_page: Is there a public status page with history? DE/FR/IT support coverage, support hours/time zone, CH/DACH contracting/partner presence and a product status-history page were not established in the support/enterprise and roadmap pass. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: open-webui:open-webui:support, open-webui:open-webui:roadmap ### 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. #### Glean Verification status: Agent cross-checked (agent-cross-checked) Support: partial Public training and templates exist; exact onboarding-service entitlements and prices remain open. Availability: generally-available Delivery: native Scope: surfaces=Glean Hosted web Assistant and Agents; version=Public documentation retrieved 2026-10-21; deployed version not observed; plan=Core Suite Agent Library/templates and public Academy links; contracted onboarding and Premium Support separately scoped; add_ons=none stated; deployment_mode=dedicated-instance; region=Selected hosting and model-provider regions; no blanket EU or Swiss processing claim; os=not specified. Limitations: - Documented findings only; unestablished atomic questions remain explicit gaps. - Exact Academy access, included onboarding, language coverage and support/professional-services entitlement under the customer Order Form remain unknown. - onboarding_service — Is guided onboarding included? [unknown]: Is guided onboarding included? Academy, agent library, SLA and legal service links were checked; included vendor-led onboarding, champion/adoption programme terms and localized end-user training were not established. - user_training — Is end-user training offered, in which languages? [partial]: Glean documentation links self-paced Agent Builder training through Glean Academy; German/French/Italian course availability was not established. Sources: glean:glean:agents, glean:glean:r2-core-entitlements. - use_case_library — Are role-based use cases and templates provided? [supported]: The internal Agent library and documented templates support reusable role/task examples. Sources: glean:glean:library, glean:glean:r2-core-entitlements. - adoption_programme — Is there a champion or adoption programme? [unknown]: Is there a champion or adoption programme? Academy, agent library, SLA and legal service links were checked; included vendor-led onboarding, champion/adoption programme terms and localized end-user training were not established. - service_cost — Which services cost extra? [partial]: Premium Support is priced separately under the SLA. The legal index directly lists the Technical Services Addendum and named Outcomes Packages. Those listings do not establish included onboarding or complete professional-services fees. Sources: glean:glean:sla, glean:glean:r3-legal-index, glean:glean:r2-core-entitlements. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: glean:glean:agents, glean:glean:r2-core-entitlements, glean:glean:library, glean:glean:sla, glean:glean:r3-legal-index #### Open WebUI Verification status: Agent cross-checked (agent-cross-checked) Support: partial Enterprise guidance includes onboarding and engineering advice. Paid hands-on implementation and training terms need separate scoping. Availability: generally-available Delivery: native Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected code pinned to v0.12.3 / 91ea4e3421d1d8069f13d4a463fcb5986d94ea60; plan=Standard self-hosted with original branding intact; Enterprise only where explicitly stated; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure country; external inference, extraction, search and support locations require separate configuration and contracts; os=not specified. Limitations: - onboarding_service: Enterprise account management advertises onboarding guidance, with package inclusion and cost unspecified. - user_training: Is end-user training offered, in which languages? No vendor training languages/curriculum, champion programme or priced change-management package was established. - use_case_library: Documentation provides assistant examples and Open Terminal use cases. A full workforce training/adoption curriculum was not established. - adoption_programme: Is there a champion or adoption programme? No vendor training languages/curriculum, champion programme or priced change-management package was established. - service_cost: Enterprise support is separately arranged; the team describes guidance rather than implementation services and recommends a systems integrator or internal team for hands-on work. Public rates were not established. - onboarding_service — Is guided onboarding included? [partial]: Enterprise account management advertises onboarding guidance, with package inclusion and cost unspecified. Sources: open-webui:open-webui:support. - user_training — Is end-user training offered, in which languages? [unknown]: user_training: Is end-user training offered, in which languages? No vendor training languages/curriculum, champion programme or priced change-management package was established. - use_case_library — Are role-based use cases and templates provided? [partial]: Documentation provides assistant examples and Open Terminal use cases. A full workforce training/adoption curriculum was not established. Sources: open-webui:open-webui:models, open-webui:open-webui:terminal. - adoption_programme — Is there a champion or adoption programme? [unknown]: adoption_programme: Is there a champion or adoption programme? No vendor training languages/curriculum, champion programme or priced change-management package was established. - service_cost — Which services cost extra? [partial]: Enterprise support is separately arranged; the team describes guidance rather than implementation services and recommends a systems integrator or internal team for hands-on work. Public rates were not established. Sources: open-webui:open-webui:support. Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: open-webui:open-webui:support, open-webui:open-webui:models, open-webui:open-webui:terminal ## Sources ### glean:glean:models Supported LLMs. The Model Hub lists text and image models, manual choice and Auto routing, with provider availability dependent on key and cloud. - URL: https://docs.glean.com/administration/llms - Locator: Supported models; availability by hosting environment and provider - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### glean:glean:key-matrix Feature availability by LLM key, provider, and cloud. Customer Key restricts cloud-provider routes and excludes Meeting Notes and podcast artifacts; some defaults must use the same provider. - URL: https://docs.glean.com/administration/llm-key-feature-availability - Locator: Provider and feature matrices - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### glean:glean:uploads Upload files in Assistant. Uploads support Office documents, PDFs, images and text, with context-dependent file caps and OCR prerequisite. - URL: https://docs.glean.com/user-guide/assistant/file-upload - Locator: Formats; upload limits; security; limitations - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### glean:glean:r2-core-entitlements Glean Core Suite entitlements and Model Hub rates. Core Suite separates included platform seats from Model Hub usage, names client/API surfaces, and publishes token rates. - URL: https://docs.glean.com/glean-core-suite-pricing - Locator: Seat capabilities, surfaces, APIs, Model Hub Usage and rate table updated10/20/2026 - Evidence kind: documented - Source date: 2026-10-20 - Retrieved: 2026-10-21 ### glean:glean:r3-october-rollout-migration October 15, 2026 release, version 563. Auto policies require rollout opt-in from October 15 with GA scheduled October 29; Brave is the new search default and existing OpenAI search migrates from October 19. - URL: https://docs.glean.com/release-notes/releases/2026-10-15-october-release - Locator: AI & Model Updates, Auto mode policies; Deprecations & Sunsets, OpenAI Web Search - Evidence kind: documented - Source date: 2026-10-15 - Retrieved: 2026-10-21 ### open-webui:open-webui:provider Connect local and cloud models. Administrators connect model endpoints; the selected endpoint determines inference location, including for attached context. - URL: https://docs.openwebui.com/getting-started/quick-start/connect-a-provider/ - Locator: How it works; Cloud Providers; Local Servers - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### open-webui:open-webui:compat OpenAI-compatible providers. The guide documents compatible cloud gateways and local inference servers, with provider-specific capability differences. - URL: https://docs.openwebui.com/getting-started/quick-start/connect-a-provider/starting-with-openai-compatible/ - Locator: Provider configuration and provider examples - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### open-webui:open-webui:rag Retrieval augmented generation. Document retrieval uses configured embeddings and chunks or full context, with citations and a Google Drive file picker. - URL: https://docs.openwebui.com/features/chat-conversations/rag/ - Locator: Embedding support; Citations; Google Drive integration; per-file retrieval mode - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### open-webui:open-webui:extraction Document extraction. Configurable extraction engines can process scanned documents; browser-only temporary extraction has format limitations. - URL: https://docs.openwebui.com/features/chat-conversations/rag/document-extraction/ - Locator: Available extraction methods; temporary chat limitation - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### glean:glean:deprecation Model deprecation. Customer Key deprecation emails are specified at 60 and 15 days, with removal and replacement behavior. - URL: https://docs.glean.com/administration/model-deprecation - Locator: Customer Key notice schedule; deprecated models - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### glean:glean:release October 15, 2026 release notes. Glean publishes dated release notes covering product and model changes. - URL: https://docs.glean.com/release-notes/releases/2026-10-15-october-release - Locator: Release entry - Evidence kind: documented - Source date: 2026-10-15 - Retrieved: 2026-10-21 ### open-webui:open-webui:openai OpenAI and Azure OpenAI connections. Customers configure their own OpenAI keys or Azure endpoint, deployment IDs and API version. - URL: https://docs.openwebui.com/getting-started/quick-start/connect-a-provider/starting-with-openai/ - Locator: Azure OpenAI tab; Advanced Configuration - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### open-webui:open-webui:releases Open WebUI release notes. Dated releases document shipped changes, including v0.12.3 Drive scope reduction and encrypted private-channel chats. - URL: https://github.com/open-webui/open-webui/releases/tag/v0.12.3 - Locator: v0.12.3, 2026-10-16; v0.12.2; v0.12.1 - Evidence kind: documented - Source date: 2026-10-16 - Retrieved: 2026-10-21 ### glean:glean:r2-flex-entitlements Glean Enterprise Flex entitlements. Enterprise Flex separates seat allowances, metered client APIs/agent runs, included platform governance and annual Protect+/support add-ons. - URL: https://docs.glean.com/glean-enterprise-flex-pricing - Locator: Seats, Developer Tools, Platform, Protect+ and Premium Support - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### glean:glean:r2-auto-policy-and-cloud-conflict Configure LLMs in the Model Hub. Balanced is the default Auto policy with per-request model choice; the AWS Vertex note conflicts with the supported-provider matrix and GCP-only Vertex setup heading. - URL: https://docs.glean.com/administration/configure-llms - Locator: Auto policies; AWS Vertex note; provider setup headings - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### open-webui:open-webui:models Models workspace. Model presets combine instructions, model, knowledge, tools and skills, with access grants and saved versions. - URL: https://docs.openwebui.com/features/workspace/models/ - Locator: Presets; Access; Builtin Tools; System prompts - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### open-webui:open-webui:enterprise Open WebUI for enterprise. Branding-intact internal use is free; enterprise branding rights, support and exclusive offerings require a separate licence. - URL: https://docs.openwebui.com/enterprise/ - Locator: Licence requirements; Deployment; Support - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### glean:glean:r4-open-model-inference Glean open models by region. Universal Model Key open models are served through LLM providers under zero-retention agreements. Creator-region grouping is not inference location; the page states these models are hosted in the US. - URL: https://docs.glean.com/administration/open-models-by-region - Locator: Creator-region controls; Operational details - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-26 ### open-webui:open-webui:memory Memory and personalization. Users manage persistent memories; administrators can disable the feature or restrict groups, including server-side use. - URL: https://docs.openwebui.com/features/chat-conversations/memory/ - Locator: Manual management; Administrative controls; Privacy - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### open-webui:open-webui:offline Run Open WebUI offline. Disconnected operation requires prepared local models, embeddings and extraction; internet APIs and tools remain external dependencies. - URL: https://docs.openwebui.com/tutorials/maintenance/offline-mode/ - Locator: Local prerequisites; disabled online functionality; verification - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### glean:glean:model-controls Exclude or restrict models. Admins can restrict eligible models by department or IdP group, but default models cannot be restricted and hiding premium pickers does not block Auto. - URL: https://docs.glean.com/administration/model-exclusion - Locator: Department and team allow-lists; premium-model toggle - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### glean:glean:model-config Configure LLMs in the Model Hub. Admins configure default models and department Auto policies. - URL: https://docs.glean.com/administration/configure-llms - Locator: Default models and Auto mode policies - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### glean:glean:restrictions Restrict LLM access to content. Admins can exclude connectors, containers and documents from LLM use; changes may take up to one hour. - URL: https://docs.glean.com/administration/assistant/configuration/content-restrictions - Locator: Exclusion and inclusion rules - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### glean:glean:limits