Glean Release Notes

User Features

JSM request routing and field mapping in tools

Glean tools now support end-to-end Jira Service Management request flows, routing users to the right request type based on their intent and collecting required application, environment, and role details in the same experience. For IT and access requests, Glean first attempts to resolve issues with knowledge, and when a ticket is still needed it creates a JSM request pre-filled with the correct fields so requests are triaged and routed correctly. This update is designed for organizations with complex, asset-backed JSM forms so agents and field teams can rely on Glean to submit tickets that match their real service desk process.

How to access: Administrators must enable for your organization. To use this capability, connect Jira Service Management to Glean and enable the Jira tools in the admin console under Platform and then Actions. Configure the Create Jira Service Management request tool with your service desk, request types, and required application, environment, and role fields. Update existing IT or access agents to call this action so that user requests are routed through the configured JSM workflow.

Set up Jira Service Management request routing

Actions [ROAD-1492]

GitHub sync and import for skills (public repos)

Admins can now import and sync skills from public GitHub repositories into Glean. This makes it easier to manage shared skill libraries in Git and keep Glean up to date with community and open-source skills that follow the open agent skills standard.

Users can paste a public GitHub repo URL, and Glean will fetch compatible .skill and .md files for import. Imported repositories stay up to date through an hourly sync, and admins can view sync status or disable syncing for a repo at any time.

How to access: Administrators must enable for your organization.

Explore skills in Glean Assistant

Assistant [ROAD-1407]

Skills for Glean Assistant: personal (public beta), governance and sharing

Glean Skills lets teams package domain-specific expertise into reusable instructions that Assistant applies automatically to tasks like account planning, meeting prep, and knowledge base creation. Skills support the open agent skills standard — import compatible skills from OpenAI, Anthropic, Cursor, and more, then tailor them to how your organization works. With GA on June 18, 2026, admins can create, share, and govern skills across their organization with a draft-to-publish lifecycle, role-based admin controls, and deterministic conflict resolution between personal, shared, and admin-published skills. The unified Capabilities library will follow in July 2026 as a separate surface for managing personal, shared, ecosystem, and admin-published skills.

How to access: Administrators must enable for your organization. Admins can create and manage shared skills, assign Skill Admin roles, and govern org-wide skills through the Capabilities tab and admin console. End users can create personal skills and use shared and admin-published skills directly in Glean Assistant, with a privacy model that keeps private skills invisible to admins.

Explore skills in Glean Assistant

Assistant [ROAD-1149]

Autodesk Construction Cloud (ACC) connector

Glean now includes a native Autodesk Construction Cloud connector, so users can search and discover ACC project files, RFIs, submittals, drawings, issues, assets, and related project content directly in Glean while respecting source permissions. This helps construction, architecture, engineering, and owner teams find project knowledge faster, discover related work across projects, and support compliance, audit, and onboarding workflows from one place. This is an admin-gated connector for end users.

How to access: Administrators must enable for your organization. In the Glean admin console, go to Data sources and add the Autodesk Construction Cloud connector. Follow the setup flow in the connector configuration page to authenticate Autodesk Construction Cloud and complete the required admin configuration. After setup is complete, run the initial crawl so ACC content becomes available to users with the appropriate source permissions.

Set up the Autodesk Construction Cloud connector

Connectors [ROAD-1326]

Panopto connector

The Panopto connector enables organizations to seamlessly integrate Panopto video content into Glean, making it easy to search, discover, and reuse knowledge stored in training videos, recorded meetings, and other video assets.

How to access: Administrators must enable for your organization. A Glean admin must add Panopto as a connector in the Glean admin console.

Set up the Panopto connector

Connectors [ROAD-1002]

Brave web search: freshness support for time-sensitive queries

Brave web search now scopes time-sensitive queries to fresher results, so questions about what is happening today, this week, or this month return up-to-date web pages instead of stale content. For customers using the Brave web search provider, Assistant only applies a recency window when the query clearly asks for current or recent information, improving relevance while keeping timeless facts unchanged. There are no new toggles or admin controls for this behavior; once Brave web search is enabled, freshness is on by default.

Configure Brave web search in Glean

Actions [ROAD-1514]

Claude Sonnet 5 in Assistant and agents

Claude Sonnet 5 is now available in Glean Assistant and agents.

How to access: Glean admins can enable Claude Sonnet 5 in the model hub.

This feature may be subject to usage-based pricing. Learn more in Glean's Help Center.

Agents [ROAD-1546]

Autonomous agent compiler: persistent chat sessions across page refreshes

Compiler chat persistence in the autonomous agent builder keeps your conversation history when you refresh the page or reopen an agent, so you don't need to re-explain context or repeat earlier steps. When you return to an agent, Glean automatically restores your latest compiler chat for that agent, and a Reset chat control lets you start a fresh conversation while previous sessions stay available in history. This improvement is available to all agent builders.

Learn about compiler chat persistence

Agents [ROAD-1513]

Artifacts support in agents

Enables artifacts in agents so they can generate rich outputs instead of only plain chat responses. Supports all artifact types that are enabled in Assistant.

This feature may be subject to usage-based pricing. Learn more in Glean's Help Center.

Work with artifacts in Assistant

Agents [ROAD-1458]

Navigate admin features more efficiently with a new streamlined left navigation and user menu

Updates to the left navigation and user menu now make it easier for admins to find valuable insights. The admin console now lives in the user menu, Insights has its own navigation path, and the updated user section improves admin accessibility.

Explore admin navigation and chat history

Assistant [ROAD-1467]

Take actions through real-time voice — send emails, post messages, create events, and more

You can now take actions directly through real-time voice — send emails, post Slack messages, create calendar events, file Jira tickets, and more, all by speaking. Say what you want to do, confirm with your voice, and Glean handles the rest. Voice actions work with all the same tools and integrations you already use in chat, so there's nothing new to set up.

This feature may be subject to usage-based pricing. Learn more in Glean's Help Center.

Explore real-time voice in Glean

Assistant [ROAD-1370]

O365 federated search: container filter facets and GST facet parity

O365 federated search now supports container filters for SharePoint and OneDrive, so users can scope queries to specific sites, libraries, lists, or folders and get precise, bounded live results. This closes a parity gap with indexed search and keeps behavior fail-closed instead of broadening the search when a container cannot be resolved. The feature applies to tenants using O365 SharePoint and OneDrive connectors with federated search enabled and requires admins to enable the container filter setting on those connectors and ensure live mode is turned on.

How to access: In the admin console, open each O365 SharePoint and OneDrive connector and enable the container filter option for federated search. Ensure O365 live mode is enabled for those connectors. After saving these changes, container-scoped queries from the Glean Search Tool and agents will automatically use O365 container filters.

Enable O365 federated search container filters

Connectors [ROAD-1459]

Enable Glean-managed MCP servers by default for customers

Glean Remote MCP Server is becoming much easier for admins to roll out and manage. Glean is enabling the Glean Remote MCP Server for customers by default with OAuth. This makes it easier for users to access Glean in supported AI tools without requiring admins to enable the remote MCP server manually.

How to access: The Glean Remote MCP Server is now enabled by default with OAuth for all customers. No manual admin setup is required. Users can connect to the remote MCP server from any supported AI tool using their existing Glean credentials.

This feature may be subject to usage-based pricing. Learn more in Glean's Help Center.

Enable the Glean Remote MCP Server

Connectors [ROAD-1397]

Choose search as your default setting in Assistant

You can now choose what happens when you press Enter in the Assistant chat bar. By default, pressing Enter still starts a new chat and Option/Alt+Enter starts a search. Users now have the option to change their personal settings so Enter starts a search and Option/Alt+Enter starts a new chat.

Customize your Assistant chat settings

Assistant [ROAD-1479]

Admin Features

Bulk agent cleanup: admin-driven inactive-agent identification and bulk delete (and Lifecycle API)

Admins can now clean up inactive agents at scale with a self-serve bulk deletion flow. From the admin console, go to Agents → Manage, where they can export an inactive-agents CSV, review which agents are unused, and soft-delete them in bulk from the admin console while preserving a 60-day restore window.

Delete and restore agents as an admin

Agents [ROAD-1453]

Original source

User Features

Turn your ideas into documents, slides, diagrams, or infographics in one click

Turn a single idea into anything you need: a document, slide, infographic, image, web page, or diagram. With the Convert button, you can capture your thinking once, then instantly transform it into lightweight, interactive experiences that live right alongside your work in Glean. Your content becomes the single source of truth, while Glean dynamically generates rich, visually engaging views. You can find the Convert button on the bottom of any chat message or at the top right of any artifact, allowing you to seamlessly switch between whatever artifact you need to get the job done.

How to access: Administrators must enable for your organization. This feature may be subject to usage-based pricing. Learn more in Glean's Help Center.

Learn more

Assistant [ROAD-962]

Interactive artifact editing with component selection

You can now edit individual components within HTML artifacts directly in Canvas. Click Edit in the top-right navigation, select any element in an artifact, and describe what you want changed. Assistant regenerates the component while keeping the rest of the artifact intact.

Learn more

Assistant [ROAD-1457]

Full-screen artifact composer for iterating with Glean

You can now keep working with AI when viewing artifacts in full screen. A chat composer appears directly in the full-screen view so you can request edits, ask questions, and iterate without switching back to the side-by-side layout. If you prefer a clean view, minimize the composer and it stays out of the way for that session.

This feature may be subject to usage-based pricing. Learn more in Glean's Help Center.

Learn more

Assistant [ROAD-1439]

Queued edits for documents in Canvas

You can now leave comments throughout a document in Canvas, just like you would in Google Docs or Word, and have Glean resolve them all in one go. Read through the draft, drop feedback on each section that needs work, and when you are ready, click Apply All. Glean revises the entire document in a single pass, addressing every comment together instead of making you issue follow-up edits one at a time.

This feature may be subject to usage-based pricing. Learn more in Glean's Help Center.

Learn more

Assistant [ROAD-1438]

Create documents via real-time voice

You can now create documents entirely through voice. Just speak your request and Glean builds the document in real time, the same way it does in text chat. Whether you are drafting a project brief hands-free or working while multitasking, voice document creation lets you produce polished content without typing a single word.

This feature may be subject to usage-based pricing. Learn more in Glean's Help Center.

Learn more

Assistant [ROAD-1372]

Try agents in Auto Mode: one-click workflow-to-Auto-Mode conversion for agent builders

Agent builders can now use Try in Auto Mode to convert an existing workflow agent into a new Auto Mode draft in a single click, without changing the original agent. The conversion uses the latest agent compiler to translate tools, triggers, knowledge sources, sub-agents, and permissions so you can compare behavior side by side and migrate when you're ready. This makes it easier to move production workflows onto Auto Mode for stronger reasoning, less brittle orchestration, and lower maintenance over time.

How to access: Administrators must enable for your organization. To use this feature, your organization must have Agents and Auto Mode agents enabled in Glean. Once enabled, open any existing workflow agent in the Agent library and choose Try in Auto Mode from the More actions menu to generate a new Auto Mode draft. Review and save the converted agent when you're ready to share it.

Learn more

Agents [ROAD-1497]

Revamped Agent Insights for admins and agent builders

Glean has revamped Agent Insights to make it easier to understand agent adoption, quality, and usage across your organization and for individual agents. The updated experience adds new views for time saved by agents, runs by outcome, top use cases, and voting feedback drill-down, while also replacing the older single-scroll page with a clearer shared dashboard and per-agent insights experience for builders. This helps admins spot adoption and quality trends faster, and helps agent builders diagnose issues and improve their agents with more actionable insight.