Set usage limits and alerts. Core Suite and Enterprise Flex limits can alert or block later billable usage after the current run finishes; team defaults are not pooled budgets. - URL: https://docs.glean.com/administration/management/usage/set-usage-limits-and-alerts - Locator: Enforcement; organization, user, team and agent limits - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### open-webui:open-webui:knowledge Knowledge bases and document chat. Persistent knowledge bases support scoped access, model attachment, incremental directory sync and admin text-file ZIP export. - URL: https://docs.openwebui.com/features/workspace/knowledge/ - Locator: Retrieval modes; Sharing; Syncing; Export; API - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### open-webui:open-webui:groups Groups. User and group grants control resources; permissions accumulate across groups rather than deny access. - URL: https://docs.openwebui.com/features/authentication-access/rbac/groups/ - Locator: Additive permissions; Resource Access; Nested Groups - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### open-webui:open-webui:privacy Chat data privacy and encryption. The deployer controls storage, encryption, logs, backups and provider connections; product admin restrictions do not prevent host-operator access. - URL: https://docs.openwebui.com/security/chat-data-privacy-and-encryption/ - Locator: Controls by concern; encryption; operators; model providers - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### open-webui:open-webui:r4-filter-implementation Open WebUI v0.12.4 filter implementation. The backend dispatches installed filter handlers with user context and propagates inlet failures. It does not itself provide a configured recurring quota or managed PII policy. - URL: https://github.com/open-webui/open-webui/blob/33c1978d5bad52a31df75ea55143025dfad18d16/backend/open_webui/utils/filter.py - Locator: process_filter_function; process_filter_functions; inlet exception propagation - Evidence kind: source-inspected - Source date: 2026-10-25 - Retrieved: 2026-10-26 - Commit: 33c1978d5bad52a31df75ea55143025dfad18d16 - Path: backend/open_webui/utils/filter.py ### open-webui:open-webui:r4-rate-limit-example Open WebUI filter functions. The official optional Python example counts requests per user and raises at its configurable per-minute threshold. This sample uses in-process state and is not an enabled product-wide quota or monetary budget. - URL: https://docs.openwebui.com/features/extensibility/plugin/functions/filter/ - Locator: Example: Rate Limiting for All Requests - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-26 ### glean:glean:analysis Data analysis overview. Uploaded spreadsheets can be analyzed in per-session sandboxes; indexed files can be truncated, and abuse-flagged files may be retained up to 30 days. - URL: https://docs.glean.com/administration/assistant/data-analysis/about-data-analysis - Locator: Known limitations; code interpreter security - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### open-webui:open-webui:env Environment variable configuration. Administrators configure document limits, accepted extensions, audio engines and instance settings. - URL: https://docs.openwebui.com/reference/env-configuration/ - Locator: RAG_FILE_MAX_SIZE; RAG_FILE_MAX_COUNT; RAG_ALLOWED_FILE_EXTENSIONS; audio; system prompt - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### glean:glean:projects Organize content with Projects. Projects persist chats and documents, are private by default and replace Collections through a gradual rollout. - URL: https://docs.glean.com/user-guide/knowledge/projects/how-projects-work - Locator: Create; sharing; access; migration - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### glean:glean:deploy Glean deployment models. Both modes use single-tenant infrastructure operated by Glean; Customer Hosted runs in customer GCP or AWS accounts with Glean support access. - URL: https://docs.glean.com/get-started/prepare/about-deployment - Locator: Glean Hosted; Customer Hosted; comparison table - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### glean:glean:connectors Connectors hub. The official catalog lists M365, Google, Atlassian and other business-system connectors. - URL: https://docs.glean.com/connectors - Locator: Native connector catalog - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### glean:glean:sharepoint SharePoint overview. SharePoint supports indexed and live retrieval; indexing uses certificate-based application permissions and admin consent. - URL: https://docs.glean.com/connectors/native/sharepoint/about - Locator: Access patterns; permissions and security - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### glean:glean:onedrive OneDrive overview. OneDrive offers indexed and live search under the Microsoft 365 parent connector, with certificate-based application permissions. - URL: https://docs.glean.com/connectors/native/onedrive/about - Locator: Access patterns; permissions and security - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### glean:glean:outlook Outlook overview. The Outlook connector supports access to Outlook content through Glean. - URL: https://docs.glean.com/connectors/native/outlook/about - Locator: Connector overview - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### glean:glean:teams-connector Teams overview. Teams indexes channels and optionally private and meeting chats, with mirrored membership checked at query time. - URL: https://docs.glean.com/connectors/native/teams/about - Locator: Supported content; permissions and security - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### glean:glean:drive Google Drive overview. Drive content and permissions are indexed with directory delegation; documented activity and group-sync schedules are distinct. - URL: https://docs.glean.com/connectors/native/gdrive/about - Locator: Permissions; crawling and updates - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### glean:glean:gmail Gmail overview. Gmail has indexed search with source-specific crawl scope and controls. - URL: https://docs.glean.com/connectors/native/gmail/about - Locator: Indexed content and scope - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### glean:glean:gateway Set up external tools with MCP Gateway. Admins proxy external MCP servers and custom tools with role and group controls and OAuth 2.1. - URL: https://docs.glean.com/administration/platform/mcp/external-gateway-tools - Locator: Prerequisites; external servers; access control - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### open-webui:open-webui:onedrive OneDrive and SharePoint. Users attach Microsoft files through a delegated file picker; the guide requires tenant app registration and admin consent. - URL: https://docs.openwebui.com/tutorials/integrations/onedrive-sharepoint/ - Locator: Work/school app registration; delegated API permissions; admin consent - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### open-webui:open-webui:sync Knowledge base sync, oikb. The separate official CLI and daemon copies sources into Open WebUI knowledge bases and propagates changes during sync. - URL: https://docs.openwebui.com/ecosystem/knowledge-base-sync/ - Locator: Overview; connectors; scheduling; incremental sync - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### open-webui:open-webui:mcp Model Context Protocol. Native remote MCP is administrator-configured Streamable HTTP with shared credentials or user OAuth modes. - URL: https://docs.openwebui.com/features/extensibility/mcp/ - Locator: Streamable HTTP; Why admins only; Authentication modes - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### open-webui:open-webui:sync-connectors-r2 oikb connector credentials and deployment boundary. The separate official oikb program lists Teams and Gmail with source credentials; it writes into knowledge bases using an Open WebUI user API key. - URL: https://docs.openwebui.com/ecosystem/knowledge-base-sync/ - Locator: Install; Sources and connectors: SharePoint, Microsoft Teams, Google Drive, Gmail; Access is your access - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### glean:glean:r4-purview-label-redlist Glean O365 sensitivity-label restrictions. Protect+ can exclude SharePoint/OneDrive items by Purview label priority. Glean configures the redlist after account-team enablement; initial full crawl and later recrawls govern propagation. Teams message text is excluded. - URL: https://docs.glean.com/administration/protect/sensitive-findings/restrict-content-via-sensitivity-labels - Locator: Glean Protect+; setup; label-processing FAQ - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-26 ### glean:glean:language Glean language support. German, French, Italian and English end-user UIs are listed; cross-language retrieval is early access and admin setup is not localized. - URL: https://docs.glean.com/administration/management/features/glean-language-support - Locator: Language support matrix; cross-language warning - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### glean:glean:research Use Deep Research. Deep Research creates cited read-only reports from company sources and Brave web search; key modes differ. - URL: https://docs.glean.com/user-guide/assistant/deep-research - Locator: Key modes; citations; limitations - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### glean:glean:sharing Share chats. Viewer chat sharing describes citation redaction and states a fixed 30-day duration. - URL: https://docs.glean.com/user-guide/assistant/chat-sharing - Locator: Viewer controls; uploaded files; retention note - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### glean:glean:memory Memory and personalization. Users can manage saved and learned memory in settings and chat. - URL: https://docs.glean.com/user-guide/assistant/memory-personalization - Locator: Saved and learned memories; user controls - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### glean:glean:memory-admin Configure memory settings. Admins can disable learned memory but not user-controlled saved memory; pricing differs for legacy customers. - URL: https://docs.glean.com/administration/assistant/configuration/memory-personalization - Locator: Configure memory; billing - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### glean:glean:builder Agent Builder. Agents combine configured steps and models; Workflow JSON export is generally available while Auto ZIP export has limited availability. - URL: https://docs.glean.com/agents/concepts/agent-builder - Locator: Instructions, tools and models; import and export - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### glean:glean:agent-sharing Sharing and permissions. Agents have controlled sharing and edit access. - URL: https://docs.glean.com/agents/concepts/sharing-permissions - Locator: Agent sharing permissions - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### glean:glean:library Agent library. Users discover and run accessible agents through the internal library. - URL: https://docs.glean.com/agents/concepts/agent-library - Locator: Browse and discover agents - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### glean:glean:agents How agents work. Agents support dynamic tool use and structured steps, loops and branches. - URL: https://docs.glean.com/agents/how-agents-work - Locator: Auto and Workflow modes; tools; steps - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### glean:glean:groups Group-based permissions. Glean syncs Entra, Google and Okta group membership with integration-dependent timing; feature flag controls group-derived roles. - URL: https://docs.glean.com/administration/identity/roles/group-based-permissions - Locator: Supported providers; sync behavior; limitations - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### glean:glean:roles Administrator Roles. Setup Admin, Admin, Super Admin and specialized moderators have distinct permissions. - URL: https://docs.glean.com/administration/identity/roles/admin-roles - Locator: Role matrix - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### glean:glean:sunset Product and feature retirements. The retirement page records November 13, 2026 end of Glean Assist embedded integrations, past Prompt Library migration and legacy billing-dashboard removal. - URL: https://docs.glean.com/release-notes/sunset - Locator: Embedded support integrations; Prompt Library; legacy billing dashboard - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### open-webui:open-webui:permissions Permissions. Feature and resource permissions cover models, knowledge, prompts, tools, search, images, files and memories. - URL: https://docs.openwebui.com/features/authentication-access/rbac/permissions/ - Locator: Workspace and feature permission tables - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### glean:glean:oauth OAuth options for tools. Connector tools support Glean-managed or customer OAuth applications. - URL: https://docs.glean.com/administration/actions/setup-actions/choose-central-or-custom-oauth - Locator: Central and custom OAuth - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### glean:glean:r3-microsoft-write-confirmation Create Microsoft 365 files. Interactive-agent builders can require write confirmation by disabling Run without user confirmation; confirmation is configurable. - URL: https://docs.glean.com/agents/generate-files-from-templates - Locator: Recommended agent instructions, Human approval - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### open-webui:open-webui:tools Tools. Tools may run through Python, OpenAPI or MCP, and an optional approval mode stops calls until the user allows or denies them. - URL: https://docs.openwebui.com/features/extensibility/plugin/tools/ - Locator: Native tools and OpenAPI; Tool call approval - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### open-webui:open-webui:approvals-r2 Open WebUI experimental tool permissions. Tool Permissions is experimental and disabled by default; interactive approvals can wait, but automations and channel replies always use full access. - URL: https://docs.openwebui.com/features/extensibility/plugin/tools/ - Locator: Tool Approval: ENABLE_TOOL_PERMISSIONS, Full access, Ask for approval, Stop, saved/temporary chats and exceptions - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### glean:glean:web Web Search tools setup. Admins configure OpenAI, Brave or Google search tools and publish them to selected Glean interfaces. - URL: https://docs.glean.com/administration/tools/setup-tools/web-search-tools-setup - Locator: Providers; surface enablement; data sent - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### open-webui:open-webui:web Web search. Search uses an administrator-configured provider and can add external sources to a conversation. - URL: https://docs.openwebui.com/features/chat-conversations/web-search/ - Locator: Enabling and using web search; providers - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### open-webui:open-webui:agent-search Agentic web search and URL fetching. Tool-capable models can repeatedly search and fetch pages, with results and citations in the conversation. - URL: https://docs.openwebui.com/features/chat-conversations/web-search/agentic-search/ - Locator: Native function calling; search and fetch tools - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### glean:glean:triggers Types of agent triggers. Agents can start from messages, forms, connected-system content changes and schedules, subject to admin access. - URL: https://docs.glean.com/agents/concepts/triggers - Locator: Content and schedule triggers - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### open-webui:open-webui:automation Automations. Recurring prompts run on the customer server through the normal chat pipeline and remain private to their owner. - URL: https://docs.openwebui.com/features/chat-conversations/chat-features/automations/ - Locator: Schedules; Access Control; Runtime behavior - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### open-webui:open-webui:r4-event-dispatch Open WebUI v0.12.4 event dispatch. Configured Event functions receive published system events and can run developer-written handlers. Event payload field sanitization is not a general prompt/file PII detection service. - URL: https://github.com/open-webui/open-webui/blob/33c1978d5bad52a31df75ea55143025dfad18d16/backend/open_webui/events.py - Locator: build_event; dispatch_event_functions; EventFunctionSink - Evidence kind: source-inspected - Source date: 2026-10-25 - Retrieved: 2026-10-26 - Commit: 33c1978d5bad52a31df75ea55143025dfad18d16 - Path: backend/open_webui/events.py ### open-webui:open-webui:r4-incoming-channel-webhook Open WebUI v0.12.4 channel webhooks. A token-validated incoming webhook creates a channel message and publishes MESSAGE_CREATED with source channel_webhook. A configured Event handler can respond to this external input; no no-code workflow engine is implied. - URL: https://github.com/open-webui/open-webui/blob/33c1978d5bad52a31df75ea55143025dfad18d16/backend/open_webui/routers/channels.py - Locator: post_webhook_message, lines 2283-2361 - Evidence kind: source-inspected - Source date: 2026-10-25 - Retrieved: 2026-10-26 - Commit: 33c1978d5bad52a31df75ea55143025dfad18d16 - Path: backend/open_webui/routers/channels.py ### glean:glean:office-output Create Microsoft 365 files with agents. Enabled tools create Office files, with limitations on arbitrary templates and output fidelity. - URL: https://docs.glean.com/agents/generate-files-from-templates - Locator: Word, Excel and PowerPoint; template limitations - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### glean:glean:r4-cancellation-release Glean October 15 release notes. Canceling or interrupting an Assistant response also stops tool calls and background tasks started by that response. This is a documented Assistant run behavior, not a tested universal stop guarantee. - URL: https://docs.glean.com/release-notes/releases/2026-10-15-october-release - Locator: Canceled Assistant responses now stop cleanly - Evidence kind: documented - Source date: 2026-10-15 - Retrieved: 2026-10-26 ### open-webui:open-webui:terminal Open Terminal. The separately deployed Open Terminal gives agents file, shell and code tools, including analysis and chart creation. - URL: https://docs.openwebui.com/features/open-terminal/ - Locator: Agent loop; Data analysis; Document processing - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### glean:glean:mcp About Glean MCP server. Glean exposes enterprise search, chat, documents and agents to external hosts through MCP. - URL: https://docs.glean.com/administration/platform/mcp/about - Locator: Server capabilities; authentication - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### glean:glean:core-price Glean Core Suite. Core Suite combines per-user monthly licensing with committed Model Hub consumption; the seat amount is not given. - URL: https://docs.glean.com/glean-core-suite-pricing - Locator: Seat fee; Model Hub Usage; provider rate table - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### open-webui:open-webui:api API endpoints. Authenticated APIs expose chat, tool use, file ingestion, knowledge attachment and model configuration export. - URL: https://docs.openwebui.com/reference/api-endpoints/ - Locator: Authentication; chat completions; tools; files; models export - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### open-webui:open-webui:hardening Hardening Open WebUI. Optional request logging has configurable bodies, path exclusions, file rotation and stdout output; deployment operators own log handling. - URL: https://docs.openwebui.com/getting-started/advanced-topics/hardening/ - Locator: Audit logging; output; path filtering; reverse proxy - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### glean:glean:mobile iOS and Android. Mobile clients use enterprise SSO and integrate with Intune App Protection. - URL: https://docs.glean.com/administration/management/features/mobile - Locator: SSO prerequisites; Intune MAM - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### glean:glean:surfaces Choose where to use Glean. Glean has web, desktop, extension and embedded access points. - URL: https://docs.glean.com/user-guide/apps/choose-where-to-use-glean - Locator: Surface table; browser; desktop; extension - Evidence kind: documented - Source date: 2026-10-19 - Retrieved: 2026-10-21 ### glean:glean:voice Use real-time voice. Real-time voice works on web, desktop and mobile; raw audio streams to the configured model provider while transcripts follow chat retention. - URL: https://docs.glean.com/user-guide/assistant/real-time-voice - Locator: Where to access; privacy; limitations - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### open-webui:open-webui:desktop-quickstart-r2 Open WebUI Desktop installation route. Quick Start links the native desktop distribution as a route without Docker/manual setup and recommends Docker or Python for production. - URL: https://docs.openwebui.com/getting-started/quick-start/ - Locator: Desktop App section and production-install note - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### open-webui:open-webui:desktop-readme-r2 Open WebUI Desktop v0.0.20 documentation. The pinned Desktop README labels the app Early Alpha, lists macOS/Windows/Linux installers and describes local execution or a connection to an existing server. - URL: https://raw.githubusercontent.com/open-webui/desktop/601137c5dec2967cfe173a6bf071fbbb460852be/README.md - Locator: Early Alpha; Download table; How It Works; System Requirements - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### open-webui:open-webui:desktop-release-r2 Open WebUI Desktop v0.0.20 release assets. The 2026-05-06 release includes macOS and Windows x64/ARM64 installers plus Linux packages; its notes describe a Linux blank-webview fix. - URL: https://api.github.com/repos/open-webui/desktop/releases/tags/v0.0.20 - Locator: published_at; assets[].name; release body - Evidence kind: documented - Source date: 2026-05-06 - Retrieved: 2026-10-21 ### open-webui:open-webui:pwa-r2 Open WebUI browser PWA installation. The web interface can also be installed as a desktop/mobile browser PWA; PWA notifications require it to stay open. - URL: https://docs.openwebui.com/getting-started/open-webui-as-app/ - Locator: Desktop browser installation; Android; iOS; notification limitation - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### glean:glean:teams-app Glean in Microsoft Teams: Admin guide. The Microsoft Teams app requires tenant admin setup and consent. - URL: https://docs.glean.com/administration/platform/embedded-integrations/glean-in-teams/glean-in-microsoft-teams--admin-guide - Locator: Installation prerequisites and deployment - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### open-webui:open-webui:notes Notes. Notes provide rich text and Markdown editing with AI rewrites and full-content attachment to chats. - URL: https://docs.openwebui.com/features/notes/ - Locator: Rich editor; AI editing - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### glean:glean:images Image Generation in Glean. Glean generates and edits images using enabled image models, independently of the text model. - URL: https://docs.glean.com/user-guide/assistant/image-generation - Locator: Model choice; editing; admin controls - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### glean:glean:terms Glean Terms of Service v5Jun2026. The contract defines customer-cloud hosting, restricted proprietary access, order-specific fees, termination deletion and New York governing law. - URL: https://www.glean.com/legal/terms - Locator: Sections 1, 2, 5, 12 and 13 - Evidence kind: documented - Source date: 2026-06-05 - Retrieved: 2026-10-21 ### glean:glean:ai-addendum Glean AI Addendum v5Jun2026. No-training commitments and Glean-key zero-day retention have legal and trust-and-safety exceptions; Customer Key responsibilities remain with the customer. - URL: https://www.glean.com/legal/ai-addendum - Locator: Sections 3 and 4 - Evidence kind: documented - Source date: 2026-06-05 - Retrieved: 2026-10-21 ### open-webui:open-webui:images Image generation. Image providers include OpenAI, Gemini, ComfyUI and AUTOMATIC1111. - URL: https://docs.openwebui.com/features/chat-conversations/image-generation-and-editing/ - Locator: Provider list - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### open-webui:open-webui:image-usage Generate and edit images in chat. Image generation and editing require configured providers, feature permissions and model capability toggles. - URL: https://docs.openwebui.com/features/chat-conversations/image-generation-and-editing/usage/ - Locator: Availability conditions; Editing; Compositing - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### open-webui:open-webui:voice Voice mode. Voice mode combines configured STT and TTS or a separately configured OpenAI-compatible realtime service. - URL: https://docs.openwebui.com/features/chat-conversations/chat-features/voice-mode/ - Locator: Standard mode; Realtime calls; Audio settings - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### glean:glean:team-chat Team chat. Beta shared Editor chats run each request as its author but expose already-generated answers to all participants. - URL: https://docs.glean.com/user-guide/assistant/team-chat - Locator: How permissions work; behavior and limits - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### open-webui:open-webui:channels Channels. Channels support multi-person collaboration and AI participation, with channel access controls. - URL: https://docs.openwebui.com/features/channels/ - Locator: Shared channels and direct messages - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### open-webui:open-webui:export Import and export. Users export their conversation history in documented JSON and can import compatible records. - URL: https://docs.openwebui.com/features/chat-conversations/data-controls/import-export/ - Locator: Exporting all chats; JSON schema - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### glean:glean:accessibility Accessibility Statement. Glean says a VPAT 2.5 ACR covering WCAG 2.0, 2.1 and 2.2 A/AA is available through its trust center. - URL: https://docs.glean.com/user-guide/about/accessibility - Locator: Conformance status - Evidence kind: documented - Source date: 2026-09-25 - Retrieved: 2026-10-21 ### open-webui:open-webui:i18n-pin Open WebUI locale registration. The pinned client registers English, German, French and Italian interface locales; this does not establish translation quality. - URL: https://raw.githubusercontent.com/open-webui/open-webui/91ea4e3421d1d8069f13d4a463fcb5986d94ea60/src/lib/i18n/locales/languages.json - Locator: src/lib/i18n/locales/languages.json, en-US, de-DE, fr-FR, it-IT entries - Evidence kind: source-inspected - Source date: Not stated - Retrieved: 2026-10-21 - Commit: 91ea4e3421d1d8069f13d4a463fcb5986d94ea60 - Path: src/lib/i18n/locales/languages.json ### open-webui:open-webui:r4-german-admin-translations Open WebUI v0.12.4 German translations. The distributed German translation file includes administrator and user-management labels. This establishes partial German admin localization, not completeness, naturalness or accessibility conformance. - URL: https://github.com/open-webui/open-webui/blob/33c1978d5bad52a31df75ea55143025dfad18d16/src/lib/i18n/locales/de-DE/translation.json - Locator: Admin Panel, Admin, Add User, Change User Role and settings entries - Evidence kind: source-inspected - Source date: 2026-10-25 - Retrieved: 2026-10-26 - Commit: 33c1978d5bad52a31df75ea55143025dfad18d16 - Path: src/lib/i18n/locales/de-DE/translation.json ### glean:glean:sso About Glean SSO. SSO is mandatory through OIDC or SAML; identity-provider policies enforce authentication conditions. - URL: https://docs.glean.com/administration/identity/sso/about - Locator: Mandatory SSO; identity providers; access controls - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### open-webui:open-webui:roles Roles. Admins can manage the system and normally bypass resource grants; environment controls can restrict product-level chat access. - URL: https://docs.openwebui.com/features/authentication-access/rbac/roles/ - Locator: Admin; User; Pending; privacy controls - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### open-webui:open-webui:sso SSO, OAuth, OIDC and trusted header. OAuth/OIDC providers and trusted authentication proxies support account creation and login-time group synchronization. - URL: https://docs.openwebui.com/features/authentication-access/auth/sso/ - Locator: Provider setup; OAuth group management; account creation - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### open-webui:open-webui:mfa Two-factor sign-in. Built-in authenticator-based sign-in can be required, with explicit configuration for OAuth bypass. - URL: https://docs.openwebui.com/features/authentication-access/mfa/ - Locator: Administrative configuration; OAuth bypass - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### open-webui:open-webui:scim SCIM 2.0 support. SCIM provisions users and groups; deactivation maps ordinary accounts to pending and ends live connections. - URL: https://docs.openwebui.com/features/authentication-access/auth/scim/ - Locator: Overview; User Operations; Deprovisioning; Group Operations - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### open-webui:open-webui:r7-scim-bearer-doc Open WebUI SCIM bearer authentication recheck. The guide configures SCIM through environment variables, including SCIM_ENABLED and SCIM_TOKEN bearer authentication. It documents no user-selectable token-scope control; account visibility rules are distinct from token scopes. - URL: https://docs.openwebui.com/features/authentication-access/auth/scim/ - Locator: Configuration; Environment Variables; SCIM API Configuration; Security Considerations - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-26 ### open-webui:open-webui:r7-scim-bearer-code Open WebUI v0.12.4 SCIM authentication. The pinned authentication function checks Bearer header format, whether SCIM is enabled, and a constant-time comparison with the configured SCIM_TOKEN. The inspected authentication path exposes no per-token selectable scopes. - URL: https://github.com/open-webui/open-webui/blob/33c1978d5bad52a31df75ea55143025dfad18d16/backend/open_webui/routers/scim.py - Locator: get_scim_auth, lines 251-297 - Evidence kind: source-inspected - Source date: 2026-10-25 - Retrieved: 2026-10-26 - Commit: 33c1978d5bad52a31df75ea55143025dfad18d16 - Path: backend/open_webui/routers/scim.py ### glean:glean:users Managing Users. Admins assign roles and feature permissions and can revoke user sessions. - URL: https://docs.glean.com/administration/identity/roles/manage-users - Locator: Member permissions; sign out all sessions - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### glean:glean:insights Insights overview. Adoption metrics and per-person activity are available; small departments are grouped and CSV export is documented. - URL: https://docs.glean.com/administration/insights/overview - Locator: Metrics; department filters; CSV; privacy - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### glean:glean:events Glean Customer Event log overview. Customer Event logs include chats and responses separately from administrative logs and export as an unfiltered stream. - URL: https://docs.glean.com/administration/gce-logs/data-dictionary - Locator: CHAT events; unified export stream - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### open-webui:open-webui:analytics Analytics. Admin analytics reports messages and provider-reported tokens by users, models and groups and exposes an export API. - URL: https://docs.openwebui.com/features/administration/analytics/ - Locator: User and model tables; Group filters; Export; Privacy - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### glean:glean:audit Audit Logs. Admin configuration logs have CSV export and 30-day default retention; ongoing delivery needs account-team configuration. - URL: https://docs.glean.com/administration/management/audit-logs/admin-audit-logs - Locator: Coverage; export; default retention - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### glean:glean:history Chat History. Admins choose Off or 30/90/180/365-day conversation retention, independently of Customer Event logging. - URL: https://docs.glean.com/administration/assistant/configuration/chat-history - Locator: Retention choices; Customer Event logs - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### open-webui:open-webui:security Enterprise security. The page describes deployment controls and states that compliance responsibility remains with the deploying organization. - URL: https://docs.openwebui.com/enterprise/security/ - Locator: Regulatory frameworks; data governance - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### glean:glean:pii Sensitive content in user prompt. Configured prompt-only regex policies can flag or block credentials, PII, IBANs and government IDs; built-in patterns start disabled. - URL: https://docs.glean.com/administration/protect/ai-security/sensitive-content-user-prompt - Locator: Prerequisites; regex templates; enforcement - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### glean:glean:protect About Glean Protect and Protect+. Protect+ adds recurring sensitive-content scanning and AI security guardrails to baseline Protect. - URL: https://docs.glean.com/administration/protect/overview - Locator: Capability comparison; AI security add-on - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### glean:glean:subprocessors Glean Subprocessors. The list names US providers and an Indian affiliate for remote support, security and debugging. - URL: https://www.glean.com/legal/subprocessors - Locator: Provider table; affiliate remote support - Evidence kind: documented - Source date: 2026-07-28 - Retrieved: 2026-10-21 ### open-webui:open-webui:filter Filter functions. Administrators can install custom Python filters in the model request path; behavior depends on the installed filter. - URL: https://docs.openwebui.com/features/extensibility/plugin/functions/filter/ - Locator: Filter lifecycle and extension examples - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### glean:glean:org-instructions Configure custom instructions. Admins can configure up to five enterprise instructions for Assistant. - URL: https://docs.glean.com/administration/assistant/configuration/custom-instructions - Locator: Five custom instructions - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### open-webui:open-webui:banners Customizable banners. Admins can display instance banners; a banner is not evidence of a mandatory recorded policy acknowledgement. - URL: https://docs.openwebui.com/features/administration/banners/ - Locator: Configuration and dismissible banners - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### glean:glean:regions Supported GCP regions. The GCP region list includes Netherlands, Belgium, Frankfurt and other regions, subject to required services. - URL: https://docs.glean.com/get-started/prepare/self-hosted-deployment/gcp/supported-gcp-regions - Locator: Preferred regions; EMEA - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### glean:glean:sla Glean Customer Support SLA v6Mar2026. Standard and paid Premium support differ; only Premium includes 99.9% monthly uptime and 10% or 20% service credits. - URL: https://www.glean.com/legal/sla - Locator: Sections 2, 4, 7 and 8 - Evidence kind: documented - Source date: 2026-03-06 - Retrieved: 2026-10-21 ### open-webui:open-webui:quickstart Quick start. The software is self-installable with Docker or Python and keeps state in customer-controlled storage. - URL: https://docs.openwebui.com/getting-started/quick-start/ - Locator: Docker; pip; data volume - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### glean:glean:dpa Glean Data Processing Addendum v6Mar2026. The DPA covers applicable Swiss and EU law, termination erasure, SCCs and 30-day subprocessor notice. - URL: https://www.glean.com/legal/dpa - Locator: Sections 1, 7, 9 and 10; SCC annexes - Evidence kind: documented - Source date: 2026-03-06 - Retrieved: 2026-10-21 ### glean:glean:r3-legal-index Glean legal. The index links both Business Associate Agreement forms, the Technical Services Addendum and named Outcomes Packages; inclusion and pricing depend on the applicable contract. - URL: https://www.glean.com/legal - Locator: Glean Customer Agreements and Policies - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### glean:glean:security-page