Learn more

Admin Capabilities [ROAD-1320]

GPT-5.4 as default for new autonomous agents

New Auto Mode agents are now created with GPT-5.4 as the default model for Glean Key customers. Existing autonomous agents will continue to use GPT-5.1 as their default model.

This feature may be subject to usage-based pricing. Learn more in Glean's Help Center.

Learn more

Agents [ROAD-1330]

Rename all actions to tools in Glean

Glean is evolving its connector terminology to reflect that connectors can both read from and write to enterprise applications. As part of this update, we are replacing the term "action" with "tool." A tool represents a discrete capability, whether that's querying data, invoking an API, updating a system, or running a computation. This change better reflects the expanded role of connectors and aligns with industry terminology, including MCP, which uses tools as the standard abstraction for capabilities exposed to AI systems.

Learn more

Actions [ROAD-1460]

MCP Gateway: invoke all 2,000+ tools externally via Claude Code, Cursor, ChatGPT, and other MCP hosts

Glean will expose all supported read tools through MCP so users can access fresh data from connected apps in tools like Claude Code, Cursor, ChatGPT, and other MCP hosts. This gives users a more consistent way to retrieve live information across MCP-connected sources without leaving their preferred AI tool. This feature is admin gated and may be subject to usage-based pricing.

How to access: Administrators must enable for your organization. This feature may be subject to usage-based pricing. Learn more in Glean's Help Center.

Learn more

Tools [ROAD-1282]

Admin Features

LLM admin refresh for Customer Key customers

Customer Key admins now get a refreshed LLM Admin experience that groups models by hosting provider and adds clear capability indicators across Assistant and Agents. You can configure provider-hosted LLMs through the updated Add LLM flow, manage which models are enabled, and block models separately for Assistant or Agents without disabling them globally. Default text models (large, small, agentic, fast agentic) must stay on a single provider, while image generation can use a different provider to match your contracts and architecture. This update brings Customer Key deployments closer to parity with the Glean Key model-management refresh while preserving CK-specific provider controls.

How to access: When the feature is available in your deployment, go to Admin console → Platform → LLMs. On Customer Key deployments, admins can use the refreshed LLM page to add providers, manage model availability, configure default models, filter by capability, and manage surface-level blocked models from Assistant → Settings and Agents → Setup.

Learn more

Admin Capabilities [ROAD-1475]

Turn slide generation on by default for all users

Slide generation in Assistant will be enabled by default for all customers no earlier than June 8, 2026. To keep it off or limit access, select Off or On only for admins. Your choice will be respected, and you can change it anytime. If you have already enabled slide generation On, no action is needed.

If your company has a slide template configured, Glean will use it automatically. If not, Glean will take styling inspiration from your company's existing visual assets so decks still feel on-brand.

How to access: Admins can access this toggle by navigating to Admin console → Assistant → Settings → Slide deck generation. This feature may be subject to usage-based pricing. Learn more in Glean's Help Center.

Learn more

Assistant [ROAD-1377]

Web Crawler configurable OAuth token injection into non-standard auth headers

Adds configurable OAuth token header injection for the Web Crawler connector, so admins can route refreshed OAuth access tokens into a customer-defined HTTP header instead of only Authorization: Bearer <token>. This removes brittle manual token minting workflows and makes it easier to support sites that expect non-standard auth headers, starting with MongoDB and similar integrations. Available for admins configuring Web Crawler connectors that use OAuth-based authentication.

How to access: From the Admin console, open your existing Website data source or create a new one. Under Advanced → OAuth, set the OAuth header name and, optionally, OAuth token prefix fields to match the header your downstream system expects. Save your changes and run a test crawl to confirm the header is being applied. No additional configuration is required outside the Web Crawler connector.

Learn more

Connectors [ROAD-1399]

Veeva Vault connector

Glean now includes a native Veeva Vault connector, so admins can make Veeva Vault quality documents searchable in Glean while preserving Veeva permissions. The connector indexes documents and associated permissions, stores searchable metadata like document type, subtype, classification, and status, and can surface additional Vault fields as searchable custom fields when available. This helps teams find regulated quality content faster in search while keeping access aligned with what users can see in Veeva Vault.

How to access: Admins can enable the connector by going to Admin console → Data sources → Add data source → Veeva Vault, then entering the Vault URL, integration username, and password. In Veeva, the setup requires either Vault Owner/System Administrator access or a dedicated Glean Integration profile, plus Dynamic Access Control so the Glean integration user can access only the allowed document types and steady-state lifecycle states.

Learn more

Connectors [ROAD-1042]

Original source

User features

Store memories in Glean from any MCP-connected tool

Connected MCP host applications such as ChatGPT, Claude, Cursor, VS Code, and Copilot can now write memories back to Glean in addition to reading them. You can add, update, and delete memories from any MCP-connected tool, and those memories are stored in Glean with full source provenance. This means the context you build while working in your IDE or AI assistant is available everywhere Glean memory is used. Admins can enable or disable memory write operations per deployment in Admin console → Platform → Glean MCP server.

How to access: Memory write operations are enabled by default on the Glean MCP server. No additional setup is required.

Learn more

Assistant ROAD-1261

New Google and Microsoft actions

Glean Assistant can now help you complete more work across Google Workspace, Microsoft 365, Slack, and Microsoft Teams, so you can move from answers to action without switching tools. You can draft emails, create docs and spreadsheets, and send messages in the apps your team already uses, helping you finish common workflows like status updates, stakeholder communications, and tracker updates faster. Admins must first configure the relevant action packs for Google, Microsoft 365, and Slack before these options appear for users.

How to access: Administrators must enable for your organization. Admins must enable the relevant action packs in Admin console → Platform → Actions before users can access these capabilities. To support Google Docs, Google Sheets, and Gmail drafts, set up Google actions and connect the Google Drive data source. To support Outlook, Word, Excel, and Microsoft Teams actions, set up Microsoft 365 actions and link them to your Microsoft 365 data source; some Microsoft environments will require admin consent before users can connect successfully.

Learn more

Actions ROAD-1194

Update Salesforce opportunities from Glean Assistant

Sales teams can now update Salesforce opportunities directly from Glean Assistant using natural language, without switching into the Salesforce app. When a user asks Assistant to change key opportunity fields—such as amount, stage, close date, or forecast category—Assistant identifies the correct record, collects any missing details in a structured way, and writes the updates back to Salesforce while honoring the user's permissions. Assistant then confirms the change and links to the updated opportunity so sellers can review and move on to their next task faster.

How to access: Administrators must enable for your organization. To use Salesforce opportunity write actions, your organization must have the Salesforce data source connected in Glean with API access to Opportunities and related objects, using the standard Salesforce connector. In the Glean Admin console, go to Platform → Actions and ensure the Salesforce action pack and the Update Opportunity write action are enabled for your deployment. End users will need to authenticate their own Salesforce account in Glean when prompted, so Assistant can respect per-user Salesforce permissions for viewing and updating opportunities. Once configured, users can simply ask Glean Assistant to update an opportunity in plain language and confirm the proposed changes in chat.

Learn more

Actions ROAD-1156

Editing for slides and image collections

You can now edit slides and image collections by annotating exactly what you want changed and asking Glean to regenerate the result with AI. Mark up a single image or a full set, describe the change in plain language, and get updated visuals without starting from scratch.

How to access: Administrators must enable for your organization.

This feature may be subject to usage-based pricing. Learn more in Glean's Help Center.

Learn more

Assistant ROAD-1402

Manually refresh interactive artifacts

You can now manually refresh interactive content in Glean to update the underlying data while keeping the existing layout and design intact. This is especially useful for dashboards and other data-driven pages that need fresh information without rebuilding the page from scratch. Each refresh creates a new version and shows when the content was last refreshed.

How to access: Administrators must enable for your organization.

This feature may be subject to usage-based pricing. Learn more in Glean's Help Center.

Learn more

Assistant ROAD-1343

Glean Assistant Meeting Notes

Glean Assistant Meeting Notes captures and transcribes your meetings, then generates an AI summary with key decisions and action items after the meeting. Transcripts and summaries are indexed in Glean and surfaceable through search and chat. It's designed to reduce the manual work of note-taking, speed up follow-ups, and help teams get answers to difficult questions without losing momentum in the conversation.

This is a desktop Mac-only feature available for Glean Key customers. Admins can control the rollout of this feature to their end users from Admin console → Assistant → Meeting Notes. The default setting lets Glean manage the rollout: "Meeting Notes" is off by default and will be turned on for users no earlier than June 8, 2026. We recommend starting with "On only for admins"; if you like it, you can turn it on for everyone in your organization at any time, or select "Off" to opt out. Your choice can be changed at any time and will not be overwritten. This feature may use credits. Learn more in Glean's Help Center.

How to access: Administrators must enable for your organization. We enabled admin configuration on May 7, 2026. Admins will be able to opt in.

We'll notify admins on May 20, 2026 about the feature and that they can opt in. GA and billing start for customers who opt in starting May 21, 2026.

We will default enable anyone who did not disable during the notice period on June 8, 2026.

This applies only to desktop users on Mac.

This feature may be subject to usage-based pricing. Learn more in Glean's Help Center.

Learn more

Assistant ROAD-769

Azure DevOps repository, pull requests, and code indexing

Glean now indexes Azure DevOps repositories, code files, commits, and pull requests, so engineering teams can search code and use Assistant to find relevant files, recent changes, and PR context in one place. This also adds permission-aware crawling for Azure DevOps code content using native project and repository ACLs.

How to access: Administrators must enable for your organization. In the Glean Admin console, open your Azure DevOps data source and review any setup warnings or validation alerts to make sure the service principal has been granted access to repositories. If you use Microsoft 365 identity mapping for Azure DevOps permissions, make sure your O365 connector is configured and healthy so indexed content appears correctly in search.

Learn more

Connectors ROAD-1246

Glean Assistant can now query Snowflake with natural language

Glean Assistant can now query Snowflake directly so users can ask questions in natural language or run SQL against approved projects and datasets, without leaving Assistant. This makes Glean a front door to your Snowflake data warehouse so business users get governed, self-serve access to live data while data teams stay in control of what is exposed and how it is queried.

How to access: Administrators must enable for your organization.

Learn more

Connectors ROAD-1166

Claude Opus 4.8 in Assistant and Agents

Claude Opus 4.8 is now available in Glean Assistant and Agents. Opus 4.8 is Anthropic's latest premium model for tasks involving code generation and agentic workflows.

How to access: Glean-hosted customers can select Claude Opus 4.8 directly in Assistant and Agents where model choice is enabled. If your organization manages model availability centrally, admins can make Claude Opus 4.8 available to end users and agent builders through model configuration in Glean.

This feature may be subject to usage-based pricing. Learn more in Glean's Help Center.

Learn more

Agents ROAD-1465

Gemini 3.5 Flash in Assistant and Agents

Gemini 3.5 Flash is now available in Glean Assistant model choice and in the Agents model hub. Gemini 3.5 Flash offers significantly better cost efficiency than larger frontier models while maintaining strong reasoning for well-scoped agent tasks.

How to access: Glean Universal Model Key: Gemini 3.5 Flash appears automatically in the Assistant model choice dropdown and Agents model hub. Admins can exclude it via Admin console → Platform → Models.
Customer Key: Gemini 3.5 Flash is available via Admin console → Platform → Models.

This feature may be subject to usage-based pricing. Learn more in Glean's Help Center.

Learn more

Agents ROAD-1445

Persistent permissions for tool use

You can now control exactly how Glean uses your connected tools with persistent permissions. Set any action to "Always Allow," "Ask," or "Block" — and your preference sticks across every session, whether you are in Assistant, Agents, or MCP. A new Connectors pane in your settings gives you a single place to see which apps you have connected, manage authentication, and fine-tune permissions for each tool individually.

Learn more

Agents ROAD-1368

Dictation in Assistant composer

You can now use your voice to compose messages in Glean Assistant. Dictation is back with a redesigned experience and a significantly upgraded transcription model supporting 98 languages — with high-accuracy results for dozens including English, Spanish, Chinese, and many more. Tap the microphone icon in the composer on web, desktop, or mobile, speak naturally, and your words appear as editable text. Perfect for capturing long thoughts, drafting on the go, or working in your preferred language.

Learn more

Assistant ROAD-1456

Greenlist application URLs for functional buttons in HTML artifacts

Interactive artifacts can now include functional buttons that link directly to your work applications — like Google Docs, Salesforce, Jira, or any other approved application. When you generate an interactive page with action buttons, those buttons actually take you to the tool where you need to act. Non-approved applications will still be accessible after a user clicks through a confirmation modal.

This feature may be subject to usage-based pricing. Learn more in Glean's Help Center.

Learn more

Assistant ROAD-1437

Save chats started from the Glean browser extension sidebar in chat history

Chats started from the Glean browser extension sidebar can now be saved in chat history, making it easier to revisit in-context conversations across sessions. This reduces repeated questions and gives users a more consistent experience between the extension and the main Glean chat experience. It is intended for end users of the browser extension.

Learn more

Assistant ROAD-1317

Build, edit, and share spreadsheets in Glean Assistant

Create and work with spreadsheets directly in Glean canvas. Upload a spreadsheet or ask Glean to generate one from scratch, then sort, filter, edit cells, and refine it through follow-up prompts without leaving the conversation. You can also export your sheet to Excel or copy it into other tools.

This feature may be subject to usage-based pricing. Learn more in Glean's Help Center.

Learn more

Assistant ROAD-1300

Support zip file analysis in Glean Assistant

You can now upload and analyze .zip files directly in Glean Assistant in thinking mode. Whether you're working with bundled documents, code packages, or compressed datasets, just drag and drop your zip file into the composer and start asking questions about its contents.

This feature may be subject to usage-based pricing. Learn more in Glean's Help Center.

Learn more

Assistant ROAD-1268

See MCP usage and adoption in Insights

Admins can now see MCP usage insights in Glean, making it easier to understand adoption and activity across MCP-connected experiences. This gives admins clearer visibility into how people are using MCP, including usage metrics that teams had previously been tracking outside the product.

Learn more

Embedded Integrations ROAD-1126

Admin features

LLM admin refresh for Glean Key customers

Admins get a clearer, more precise way to manage model availability for Glean Key deployments, including per-model toggles and surface-specific restrictions for Assistant and Agents. This improves governance for model access and makes the admin experience easier to understand and operate.

Learn more

Admin Capabilities ROAD-1404

MCP insights

Admins can now see how their organization is using Glean MCP directly in Insights, with visibility into adoption and activity across connected MCP hosts and tools. This helps teams understand which apps are driving value, identify active users, and track MCP usage without relying on manual reporting or backend logs. This feature is for admins only.

How to access: Open the Insights page in the Glean Admin experience to view MCP usage and adoption data. No additional setup is required beyond having Glean MCP enabled for your deployment. If MCP has not been enabled yet, first turn on the Glean OAuth Authorization Server under Users and permissions → Third-party access (OAuth), then enable Glean MCP server under Platform → Glean MCP server.

Learn more

Admin Capabilities ROAD-1329

Turn slide generation default on for all users

Slide generation in Assistant will be enabled by default for all customers no earlier than June 8, 2026. To keep it off or limit access, select "Off" or "On only for admins". Your choice will be respected, and you can change it anytime. If you have already enabled slide generation "On", no action is needed.

If your company has a slide template configured, Glean will use it automatically. If not, Glean will take styling inspiration from your company's existing visual assets so decks still feel on-brand.

How to access: Admins can access this toggle by navigating to Admin console → Assistant → Settings → Slide deck generation.

This feature may be subject to usage-based pricing. Learn more in Glean's Help Center.

Learn more

Assistant ROAD-1377

Original source

Admin Features

Merge Microsoft 365 connector set up

Admins can now set up Microsoft 365 connectors for SharePoint and OneDrive through a shared Microsoft 365 setup flow, which reduces duplicate configuration and makes setup easier to manage.

This change is for admins only and currently applies to SharePoint and OneDrive only — Outlook and Teams are not included in this launch.

The new flow introduces shared/common settings at the Microsoft 365 level, while SharePoint- and OneDrive-specific configuration remains in their respective child setup flows.

Admins should be prepared to complete the Microsoft 365 parent setup first, then finish any SharePoint- or OneDrive-specific permissions and settings needed for each connector.

How to access: In the Admin Console, start with the new Microsoft 365 connector setup, which now acts as the shared parent setup for SharePoint and OneDrive.

After completing the Microsoft 365 setup, finish configuration for SharePoint and/or OneDrive in their child setup flows, including any connector-specific permissions, domains, certificates, or REST API setup required for your environment.

If you already use SharePoint or OneDrive, review the updated setup documentation because credentials and shared authentication are now handled through the Microsoft 365 parent flow rather than as fully separate standalone setups.

Learn more

Admin Capabilities [ROAD-997]

Sensitive content models: Find the signal in the noise

Glean’s sensitive content models separate the signal from the noise by pairing traditional infotype detection with AI models trained on your full enterprise context, such as document content and permissions, to surface true exposure. Each finding receives a low/medium/high severity label with plain-language explanations. Our sensitive content models reduce false positives and achieve about 80% accuracy rate on unstructured data. Both GCP and AWS are supported.

How to access: Available in Glean Protect+. Super admins or Sensitive Content Moderators can go to Admin Console → Glean Protect → Sensitive findings → Policies, then create or edit a policy and select Enable document analysis.

Learn more

Protect [ROAD-753]

User Features

Auto mode agents powered by natural language

Auto Mode agents are now generally available, featuring a redesigned natural language agent builder where you simply describe what you want, answer a few guided questions, and reach a testable first draft faster than ever — with full control to refine as you iterate. This release also introduces debug and trace views for step-by-step visibility into agent behavior, and an agent sandbox for dynamic context management and code execution on complex tasks. From idea to production-ready agent, faster — with more power, transparency, and flexibility built in from the start.

This feature may be subject to usage-based pricing. Learn more in Glean's Help Center.

How to access: Administrators must enable for your organization.

Learn more

Agents [ROAD-730]

Nested Container Search in Chat/Agents

Chat and Agents can now search within tagged folders, spaces, sites, and other containers more effectively, including content nested inside subfolders. This helps users get more complete, relevant answers from large containers without having to sift through top-level contents first, and improves performance by focusing only on matching documents. This applies to Assistant (Chat with AL), Agents Plan and Execute, Agents Autonomous mode, and the Agents Company Search step. It does not change Chat V2 or workflow agents.

How to access: Once this feature is available in your environment, users can start tagging supported container URLs in Chat or using supported container sources in eligible Agent steps. If your team manages custom search configuration, make sure co.gsto.enable_container_filter is enabled. No other admin setup is required.

Learn more

Agents [ROAD-1362]

View images in Assistant and Agents for custom datasources

Assistant and Agents can now caption, index, and render images from content ingested through custom data sources, not just native connectors. This helps people get more complete answers from proprietary document repositories when diagrams, charts, screenshots, or other visuals are important to understanding the source content.

How to access: Administrators must enable for your organization.

Learn more

Agents [ROAD-1314]

Model Choice in Assistant for Customer Key

Customers on their own LLM key now have access to model choice drop down in Glean Assistant where they can select from a variety of models their organization has enabled.

How to access: Administrators must enable for your organization.

Learn more

Assistant [ROAD-1288]

Blocked Chat Status Indicator

Chat status indicators make it easier to keep work moving in Glean by showing which conversations need your attention, including chats with new updates, chats that are ready for review, and chats where an agent is waiting on your confirmation or additional input. This helps users quickly return to long-running or asynchronous work when results are ready.

Learn more

Assistant [ROAD-1367]

See step-by-step elapsed time in Assistant plans

Glean Assistant now shows the elapsed time for each step while it works through a multi-step plan, so you can better understand progress and how long each part of a task takes. This makes longer-running work more transparent and helps you decide whether to wait, redirect, or refine the request. This is available to all end users in Assistant when a plan is shown for complex, multi-step queries in Thinking mode.

How to access: No setup is required. The elapsed time appears automatically in Glean Assistant when a complex query triggers a plan in Thinking mode.

Learn more

Assistant [ROAD-1327]

Sigma connector

Connect Sigma to Glean so users can search and discover Sigma dashboards, workbook pages, and chart elements directly in Glean. This helps teams get to the right BI content faster, brings more analytics context into Glean, and respects Sigma permissions.

How to access: Administrators must enable for your organization.

Learn more

Connectors [ROAD-1192]

Addition of boards and work items to Azure Devops connector

Glean now supports indexing for Azure DevOps boards and work items, including Epics, Features, Stories, Tasks, and Bugs. This enhancement enables users to search for project status and work items from Azure DevOps directly within Glean, streamlining project tracking.

How to access: Administrators must enable for your organization.

Learn more

Connectors [ROAD-914]

Glean app in ChatGPT

Automatically connect to Glean within ChatGPT apps with a single click of a button. You can get full enterprise context in OpenAI ChatGPT.

How to access: Admins must first configure the Glean MCP connector in ChatGPT and enable both Glean OAuth and Glean MCP servers in the Glean Admin Console. After setup, end users can open a ChatGPT conversation, click the plus icon, open More, and select Glean to activate it for that conversation.

Learn more

Embedded Integrations [ROAD-1111]

Original source

Admin Features

Add Glean usage logging across GCE and Insights

Admins can now track Glean usage more consistently across Glean Customer Event Logs and Insights, making it easier to audit activity, analyze adoption, and answer questions about who used Glean, when, and where. Glean Customer Event Logs are designed to capture key user actions for analytics and reporting, including searches, chats, feedback, and workflow activity. This improves visibility for reporting, debugging, and downstream analysis across Glean surfaces.

How to access: Admins can use Glean Customer Event Logs to analyze usage activity and build custom reporting workflows. By default, these logs are written as a unified glean-customer-event stream to storage in your Glean project, and are typically loaded into a data warehouse such as BigQuery or Athena for analysis. Admins can also use Insights in the Admin console to review adoption and usage trends, including the Overview tab and Insights chat for natural-language analysis of platform usage.

Learn more

Admin Capabilities [ROAD-1281]

Add IdP-level permissions for Agent Scheduling

Admins can now control access to Agent Scheduling with identity provider groups, not just individual users. In Admin console → Platform → Agents → Scheduled triggers, you can add Google Groups or Azure AD / Entra ID groups alongside individual users, so the right teams can schedule agents without manual user-by-user setup.

How to access: To use this feature, go to Admin console → Platform → Agents → Scheduled triggers and turn scheduled triggers on for everyone or some users. If you choose a limited rollout, add individual users or supported IdP groups from Google Groups or Azure AD / Entra ID to the access list; members of those groups will inherit scheduling access automatically.