Glean Protect security page. Glean claims SOC 2 Type II, ISO 27001 and ISO 42001; no issuer-scoped certificate was retrieved. - URL: https://www.glean.com/platform/security - Locator: Enterprise security and compliance badges - Evidence kind: vendor-claimed - Source date: Not stated - Retrieved: 2026-10-21 ### glean:glean:r4-aws-cmk-faq Glean customer-hosted AWS FAQ. Customer-managed CMKs are supported for AWS, although the FAQ recommends default AWS-managed KMS keys and documents SCP-based emergency controls. - URL: https://docs.glean.com/security/cloud-prem/aws/faq - Locator: Are customer managed keys supported? - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-26 ### glean:glean:r4-aws-key-control Glean AWS account access and deployment model. The customer-hosted AWS deployment guide says customers own and control KMS customer-managed keys used for data at rest. This does not establish key control for Glean Hosted or GCP. - URL: https://docs.glean.com/security/cloud-prem/aws/account-access-and-deployment-model - Locator: Customer controls - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-26 ### glean:glean:dpa-confidentiality Glean DPA. General DPA confidentiality binds authorized personnel and no-less-protective subprocessor agreements; no specific §203/Art321 undertaking was retrieved. - URL: https://www.glean.com/legal/dpa - Locator: Section4 authorized personnel confidentiality; section9 subprocessor written agreement and necessary access - Evidence kind: documented - Source date: 2026-03-06 - Retrieved: 2026-10-21 ### open-webui:open-webui:secrecy-access Open WebUI chat data access boundary. The privacy guide identifies application, infrastructure operators and configured model providers as content-access trust boundaries; admin UI controls do not remove infrastructure access. - URL: https://docs.openwebui.com/security/chat-data-privacy-and-encryption/ - Locator: Who Can Read Chat Data?; What Encryption Protects; informational-content disclaimer - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### open-webui:open-webui:secrecy-legal Open WebUI for law firms. The law-firm page describes customer-operated storage/routing and links technical guidance and US ABA materials; it is general product guidance. - URL: https://www.openwebui.com/legal - Locator: Materials for risk, KM, security, and legal ops review; FAQ: confidential matter information and uploaded files - Evidence kind: vendor-claimed - Source date: Not stated - Retrieved: 2026-10-21 ### open-webui:open-webui:secrecy-support Open WebUI enterprise support. Enterprise support describes advisory engineering access, dedicated channels and SLAs, with contractual commitments dependent on applicable terms. - URL: https://docs.openwebui.com/enterprise/support/ - Locator: Support Capabilities; Consulting Topics; For Procurement & Legal; informational-content disclaimer - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### glean:glean:flex-price Glean Enterprise Flex. Enterprise Flex pools credits and separately meters advanced features and premium models; learned-memory billing starts November 7, 2026 for the stated scope. - URL: https://docs.glean.com/glean-enterprise-flex-pricing - Locator: Enterprise Flex seats; FlexCredits; rate card - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### open-webui:open-webui:terms Terminals orchestrator. The separate per-user terminal orchestration layer requires an Open WebUI Enterprise licence for production. - URL: https://docs.openwebui.com/features/open-terminal/terminals/ - Locator: Prerequisites; Licensing - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### glean:glean:fx-ecb ECB historical euro reference rates. The 2026-10-20 reference is 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 ### glean:glean:r2-customer-default-example Change your default model on Customer Key. Customer Key admins choose defaults; GPT5.6 Luna is expressly an example, not a fixed or recommended routine model. - URL: https://docs.glean.com/administration/change-default-model - Locator: Opening note and prerequisites - Evidence kind: documented - Source date: 2026-10-19 - Retrieved: 2026-10-21 ### glean:glean:r2-direct-provider-proxy OpenAI direct API pricing. The shared direct-provider comparison uses USD0.10 input andUSD0.50 output per1M tokens; vendor usage is not replaced by this proxy. - URL: https://developers.openai.com/api/docs/pricing - Locator: Standard short-context gpt-6-luna - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### glean:glean:r2-proxy-lowest-effort GPT6 Luna model documentation. Lowest effort none is used only for the direct-provider comparison assumption. - URL: https://developers.openai.com/api/docs/models/gpt-6-luna - Locator: Reasoning effort - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### open-webui:open-webui: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 ### open-webui:open-webui: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 ### open-webui:open-webui: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 ### open-webui:open-webui: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 ### open-webui:open-webui: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 ### open-webui:open-webui:license-pin Open WebUI v0.12.3 licence. The pinned licence preserves notices and restricts branding changes, with exceptions for up to 50 rolling-30-day users, prior written permission or enterprise permission. - URL: https://raw.githubusercontent.com/open-webui/open-webui/91ea4e3421d1d8069f13d4a463fcb5986d94ea60/LICENSE - Locator: LICENSE, clauses 1-4; prior-licence reservation - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### open-webui:open-webui:desktop-license-r2 Open WebUI Desktop v0.0.20 licence. The separately packaged Desktop repository distributes GNU AGPL version 3 licence text at its v0.0.20 revision. - URL: https://raw.githubusercontent.com/open-webui/desktop/601137c5dec2967cfe173a6bf071fbbb460852be/LICENSE - Locator: LICENSE heading and GNU Affero General Public License version 3 text - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### open-webui:open-webui:chats-pin Open WebUI admin chat export implementation. The admin-only all/db route returns chat records when ENABLE_ADMIN_EXPORT is enabled. - URL: https://raw.githubusercontent.com/open-webui/open-webui/91ea4e3421d1d8069f13d4a463fcb5986d94ea60/backend/open_webui/routers/chats.py - Locator: backend/open_webui/routers/chats.py, get_all_user_chats_in_db, lines 1113-1117 - Evidence kind: source-inspected - Source date: Not stated - Retrieved: 2026-10-21 - Commit: 91ea4e3421d1d8069f13d4a463fcb5986d94ea60 - Path: backend/open_webui/routers/chats.py ### open-webui:open-webui:support Support and SLAs. Enterprise support advertises account management and engineering guidance, while hands-on implementation remains with the customer or integrator. - URL: https://docs.openwebui.com/enterprise/support/ - Locator: Account manager; Office hours; Consulting; guidance scope - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21 ### open-webui:open-webui:roadmap Open WebUI roadmap. Budget controls, broader localization and accessibility appear on an undated roadmap and are not treated as shipped guarantees. - URL: https://docs.openwebui.com/roadmap/ - Locator: In progress; Planned - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-10-21