If your scheduled agents need to send outputs automatically, also configure the relevant action packs to allow Run without user confirmation for agents; otherwise, background runs can't use those actions.

Learn more

Admin Capabilities [ROAD-1219]

Model Insights for Customer Key Admins (BYOK)

Customer Key admins can now use LLM Insights in Glean to monitor Glean-attributed LLM usage and reliability, helping them provision capacity and troubleshoot issues with more confidence. The dashboard shows key metrics like peak and average TPM, peak RPM, 429 rate, and 5xx rate, with model-level breakdowns so admins can distinguish quota pressure from provider instability faster.

This release is available only for Customer Key (BYOK) deployments in v1, and it is not available for Glean Key deployments. Data updates once daily, may be delayed by up to 24 hours, and is intended for trend analysis and capacity planning rather than real-time monitoring or billing reconciliation.

Learn more

Assistant [ROAD-1280]

Glean Agentic Search Model [Glean Key, Glean Hosted Only]

Glean's Agentic Search Model is a retrieval-optimized model that runs before the frontier model on eligible Assistant queries. It first gathers the most relevant enterprise context, then passes that evidence to the frontier model so responses are faster, better grounded, and more efficient.

In testing, this architecture delivered roughly 50% lower latency with no regression in answer quality or satisfaction.

Available for customers hosted by Glean on GCP using the Glean Universal Model Key. Not applicable to AWS, Azure, customer-managed key deployments, or EU customers.

Learn more

Assistant [ROAD-1250]

Agent alignment check for write actions

Glean Protect now has an agent alignment check before agent write actions run, helping detect unsafe or misaligned actions before they can make changes in connected systems. This strengthens protection for higher-risk agent workflows, especially background and automatically triggered agents, where write actions can run without per-run approval. When configured in flag-for-review mode, potential violations are logged in the Findings dashboard so admins can investigate without interrupting the run.

How to access: Admins can manage AI security policies in the Admin console under Glean Protect → AI security → Policies. From there, they can choose which agent types a policy applies to, including Automatically triggered agents, and set the enforcement action to Flag for review so issues appear in the Findings tab for triage.

Learn more

Protect [ROAD-811]

User Features

In-line previews for write actions in Assistant

Assistant now shows a richer in-line preview before a write action runs, so users can quickly understand what will happen before they create, update, or post anything. The preview surfaces key parameters in a compact, human-readable card and uses a clearer action button such as Create, Update, or Post, which makes actions feel more transparent, predictable, and safer to use without breaking conversation flow.

How to access: Write actions in Glean let users complete tasks like creating tickets, updating records, sending messages, or exporting content directly from a conversation. In the Glean web app, write actions can pause for review before they run, and for supported actions users can review and edit fields or content inline before saving the change. Access depends on your organization having the relevant actions enabled and authenticated in the Glean Admin console, and actions always respect the user's existing permissions in the connected application.

Learn more

Actions [ROAD-1193]

Glean agents support Snowflake Cortex Agents API

Glean is introducing new functionality enabling Glean agents to call Snowflake Cortex agents to answer natural language questions over Snowflake‑governed data. The integration is powered by Snowflake's Cortex Agents REST API, so customers can reuse their existing agent orchestration, tools, and semantic models directly inside Glean.

How to access: Administrators must enable for your organization.

Learn more

Actions [ROAD-1056]

See contextual images in Glean Assistant responses (AWS customers)

Glean Assistant now displays relevant images from Google Drive and SharePoint documents alongside text responses when appropriate. This enhancement helps users better understand complex information by providing visual context directly in chat answers—no extra steps required. Images are shown only when relevant to the user's query, with full permissions enforced for every user.

This was previously released for GCP customers.

How to access: Administrators must enable for your organization.

Learn more

Agents [ROAD-916]

GPT 5.5 in Assistant and Agents

Glean now supports OpenAI GPT-5.5 in Assistant and Agents as a premium model. In Assistant, users can select GPT-5.5 from model choice. In Agents, builders can use GPT-5.5 in the Model Hub for supported agents and steps. GPT-5.5 is available for Glean Universal Model Key deployments and for Customer Key deployments through OpenAI, and premium model usage may consume FlexCredits or other usage-based charges based on your plan.

How to access: Administrators must enable for your organization. In the Admin console, go to Platform → LLMs and make sure GPT-5.5 is enabled in the Model Hub. For Assistant, users can then select GPT-5.5 from the model picker when model choice is available. For Agents, builders can choose GPT-5.5 as the default model in agent settings or for individual eligible steps in the canvas.

This feature may be subject to usage-based pricing. Learn more in Glean's Help Center.

Learn more

Agents [ROAD-1316]

Write tool previews, batch writes, and simplified auth in Assistant

Write tools in Glean now show a clear preview before they run, so users can review and approve changes before execution. This applies to both single-item and batch write flows. We also simplified tool auth to reduce setup friction for admins and end users.

This feature may be subject to usage-based pricing. Learn more in Glean's Help Center.

Learn more

Agents [ROAD-1299]

Additional SharePoint List support

Glean now supports indexing four additional types of SharePoint Lists: Discussion Board, Custom List in Datasheet View, Tasks, and Issue Tracking. This expands search coverage for content teams commonly use to manage discussions, track work, and organize operational data, making it easier for users to find more of their SharePoint knowledge in Glean.

How to access: Administrators must enable for your organization.

Learn more

Connectors [ROAD-1211]

Switch models within an existing Assistant chat session

You can now switch models mid-conversation in Glean Assistant without losing your thread. Previously, changing models would drop you into a new chat — losing your context, canvas, and conversation history. Now your session stays intact, so you can start with a faster model and upgrade to a stronger one when you need it, or experiment across models without starting over.

Learn more

Assistant [ROAD-1315]

Updated navigation, chat bar, and personalized activity cards in Assistant

Glean has been updated with a more streamlined layout, including a refreshed chat bar and new proactive cards that surface relevant next steps based on the context of your work. The updated navigation introduces a dedicated Search entry point along with a new content library. Together, these updates create a more unified way to search, chat, and work within Glean. Most users will see the change on April 29, 2026.

Customers who were part of the earlier gradual rollout of the new layout (ROAD-1040) will now be moved to 100% rollout on April 29, 2026.

Learn more

Assistant [ROAD-1318]-MR

Experience real-time, hands-free voice conversation support with Glean on web, desktop, and mobile

Experience natural, hands-free real-time voice conversations with Glean Assistant on web, desktop, and mobile. Talk to Assistant and hear it respond immediately and naturally, with low-latency, back-and-forth dialogue—just speak, and Glean responds out loud, allowing you to interrupt or steer the conversation at any time. Real-time voice unlocks new ways to brainstorm, prepare for your day, and get work done wherever you are, making Glean more accessible and productive for users on the go or at their desk.

This feature is available for Glean Key customers. Admins can control the rollout of this feature to their end users from Admin console → Assistant → Realtime Voice. The default setting lets Glean manage the rollout: voice is off by default and will be turned on for users no earlier than mid-April 2026. We recommend starting with "On only for admins"; if you like it, you can turn it on for everyone in your organization at any time, or select "Off" to opt out. Your choice can be changed at any time and will not be overwritten. This feature may use credits. Learn more in Glean's Help Center.

How to access: Administrators must enable for your organization.

This feature may be subject to usage-based pricing. Learn more in Glean's Help Center.

Learn more

Assistant [ROAD-911]

Deprecation of Claude Sonnet 4, Sonnet 4.5 and Opus 4.5

Anthropic is retiring the 1M token context window beta for Claude Sonnet 4.5 and Claude Sonnet 4 on April 30, 2026. After this date, the context-1m-2025-08-07 beta header will have no effect and requests exceeding the standard 200k-token context window will return an error.

Users should migrate to Claude Sonnet 4.6 or Claude Opus 4.6, which support 1M context at standard pricing with no beta header required.

Ref: Anthropic release notes

Learn more

Agents [ROAD-1271]

See live task progress in Assistant plans

Glean Assistant now shows a live task list for complex, multi-step requests, so you can see the plan it creates and track progress as work happens. Each step updates in real time as Pending, In Progress, or Done, which makes longer-running research, analysis, and workflow tasks easier to follow and less opaque. You can also stop Assistant and redirect it if you want to change course mid-task. This is available in Thinking mode for all users on Glean Universal Key and Glean Hosted.

How to access: Open Glean Assistant and submit a complex request in Thinking mode, such as a multi-step research or analysis task. If Assistant decides the request needs planning, it will show a task list card in chat with live step-by-step progress. No admin setup is required.

Learn more

Assistant [ROAD-1332]

Create images with Open AI's Image 2 model in Assistant and Agents

Glean now supports OpenAI Image 2, giving users access to a new, high-quality image generation capability from OpenAI that was not previously available. Users can generate richer visuals directly from Glean Assistant and Agents, with images embedded into artifacts like slides and docs where supported. Agent builders also now have a dedicated Image Creation node, and Plan & Execute plus autonomous agents can explicitly incorporate image generation into multi-step workflows. Usage continues to follow your organization's existing safety, quota, and eligibility settings, with graceful fallbacks to text-only responses when requests are blocked or exceed limits.

This feature may be subject to usage-based pricing. Learn more in Glean's Help Center.

Learn more

Assistant [ROAD-1324]

See file pills for Memory and Skills in intermediate steps

Glean Assistant now shows file pills for triggered skills in intermediate steps, so users can more easily see which skill influenced a response and open it in the side panel for more context. This makes Assistant less opaque during longer-running tasks and gives users a clearer view into how responses are being shaped. No admin setup is required.

How to access: When Assistant shows intermediate steps during a query, look for the skill pill in the progress area and click it to open the skill in the side panel.

Learn more

Assistant [ROAD-1323]

Import Memory to Glean from other AI Providers

You can now bring work-related preferences, role context, active projects, and communication habits from other AI assistants into Glean, so Assistant can personalize responses faster without making you start from scratch. Users can open Settings, go to Personalization, copy Glean's import prompt, paste it into another AI assistant, then paste the response back into Glean to save imported memories. Imported memories are reviewed and written into Glean's memory system, where users can later view or delete them from Personalization. Fast mode is not supported for this flow.

How to access: Open Glean, go to Settings, and select Personalization. Use the import option to copy Glean's prompt into another AI assistant, then paste that assistant's response back into Glean to add work-related memories. No admin setup is required beyond having memory enabled for your organization.

Learn more

Assistant [ROAD-1304]

Agent Sandbox & Programmatic Tool Calling [Customer-Hosted on GCP, AWS]

Agent sandbox and programmatic tool calling are now available for customer-hosted deployments in AWS and GCP. In Thinking mode, Glean Assistant can perform secure code-backed analysis, large result retrieval, and multi-step reasoning while keeping execution and data inside the customer's cloud environment. Programmatic tool calling lets Glean orchestrate large numbers of tools for parallel research tasks by writing and executing code in a sandbox.

How to access: After setup, Glean Assistant Thinking mode automatically activates sandbox when a query benefits from code execution, exhaustive retrieval, or structured analysis. For best results, use a supported frontier model such as GPT 5.4 or later, Claude Sonnet 4.6, Claude Opus 4.6 or later, or Gemini 3.1 Pro.

Learn more

Assistant [ROAD-1285]

Add, find, and revisit content in the library

The library is a new dedicated tab for everything you've created and saved in Glean. It replaces the Content section in the left navigation with a single, searchable surface for all your documents, slides, images, emails, interactive pages, Collections, Pins, and Go Links. You can also discover content that teammates have shared with you or your organization.

How it works: Open the library from the left navigation to browse everything in one place. Filter by type to narrow results, or search to find a specific item. Clicking any item opens it in context with its original conversation.

Content created with Assistant is retained indefinitely, until a user deletes it from the library. This content includes artifacts such as documents, slides, emails, and images.

This does not apply to standard chat responses, where your organization's chat retention period still applies. The library help page on docs.glean.com will include a full description of content types when the library reaches GA.

Learn more

Assistant [ROAD-1278]

Allow users to manually rename chat conversations

Users can now manually rename their chat conversations in Glean Assistant by clicking on any chat title and editing it inline. Custom titles persist across sessions, making it easy to organize and revisit past conversations. Chats you don't rename will continue to use automatically generated titles, so no action is required.

Learn more

Assistant [ROAD-1210]

Original source

User Features

One click install of Glean's remote MCP server to claude code, cursor, desktop apps

Use your MDM provider (Jamf, Kandji, Intune) to configure Glean's remote MCP server on your desktop apps (Claude Code, Codex, Cursor, Gemini CLI, Goose, JetBrains AI assistant, Visual Studio Code, Windsurf).

How to access: Admins can now deploy a Glean MCP remote server to user devices through their organization's MDM server, so users do not need to manually set up Glean MCP themselves.

Learn more

Admin Capabilities ROAD-1123

Claude Opus 4.7 in Assistant and Agents

Opus 4.7 is now available in Glean Assistant and Agents! This feature may be subject to usage-based pricing. Learn more in Glean's Help Center.

Learn more

Agents ROAD-1296

Glean Assistant can create Google Slides presentations

Glean Assistant can now generate full slide decks with day zero support for Google Slides presentations directly from prompts. Ask Assistant to create a slide deck on any topic, and it will automatically use your company's approved template to maintain consistent branding and formatting across all presentations. Available for Glean Key and Customer Key. Admins must add their company slide template to the admin console via Console > Assistant > Settings > Slide deck generation > upload template. This feature may be subject to usage-based pricing. Learn more in Glean's Help Center.

How to access: Admins must enable Google slide generation via the Admin console for admins or all users, and upload a company template.

Learn more

Assistant ROAD-1272

View changes between versions of your documents, emails, and messages

You can now see exactly what changed between versions of a document, email, or message generated in Glean Assistant. When you ask the assistant to revise an artifact, the diff view highlights additions, deletions, and edits inline — so you can review changes at a glance instead of re-reading the whole thing. Whether you are iterating on a customer email, refining a proposal, or editing a team update, diffs make every revision transparent and easy to approve.

Learn more

Assistant ROAD-1305

Experience refreshed progress updates

We've improved the intermediate steps experience in Assistant so it's easier to scan tool execution and reasoning while a task is running. This makes progress clearer, helps users better understand what Assistant is doing, and creates a more polished overall experience.

How to access: The intermediate steps automatically invoke for queries in assistant.

Learn more

Assistant ROAD-1294

Ask clarifying questions in Glean Assistant

Glean Assistant can now ask concise, contextual clarifying questions when a request is ambiguous or under-specified, helping it choose the right path before taking action. This improves first-pass quality, reduces wasted work caused by incorrect assumptions, and makes Assistant feel more collaborative on multi-step tasks.

How to access: Clarifying Questions activate automatically for Glean Assistant.

Learn more

Assistant ROAD-1269

MCP Apps Extension support in Glean Assistant

You can now bring your favorite applications right into Glean with MCP App Extensions. Glean acts as an MCP app host, so when an MCP server returns a UI resource, the app can render directly inside the chat experience as an interactive widget.

That means users can interact with dashboards, forms, approval flows, and data visualizations natively in Glean—without switching tools or opening a separate window. All third-party UI runs in a secure, sandboxed environment with enforced content security policies, so you get a seamless experience without compromising safety. This feature may be subject to usage-based pricing. Learn more in Glean's Help Center.

Learn more

Assistant ROAD-1234

Salesforce object query filters in setup page

Admins can now add query filters to Salesforce objects directly in the Glean Admin Console, so you can control which Salesforce records are indexed without backend configuration changes. Filters support SOQL-style conditions and combine multiple rules with AND logic, so only records that match all configured conditions are indexed. This makes it easier to limit crawl scope, support compliance and data minimization needs, and manage Salesforce indexing in a more self-serve way.

How to access: In the Admin Console, go to Data sources → Salesforce → Objects, then add a new object or edit an existing one. Open Advanced options, select Add filter, choose the Salesforce field, operator, and value for each condition, then save your changes and run a crawl for the filters to take effect. Filters apply only to the object you configure, so if you need similar scoping on related objects, configure filters separately for each one.

Learn more

Connectors ROAD-1265

Native search replacement in Atlassian's Confluence and Jira is moving to the browser extension

Glean's Atlassian Native Search replacement previously available within Jira and Confluence will revert to Atlassian's native search capabilities over the coming weeks. However, users can still search from Atlassian pages with the Glean browser extension sidebar, which lets them leverage Glean search without leaving the browser or the Atlassian page. This change is being made due to low usage and the broader benefits and extensibility of the Glean extension.

Learn more

Search ROAD-1276

Admin Features

Glean now supports custom static & dynamic headers for MCP

Glean now supports customer-specific custom HTTP headers for outbound requests to external MCP servers, making it easier to connect servers that require tenant-specific metadata, vendor-specific headers, or request-time identity context. Customers can configure any fixed static headers and dynamic headers for user email, user ID, and API key.

How to access: Reach out to your support representative with the list of headers you want to enable for MCPs and they can update your config.

Learn more

Actions ROAD-1306

Simplified OAuth management for admins

Admins can now manage OAuth settings in a clearer, more organized Third-party access page. The updated experience separates IDP-configured OAuth and the Glean OAuth Authorization Server into distinct views, making it easier to find the right settings and manage third-party access with more confidence.

How to access: Go to the Admin Console and open Settings → Third-party access (OAuth) to manage OAuth configuration. From there, admins can enable the Glean OAuth Authorization Server and create static OAuth clients with the redirect URIs and scopes needed for their internal or third-party applications. If you're using MCP, enable the OAuth authorization server first, then enable Glean MCP Servers under Platform → Glean MCP servers.

Learn more

Admin Capabilities ROAD-1216

Latency enhancements for Egnyte customers with multiple admin accounts

Glean's Egnyte connector now supports multiple administrator authentications for a single Egnyte data source, so you can authorize more than one Egnyte admin account. Glean uses every active admin token during Egnyte crawls, which improves crawl throughput as you add admins while continuing to enforce Egnyte's native permissions. This helps large Egnyte deployments index content faster and keep more content fresh in Glean.

Learn more

Connectors ROAD-1238

OneDrive and SharePoint connector enhancements

Glean supports real-time search across Microsoft OneDrive and SharePoint, including Document Libraries, Sites, and Lists. The feature streamlines collaboration and ensures users can quickly find and use the most up-to-date documents across their Microsoft 365 environment.

How to access: Admins can turn on the feature in the Glean Admin Console. For OneDrive and SharePoint, setup requires registering an app in Azure, granting the necessary application permissions (including Sites.FullControl.All and Files.ReadWrite.All), and completing the configuration in Glean. Once enabled, users can paste OneDrive or SharePoint links into Assistant to fetch and interact with documents, provided they have access rights. For detailed setup steps, refer to the Glean Help Center documentation for OneDrive and SharePoint connectors.

Learn more — OneDrive | Learn more — SharePoint

Connectors ROAD-1141

NetSuite connector

Glean now offers a NetSuite connector, enabling organizations to securely search key financial and operational data from their NetSuite ERP. The connector supports high-value workflows such as viewing invoices, payment histories, unpaid invoices, and customer records directly within Glean. By making critical NetSuite data discoverable, teams can streamline finance, sales operations, and back-office processes, improving visibility and productivity across the business.

Learn more

Connectors ROAD-842

Glean OAuth - Dynamic client registration

Glean now supports a generally available OAuth authorization server for secure third-party access and MCP host connections. Admins can enable Dynamic Client Registration so supported MCP hosts can register at runtime, apply redirect URI restrictions for tighter control, and manage connected OAuth applications, including revocation, from the Admin Console. This makes it faster to connect approved tools to Glean while giving admins more visibility and control over access.

How to access: In the Admin Console, go to Settings > Third-party access (OAuth) and enable the Glean OAuth Authorization Server. If you want to control which dynamically registered apps can connect, open Manage settings, turn on Restrict Dynamic Clients by Redirect URI, and use either the Glean-managed list or your own static list of allowed redirect URI patterns. If you're using Glean MCP Servers, also go to Platform > Glean MCP servers and enable them there.

Learn more

Developer Experience ROAD-1205

Restricted topics policies (acceptable use policies / topic guardrails) on user prompt for Assistant compliance

Glean now enables organizations to enforce Acceptable Use Policies (AUP) at the user query level in Glean Assistant and Agents. Admins can define and centrally manage topic-based guardrails to block or flag user prompts on sensitive topics—such as performance reviews, disciplinary actions, compensation, and other HR-sensitive areas—ensuring compliance with internal policies and regulatory requirements. This feature helps reduce the risk of information leakage, supports adoption in regulated industries, and builds trust by preventing prohibited queries from being processed or answered, regardless of underlying data source permissions.

Learn more

Protect ROAD-872

Original source

User Features

Agents now support adding apps instead of individual actions for Auto mode and Plan and Execute agents

Builders can now give Auto mode and Plan and Execute agents access to whole apps like Jira, Slack, Gmail, and Google Docs instead of adding individual actions one by one. This makes agent setup faster, easier to understand, and less cluttered.

Existing agents will transition to this new experience automatically, with no breaking changes. If an agent already uses multiple actions from the same app, those actions will continue to work after migration. For user confirmation settings, we take the more conservative approach: if any one of those actions requires user confirmation, then all actions from that app in that agent will require user confirmation.

How to access: No rebuild is required for existing Auto mode or Plan and Execute agents. Existing agent configurations that already use individual actions will continue to work as-is, and builders can now add supported apps directly when creating or editing Auto mode and Plan and Execute agents. Static workflow agents are unchanged in this release and still use individual actions.

Learn more

Actions ROAD-1236

Memory usage in agent debug traces

Debug mode now shows how much of each LLM call's context window is used, with separate input and output percentages for workflow and auto mode agents. This helps builders spot steps nearing context limits, diagnose truncation-related quality issues, and tune memory and model settings. For workflow agents, the memory setting is also now more prominently displayed beneath Instructions in each step.

Learn more

Agents ROAD-1215-MR

Share content with your teammates

Sharing enables Glean users to publish dashboards, infographics, visualizations, and other content to a stable, shareable link that teammates can open directly in Glean, resulting in seamless distribution of created work without leaving the platform.

How it works: Click Share on any artifact, set audience and permissions (private, team, or org-wide).

Learn more

Assistant ROAD-1153-MR

Viewing generated visual media within Glean Canvas

Users can now view AI-generated slides and images inline in Canvas, staying in flow as they scroll through decks, zoom into visuals, and quickly sanity-check content without downloading files or opening other apps. When they're ready to share or polish, they can still export to PowerPoint, Google Slides, PDF, or image files — making fast in-product review the default and export an explicit follow-up step.

Learn more

Assistant ROAD-1108

Glean Assistant can create PowerPoint presentations

Glean Assistant can now generate full slide decks with day zero support for Microsoft PowerPoint (Google Slides support coming soon) presentations directly from prompts. Ask Assistant to create a slide deck on any topic, and it will automatically use your company's approved template to maintain consistent branding and formatting across all presentations. Available for Glean Key and Customer Key. Admins must add their company slide template to the admin console via Console > Assistant > Settings > Slide deck generation > upload template.

See Coming Soon release notes for upcoming Google Slides support.

This feature may be subject to usage-based pricing. Learn more in Glean's Help Center.

How to access: Admins must enable PowerPoint slide generation via the Admin console for admins or all users, and upload a company template.

Learn more

Assistant ROAD-898

Create and execute structured plans in Glean Assistant

Glean Assistant generates an interactive plan displayed directly in chat, breaking the task into clear, numbered steps. Each step updates live with its status (Pending, In Progress, or Done) along with an overall progress bar and elapsed time, so you can follow along as work gets done.

Stay in control: Stop Assistant at any time and redirect it. Assistant can regenerate a new plan or update its existing one based on your feedback.

Adaptive execution: If new information emerges mid-task, Assistant revises its plan in real-time, adjusting steps rather than following a rigid sequence.

How to access: This feature automatically gets enabled in Thinking Mode.

Learn more

Assistant ROAD-1248

Download Canvas content as Markdown

Canvas documents now include a Download Markdown option in the export menu, letting you save your content as a clean .md file with a single click. Any Glean-hosted images are preserved as clickable links so nothing is lost in translation. Whether you're moving content to GitHub, a README, or another markdown-friendly tool, it just works.

Learn more

Assistant ROAD-1244

Bring your Glean memory to any AI tool with MCP (GCP)

Bring your Glean memory to any AI tool with MCP, enabling employees to use their existing Glean memory in third-party AI assistants and IDEs. This allows them to receive personalized, context-aware responses without repeatedly restating their role, projects, preferences, or writing style. Tools like ChatGPT, Claude, Cursor, VS Code, and Copilot can retrieve this context through the MCP memory tool. Memory remains read-only and fully governed within Glean. This is available by default for existing Glean MCP server deployments on GCP. We are working on this for our AWS customers. Admins can disable the memory tool for a deployment at any time.

How to access: The read_memory tool is included in Glean's MCP server and enabled by default for deployments on GCP. No additional integration is necessary. We are working on this for our AWS customers.

Admin controls: Administrators can enable or disable the read_memory tool for a deployment in MCP Hub or the Glean Admin Console.

End-user context: End users manage the information used by this tool through their memory profile in Glean under Settings > Personalization. Connected AI tools (e.g., ChatGPT, Claude, Cursor, VS Code, Copilot) can call read_memory via MCP to retrieve this governed, read-only context.

Learn more

Assistant ROAD-1203

Agent sandbox and programmatic tool calling in Assistant [Glean Key and Glean Hosted Only]

Glean Assistant can now use a secure sandboxed environment in Thinking mode to handle more complex analysis and research tasks. This helps Assistant work through large result sets across connected systems, run code to analyze data, and return richer outputs like summaries, charts, and CSVs — without requiring any extra setup from end users. It's especially useful for multi-step analytical questions that would otherwise exceed a model's context window and executing skills (currently in beta).

How to access: Available for Glean Key and Glean-hosted customers in Assistant Thinking mode. Agent Sandbox activates automatically when a query benefits from code execution, exhaustive retrieval, or cross-system analytics, so users don't need to enable or configure anything. Customer-hosted deployments are not included in this launch.

Learn more

Assistant ROAD-1160

Create dynamic, interactive pages with Glean Assistant

Glean Assistant can create interactive pages that run safely inside Glean, no separate tools or coding required. Describe what you want (an interactive dashboard, infographic, or simple calculator, for example) and Assistant will generate HTML you can preview, click through, and refine directly in Canvas.

This feature may be subject to usage-based pricing. Learn more in Glean's Help Center.

Learn more

Assistant ROAD-1136

Edit images in Glean Assistant

You can now edit Assistant-generated images right inside Glean. Open any image in the viewer, draw annotations on the areas you want changed, describe the edit in plain language, and click Apply to get an updated version. Compare versions as you iterate with version history.

This feature may be subject to usage-based pricing. Learn more in Glean's Help Center.

Learn more

Assistant ROAD-1117

Create images with OpenAI's Image 1.5 model in Assistant and Agents

Glean now supports OpenAI Image 1.5, giving users access to a new, high-quality image generation capability from OpenAI that was not previously available. Users can generate richer visuals directly from Glean Assistant and Agents, with images embedded into artifacts like slides and docs where supported. Agent builders also now have a dedicated Image Creation node, and Plan & Execute plus autonomous agents can explicitly incorporate image generation into multi-step workflows. Usage continues to follow your organization's existing safety, quota, and eligibility settings, with graceful fallbacks to text-only responses when requests are blocked or exceed limits.

This feature may be subject to usage-based pricing. Learn more in Glean's Help Center.

Learn more

Assistant ROAD-1115

Gainsight connector

The Gainsight connector gives go-to-market and customer success teams a complete 360-degree view of their customers by supporting core Gainsight Customer Success objects.

How to access: Admins will need to enable the connector in data sources.

Learn more

Connectors ROAD-930

Glean in Slack — UI refresh and interaction design improvements

Glean has refreshed the visual design and interaction flows for Glean in Slack. Updates include redesigned feedback buttons, improved loading/latency indicators, cleaner citation and source attribution, proper table rendering in DMs, and streamlined button layouts. These improvements make the Slack experience more polished, intuitive, and consistent for end users.

Learn more

Embedded Integrations ROAD-1233

Gradual rollout of new Glean homepage to select customers

Beginning March 26, Glean will start a gradual rollout of a new homepage to customers that were previously contacted via email. The updated experience streamlines where users start their work in Glean without taking away any core functionality. The new homepage proactively recommends personalized next steps to move work forward, includes a dedicated company tab, and brings search and chat into a single entry point. The experience will roll out gradually to all users in the notified customer base. During this period, users within the same organization may temporarily see different homepage experiences.

Note: All Glean customers will receive these updates later this month (see Coming Soon ROAD-1043).

How to access: Admins can opt out of the early rollout in Admin Console > Appearance using the homepage experience toggle, if the homepage rollout is available in their environment. If you have questions or feedback, join the conversation in the Gleaniverse.

Learn more

Glean Home ROAD-1040

Admin Features

Introduce billing alerts and monthly budgets

Admins can now set billing alerts and monthly budgets to proactively stay ahead of FlexCredits usage. They can configure alerts when total credit consumption reaches 50%, 75%, 90%, or 100% of available credits, and set a monthly soft budget with alerts at the same thresholds. By default, admins receive alerts at 75%, 90%, and 100% of total available credits, and those alert settings are editable.

How to access: Open the Admin console and select FlexCredits to access the billing dashboard. To use the dashboard, you must have either the Super admin role, Admin, or the Billing Moderator role. From there, review your current FlexCredits balance and usage, then configure billing alerts or monthly budget thresholds when those controls are available in the dashboard.

Learn more

Admin Capabilities ROAD-1251

[Action Required] Update your Linear Connector Authentication tokens before April 1

Linear is moving from long-lived access tokens to short-lived access tokens with refresh token support. This is a security improvement on Linear's side, and requires a quick update before April 1, 2026 to ensure your Glean-Linear connector continues to work properly.

How to access: The process should only take a few minutes. If you'd like any guidance or run into issues, don't hesitate to reach out to your Glean support team — we're here to help.

In your Linear OAuth2 application settings, modify specifically the OAuth application you have used to authenticate in Glean (most likely with the application name being "Glean Application") to enable refresh token support.

Once that's done, re-authenticate the Linear connector in your Glean admin console.

Learn more

Admin Capabilities ROAD-1225

Custom actions no longer send user email by default

Custom actions no longer send the authenticated user's email address to third-party endpoints by default. This reduces exposure of user identity data while preserving support for organizations that rely on it for authorization, routing, or workflow logic. If your workflows depend on this behavior, contact Glean Support to keep it enabled before April 1st.

Learn more

Actions ROAD-1208

GPT 5.4, Claude Sonnet 4.6, and Claude Opus 4.6 for Customer Key in Assistant and Agents

Customer Key admins can now configure GPT 5.4, Claude Sonnet 4.6, and Claude Opus 4.6 for Glean Assistant and Agents, expanding access to newer premium models for stronger reasoning and long-context tasks. This gives Customer Key deployments more model choice across OpenAI, Azure OpenAI, Vertex AI, and Amazon Bedrock, helping teams use the latest frontier models in the surfaces they rely on most. These premium models may increase usage costs compared with existing defaults.

How to access: In the Admin Console, go to Platform > LLMs, click Add LLM, choose your hosting provider, select the models you want to use for Assistant and Agents, validate the connection, and save. For Customer Key deployments, GPT 5.4 is supported via OpenAI or Azure OpenAI, and Claude Sonnet 4.6 and Claude Opus 4.6 are supported via Google Vertex AI or Amazon Bedrock. If you want to use a supported model in an agent, you can then select it as the default model in agent settings or for an individual step in the canvas.

Learn more

Agents ROAD-1262

Databricks connector: Index Genie spaces for Search and Assistant

Glean's Databricks connector now indexes Databricks Genie spaces as searchable content, bringing Genie space metadata into Search and Assistant. This helps users find relevant Genie spaces more easily and improves Assistant routing for Databricks natural language questions. Indexed metadata includes details such as sample questions, example SQL, tables, metric views, and permissions-aware access controls.

How to access: Admins can enable this by setting up the native Databricks connector in the Glean Admin Console and connecting their Databricks account with the required OAuth credentials and workspace configuration. Once configured, the connector crawls Databricks content and validates permissions automatically during setup.

Learn more

Connectors ROAD-1230

[Action Required by April 2] SharePoint Connector to switch from secret-based to certificate-based authentication

Customers using SharePoint Online with Azure ACS secrets authentication must update your authentication to Microsoft Entra ID by April 2 to continue accessing the latest data in Glean.

Microsoft is retiring the legacy Azure ACS secrets-based method for SharePoint Online authentication, which will stop updating SharePoint permissions in Glean after April 2, 2026 if not changed. Glean now supports an in-place switch for the SharePoint connector from client secret to certificate-based authentication, helping you stay compliant with Microsoft's change while keeping SharePoint permissions and content in Glean fresh and accurate. With certificate-based authentication using Microsoft Entra ID, your organization benefits from stronger, standards-based identity security and more reliable permission updates for SharePoint data in Glean.

Learn more

Connectors ROAD-1227

Mobile app access now requires Chat to be enabled

On March 31, 2026, Glean is retiring the native mobile app experience for deployments that do not have Assistant enabled. When users from these organizations open the Glean mobile app, they'll see a message explaining that mobile app access is no longer available, but can continue to access Glean from their mobile browser for search and other supported functionality, or the admin can contact their account team to enable the chat experience for the organization.

Learn more

Mobile App ROAD-1198

Quickly triage AI security violations with richer context and workflows, while reducing false positives

AI security findings are now easier to review and more accurate. Security teams can quickly triage AI security violations with richer context and workflows, while backend improvements reduce noisy false positives so they can focus on real risks. This helps you focus on true AI security prompt injection, harmful content, and malicious code without drowning in unnecessary alerts.

How to access: AI security violations triage are part of Glean Protect+ AI security guardrails. To use them, ensure Protect+ is enabled for your organization, then have a Super Admin or Sensitive Content Moderator open the Protect+ or AI security area in the admin experience to review violations and configure guardrail policies. From there, they can use the violations dashboard and related filters to prioritize issues, tune policies, and refine guardrail behavior based on feedback, improving precision over time.

Learn more

Protect ROAD-1105

Original source

User Features
New actions added in agents will not support customization of parameters
Glean is simplifying how new actions are introduced and maintained in Assistant and Agents. Going forward, agents will no longer support per-action parameter customization for any newly added action. Instead, these actions have use a clean, standard configuration so Glean can safely improve parameters and behavior over time without breaking existing workflows. If you need consistent parameter values (for example, always using a 30-minute meeting duration), you can still enforce this via agent-level action instructions rather than low-level parameter overrides.
How to access: To standardize how parameters are filled (for example, default durations or statuses), agent builders should use the agent's action instructions to tell Assistant how to populate those fields instead of relying on per-action parameter customization.
Learn more
Actions ROAD-1207
Agent delete flow changes
The agent deletion flow now explicitly warns that removals are permanent and non-recoverable, reducing the risk of accidental loss. To streamline management, the Delete button has been removed from the Template Library. Use the Agent Builder as the single hub for sharing and deletion.
How to access: Administrators must enable for your organization. Admins can recover deleted agents by navigating to the Admin Console, clicking "Agents", and selecting the "Recover deleted agents" section.
Learn more
Agents ROAD-1008
Share agents with permissions groups
Share Glean agents with user groups from your connected identity provider (Azure Active Directory via O365 or Google Groups), not just with individuals or departments. This makes it easier for organizations—especially at enterprise scale—to manage who can access specific agents, speed up agent rollout, and give the right teams or communities instant access. Admins and Agent Moderators can share agents with any group from the configured IdP system. Default Members—if group sharing is enabled—can share with groups they're part of. When an agent is shared with a group, all group members get the assigned permissions (view, edit, or owner) for that agent, and group membership changes are automatically reflected in agent access.
How to access: Administrators must enable for your organization. Admins can enable sharing agents with IdP groups by navigating to the Admin Console, clicking the "Agents" tab, and configuring the data source to be used for sharing agents with groups.
Learn more
Agents ROAD-763
Agents in Slack now respond more intelligently
Agents deployed to Slack channels now use smarter question detection to determine when to respond. Instead of relying on generic question detection, the system considers the agent's configured capabilities, conversation starters, and any user-provided instructions to decide whether to proactively respond to a message. This ensures agents trigger appropriately based on what they are designed to do, reducing false triggers and missed responses. Admins can further refine behavior by providing custom instructions for each agent's Slack deployment.
How to access: This behavior applies to agents that are published to Slack channels using a chat trigger and the standard "Publishing to Slack" flow in the Agent Builder.
To use it, publish your agent to the appropriate Slack channels from the Share dialog, ensuring the agent has clear conversation starters and scoped instructions that describe what it should handle in that channel.
Admins can continue to control where Glean responds in Slack using the existing "Enable Gleanbot to respond in channels" settings and per-channel /glean configure controls.
If your deployment uses feature flags, the new detection logic can be rolled out via the documented flags for agent question detection in Slack; once enabled, no additional per-user setup is required.
Learn more
Agents ROAD-1200
Use of Nano Banana 2 in Assistant and Agents
Glean now uses Nano Banana 2 as the default image generation model in Assistant and Agents, delivering faster image generation with comparable or improved visual quality over Nano Banana Pro. The upgraded model offers significantly better capacity and throughput, reducing rate-limiting errors during peak usage. All existing image generation workflows—including inline images in Assistant, the Image Creation node in Agent Builder, and image actions in Plan & Execute agents—work seamlessly with the new model.
This feature may use credits. Learn more in Glean's Help Center.
How to access: Administrators must enable for your organization.
Learn more
Assistant ROAD-1209
Claude Opus 4.6 in Assistant and Agents
Glean supports Claude Opus 4.6 for Glean universal model key customers on Assistant and Agents. We also offer Opus 4.6 for customer keys deployments for Glean agents (agent builder) via Vertex AI and AWS Bedrock.
Claude Opus 4.6 delivers state-of-the-art performance for agentic coding, search, and knowledge work, enabling higher-quality, longer-horizon reasoning in chat and autonomous workflows. With support for 1M-token context and improved long-context retrieval, users can tackle more complex, multi-document tasks and reduce context-rot failures in long conversations. This reinforces Glean's position as best-in-class for long-context, agentic knowledge work.
This feature may use credits. Learn more in Glean's Help Center.
How to access: Administrators must enable for your organization. Glean universal model key customers can turn on model choice in Assistant and configure their models in the model hub. Customer key customers can configure models directly in model hub.
Learn more
Assistant ROAD-1138
Expand list of supported doc types in file upload
Going forward, file uploads will support 50+ additional text-based formats (e.g., TSV, TOML, RST, MD) that were previously restricted. Security safeguards remain in place to continue blocking unsafe file types while improving compatibility for valid text files.
Learn more
Assistant ROAD-1186
Search now can filter by Google Drive labels
Users can now filter and refine search results in Glean based on Google Drive document labels. When this feature is enabled, a "Labels" filter appears in the search experience—making it easier to find specific documents by their assigned Google Drive labels. This enhancement helps users quickly identify and differentiate internal, client-shareable, or otherwise labeled documents, streamlining information access and supporting better information governance. Search by label improves accuracy and efficiency for teams who use Google Drive labels for classification and visibility.
How to access: Administrators must enable for your organization. Admins must enable via Admin Console → Data sources → Google Drive → Setup and turn on Drive labels / Enable Google Drive labels.
Learn more
Connectors ROAD-756
Docs.glean.com update
You may notice minor visual differences as we update our docs site to allow for future enhancements.
Learn more
Platform Capabilities ROAD-1150
Admin Features
Admin Left Nav Enhancement
We've made some updates to Admin settings to make navigation clearer and help you get to the right controls faster. As Glean has grown, there's simply more to manage in admin. This update is designed to better organize settings so it's easier to find what you need and understand where different controls live.
We've introduced a few new categories in Admin that replace Settings including:
User and permissions — includes User management (formerly Teammates), Networking, Single sign-on, Third-party access, and Audit logs
Customization — includes Appearance
Notifications- includes alerts and email settings
What's new — includes Feature rollouts and Admin updates
We hope this update makes Admin feel more intuitive and easier to navigate as your use of Glean grows.
How to access: This update applies automatically in the Glean Admin Console — no additional setup is required. Admins will see the new left nav structure the next time they sign in and can continue using all existing settings and controls as before. If you need help locating a specific page, use the Admin Console search or refer to the Admin Guide in the Help Center.
Learn more
Admin Capabilities ROAD-1196
Manager-level view on Insights
The Insights page will now include a new "Manager" tab that will provide a table view of the usage of Glean within teams under different managers, enabling you to understand the managers who are able to drive adoption and those that need assistance.
Learn more
Admin Capabilities ROAD-1175
[Action Required] Sunsetting Gemini 3.0 Pro Preview
Google is retiring Gemini 3.0 Pro on March 26, 2026, so Glean will stop supporting Gemini 3.0 Pro models in Assistant and Agents and migrate configurations to supported successors such as Gemini 3.1 Pro or Gemini 3 Flash. If you're using Gemini 3.0 on your own key, please ensure a supported Gemini model is available in your GCP project and update your model selection in the LLM configuration page before the deprecation date to avoid disruption; Glean-key deployments will be migrated automatically, and Agent Builders have been notified if their agents selected this model.
Learn more
Agents ROAD-1223
Restrict Google Drive content based on sensitivity labels
Admins can configure a label-based redlists (Option List/Badge List selection IDs) to exclude sensitive Google Drive data from being visible within Glean.
Learn more
Connectors ROAD-760
Create static OAuth clients to connect apps to Glean
Glean now lets admins create static OAuth clients in the Admin Console, making it easier to connect trusted applications—like internal tools or third-party apps such as Zoom—to Glean on behalf of users. By using Glean as the OAuth authorization server instead of relying on your identity provider for every integration, you can reduce setup friction between IdP and Glean admins and prepare for finer-grained, Glean-defined scopes in future Client API integrations. This update is especially valuable for organizations and partners that want a standard, secure way to obtain Glean access tokens for MCP hosts and other OAuth-capable apps.
How to access: To use static OAuth clients, first enable the Glean OAuth Authorization Server by going to the Admin Console and navigating to Settings → Third-party access (OAuth), then turning on the Glean OAuth Authorization Server. Once enabled, you can create and manage OAuth clients from this area, configuring redirect URIs and scopes according to the requirements of your internal or third-party applications. For MCP remote servers and other OAuth-enabled apps, point the client to Glean's Authorization and Token endpoints and complete a standard Authorization Code with PKCE flow to obtain access tokens.
Learn more
Developer Experience ROAD-1195

Original source

User Features

Agent Library Enhancements: Manage categories + Verification

Agent Library now scales for organizations with hundreds or thousands of agents by turning the Agents page into a single, discovery-focused library with richer curation tools. Admins and agent moderators can create and reorder company-owned categories, add agents to multiple categories, and brand or verify “official” agents so users see a trusted, tailored catalog instead of a noisy list. End users can quickly filter by company-curated agents or Glean-provided agents and find high-quality workflows that match their role and team

How to access: Administrators must enable for your organization.

Learn more

Agents ROAD-1091-MR

Sunsetting speech to text dictation

We’re retiring the dictation (“Speak to Type”) button across Glean web, desktop, and mobile composers. This includes the mic icon in the home page, chat, and Conversational Agent creators. As part of this change, the dictation mic button will be removed from supported composers and users will no longer be able to start new dictation (voice‑to‑text) sessions. Existing chat and authoring flows will continue to work as normal with typed input.

We’re making this change because dictation is used by only a small fraction of Assistant users, and keeping the control adds unnecessary clutter. Removing it simplifies the experience while we focus our investment on supporting real-time voice as the primary, interactive voice experience, rather than one‑off voice‑to‑text dictation.

How to access: Administrators must enable for your organization.

Learn more

Agents ROAD-1017-MR

Agent Notifications

Glean now sends notifications when an agent needs your input or when long‑running work like Deep Research finishes, so you can act without constantly checking chats or the Agent Library. You’ll see browser notifications (if enabled) and, for agent approval steps, email alerts that deep link you back to the right chat or run to review, approve, or provide missing information. This helps you unblock background agents faster, complete tasks on time, and reliably find results from async work instead of hunting through multiple screens.

How to access: For end users, notifications work automatically. You’ll see a Notifications entry in the Glean UI and will start receiving alerts for agent HITL steps and completed Deep Research runs. To turn browser/desktop notifications on or off, update notification permissions for your Glean URL in your browser settings and, if needed, in your operating system’s notification preferences. You can manage whether you get email and browser notifications for assistant and agents from Your settings → Notifications in the Glean app. If you don’t see Notifications in the left navigation, your organization may not have enabled this feature yet in the Admin Console.

Learn more

Agents ROAD-894-MR

Connect Glean Agents to Remote MCP Servers (MCP Host)

Glean Agents can now call tools hosted on remote Model Context Protocol (MCP) servers, so your agents can take actions in systems like Notion, Asana, GitHub, ServiceNow, Snowflake, and more—all from within Glean. Admins and builders can plug approved third-party or internal MCP servers into agent workflows. This helps teams automate more of their workflows without rebuilding custom integrations for every system.

How to access: To use MCP servers in Glean Agents, first have a Glean admin configure the MCP servers in the Admin console under Platform → Actions, where MCP-powered integrations and templates are listed. Admins can either import an MCP server by providing its URL and metadata or use pre-set templates from the MCP registry, then connect and discover available tools and choose which tools are available to which users or groups.

Once servers and tools are configured, agent builders can open Agent Builder, create or edit an agent, and add an MCP server as part of a Plan and execute or autonomous agent step, choosing which tools from that server the agent is allowed to use. When users run the agent, it will automatically route to the configured MCP tools as needed to read data or perform write actions in connected systems.

Learn more

Actions ROAD-1033

Support GPT 5.4 on Glean Assistant and Agents

GPT-5.4 is now available in Glean Assistant model choice and Agents for customers using the Glean Universal Model Key, and the Agents model hub for all customers. GPT-5.4 delivers significantly improved citation quality, instruction following, and tool usage compared to prior OpenAI standard models.

This feature may use credits. Learn more in Glean's Help Center.

How to access: Glean Universal Model Key: GPT-5.4 appears automatically in the Assistant model choice dropdown and Agents model hub. Admins can exclude it via Admin Console → Platform → LLM.

Customer Key: GPT-5.4 is available for Agents via Admin Console → Platform → LLM. It is not yet available for Assistant model choice on Customer Key.

Learn more

Agents ROAD-1189

Create Images with Glean Agents in both Workflow and Auto mode

We are releasing dedicated, governed image creation capabilities in our Agents platform across three surfaces: a dedicated node in the Agent Builder, an explicit “Generate Image” action within Plan & Execute, and native support in autonomous agents. In the Agent Builder, a configurable “Generate Image” node enables builders to define prompts, styles, aspect ratios, and image counts, draw on relevant context, and return structured outputs (image URLs plus metadata) for downstream nodes, while in Plan & Execute a dedicated action lets the planner reason explicitly about visual steps—when to generate images, how many, and which parts of the plan they support—using the same backend with quotas and fallbacks so plans can still succeed in text-only mode if image creation fails. Autonomous agents determine when visuals materially improve a task, derive prompts from artifact content, generate and embed images in the final output, and operate under clear safety, cost, and performance guardrails.

This feature may use credits. Learn more in Glean's Help Center.

Learn more

Agents ROAD-1113

Deep Research is now supported for Customer Key

Deep Research now supports all models on Customer Key (GPT5, GPT 5.1, Claude 4.5 Sonnet, and Gemini 3 Pro) and model providers (Azure OpenAI, AWS Bedrock, and Google Vertex AI).

Admins have full control over which users have access to Deep Research and their usage quotas. Admins can set monthly query limits per user, restrict usage to specific users or departments, or turn off the feature entirely in Admin Console → Assistant → Deep Research. This feature is subject to usage-based pricing; for details, contact [email protected] or view our Flex pricing documentation.

This feature may use credits. Learn more in Glean's Help Center.

How to access: This feature is default on. Admin can control the feature via the Admin Console -> Assistant.

Learn more

Assistant ROAD-1020

Customer Key customers can now access image generation in Glean Assistant

Bring your ideas to life directly in Glean Assistant with Image Generation models from Gemini & Open AI, now available for Customer Key customers on all clouds (and previously for Glean Key customers). If you’re already using image generation elsewhere, you can now do the same right inside Assistant: ask for visuals from natural language prompts, and see images show up in your chat response and artifacts.

This accelerates creative cycles and keeps iteration for drafts, diagrams, social posts, and more in one place, with prompts that can incorporate design direction from your internal documents instead of forcing you to switch tools.

This feature may use credits. Learn more in Glean's Help Center.

Learn more

Assistant ROAD-1114

Desktop App Refresh and improvements to Spotlight

The Glean desktop app now has a refreshed, modern look with a dedicated app shell that makes it easier to move and resize the window. We’ve also upgraded the desktop Spotlight (the Cmd‑Shift‑J quick entry bar) so it’s no longer just a simple input field—it now supports the full Glean Assistant chat experience, including switching between Fast and Thinking modes, choosing custom models, and generating images, all without opening the main app. This makes Spotlight a more powerful, always-available way to start or continue chats, run searches, and get work done directly from your desktop.

Note: Mac desktop refresh now available. Windows desktop app refresh will launch by March 26, 2026.

How to access: To use the updated desktop experience, download or update the Glean desktop app for macOS or Windows from your Glean settings under the desktop app installation page, then sign in with your Glean account.

Learn more

Desktop App ROAD-1152

Salesforce Support for permissions via Territory

Glean’s Salesforce connector now supports territory-based record access. With this enhancement, users can see Salesforce records assigned to them through territories, in addition to existing access rules. This ensures that Salesforce data indexed in Glean fully respects Salesforce sharing and visibility settings.

Learn more

Connectors ROAD-1144

Freshdesk Connector

The Freshdesk Connector enables organizations to connect their Freshdesk instance to Glean, making support tickets, conversations, solutions articles (knowledge base), contacts, and companies fully searchable within Glean. By integrating Freshdesk, support teams can quickly find and manage customer inquiries, leverage Glean’s powerful search and knowledge management capabilities, and streamline workflows. This integration helps improve response times, ensures consistent and accurate information delivery, and elevates the overall customer support experience.

How to access: To connect Freshdesk to Glean, an admin must add Freshdesk as a data source in the Glean Admin Console. Additionally, each user who wishes to access Freshdesk data in Glean must authenticate with their own Freshdesk API key. After setup, Glean will index tickets, conversations, solutions articles, contacts, and companies according to the user’s permissions in Freshdesk.

Learn more

Connectors ROAD-956

Admin Features

Improving Calendar Events for Microsoft Outlook and Teams

Glean has improved calendar event accuracy and freshness for organizations using Microsoft Calendar. By enabling a federated retrieval for the meeting lookup tool, users now see up-to-date, comprehensive calendar data directly in Glean Assistant and Agents.

How to access: This improvement is automatically applied for organizations with the Microsoft Calendar connectors configured in Glean, no additional setup is required for the calendar improvements to take effect.

Admins can verify their Microsoft Teams connector is active and properly configured by navigating to Admin Console → Data Sources → Microsoft Teams.

For full calendar and transcript support, ensure the connector has the required Microsoft Graph API permissions, including Calendars.Read, OnlineMeetings.Read.All, and OnlineMeetingTranscript.Read.All.

Learn more

Assistant ROAD-1187

Ironclad connector

The Ironclad connector for Glean enables organizations to seamlessly search contract records, workflows, and related legal documents managed in Ironclad.

Learn more

Connectors ROAD-823

Canva connector

The Canva Connector enables Glean users to search documents and designs from Canva directly within their workspace. With this integration, teams can discover, search, and collaborate on Canva design docs in Glean alongside all enterprise data.

Learn more

Connectors ROAD-820

Affinity connector

The Affinity Connector lets teams—especially those in private equity, venture capital, and investment banking—bring Affinity’s relationship intelligence into Glean. With this integration, users can search for contacts, companies, opportunities, and lists from Affinity alongside other sources in Glean.

Learn more

Connectors ROAD-737

Service restoration access for customer deployments

We’re introducing service restoration access to provide secure, audited, and time‑bound infrastructure-only access during rare, high‑severity incidents when normal administrative paths are unavailable for cloud-prem customers. As part of this change, we’re also moving from broad “project admin/owner” access to more granular, least‑privilege roles.

In addition, we’re deploying an isolated backend service that automatically executes pre‑approved infrastructure commands using these least‑privilege credentials—no human ever authenticates directly with this account.

In cases of service account restoration, you may see cloud audit logs labeled service restoration access. Learn more about Glean's access to customer cloud-prem deployments on the Trust Center (https://trust.glean.com/resources?s=xeeowws1dsh9xnx0n33ij\&name=glean-access-to-customer-deployments)

Learn more

Platform Capabilities ROAD-985

Original source

User Features

Glean homepage now defaults to the Chat tab

We’re updating Glean to make Chat the primary way you start working, while keeping all of your existing Search functionality available when you need it. This change is designed to reduce tab switching, keep you in one flow, and help you get more value out of a single workspace since Search results are also available in Chat conversations.

The Glean homepage now defaults to the Chat tab, and users can choose to change their default back to the Search tab if desired. This has been the experience for all new deployments since Nov 2025 and a percentage of users on all other deployments since Jan 2026, where it has led to a 29% increase in Chat queries.

Learn more

Assistant ROAD-1151-MR

Connect Glean Assistant to Remote MCP Servers (MCP Host)

Glean Assistant now supports integration with remote Model Context Protocol (MCP) servers, enabling secure connections to third-party tools like Notion, Jira, and Salesforce. Admins can centrally approve and manage which MCP servers are available, ensuring secure, controlled access to enterprise systems. This update delivers seamless, permission-aware integration that empowers users to automate workflows and fetch live data directly within Assistant.

Customers and users with Gemini LLM model as their Assistant or chosen default are not yet able to use this functionality. We aim to remove this limitation within the next few weeks.

How to access: Administrators must enable for your organization.

Learn more

Assistant ROAD-867

Bringing Email & Message Canvases into chat

The dedicated Canvas experiences for composing emails and messages are now integrated directly into the chat thread. Users no longer need to switch to a side-by-side view for quick messages or small edits; everything can be viewed, drafted, and refined right within the chat. The Canvas adapts to the medium (email or chat), providing the right fields and structure, and you can export your finished message to your preferred client in one click, with all formatting and details preserved.

Learn more

Assistant ROAD-1131

Model retirement of Claude 3.7 Sonnet

Support for the Claude 3.7 Sonnet model will end on January 28, 2026. After this date, Claude 3.7 Sonnet will no longer be available for use in Glean Assistant or Agents. Any agents or workflows currently using this model will be automatically migrated to a supported fallback model to ensure continued service. Administrators should review their model selections and update to a supported model before the deprecation date to avoid disruption.

Learn more

Assistant ROAD-1071

Gemini 3.1 Pro in Assistant and Agents

Glean supports Gemini 3.1 Pro for Glean universal model key customers on Assistant and Agents. We also offer Gemini 3.1 Pro for customer key deployments for Glean Agents (agent builder) via Vertex AI.

Gemini 3.1 Pro is Google's latest frontier model, delivering improved performance in coding, reasoning, and agentic workflows over Gemini 3 Pro — at the same price point. Customers can select Gemini 3.1 Pro via model choice in Assistant or configure it for Agent steps in the model hub.

How to access: Admins can configure the model by going to Admin Console -> Platform -> LLM.

This feature may use credits. Learn more in Glean's Help Center.

Learn more

Agents ROAD-1171

Claude Sonnet 4.6 in Assistant and Agents

Glean supports Claude Sonnet 4.6 for Glean universal model key customers on Assistant and Agents. We also offer Sonnet 4.6 for customer key deployments for Glean Agents (agent builder) via Vertex AI and AWS Bedrock.

Claude Sonnet 4.6 is Anthropic's latest mid-tier model, delivering improved performance in coding, reasoning, and agentic workflows over Sonnet 4.5 — at the same price point. Customers can select Sonnet 4.6 via model choice in Assistant or configure it for Agent steps in the model hub.

How to access: Admins can configure the model by going to Admin Console -> Platform -> LLM.

This feature may use credits. Learn more in Glean's Help Center.

Learn more

Agents ROAD-1162

New Personal Productivity Agent Templates

Glean now offers new task management agent templates for common productivity tasks like “Plan my Day” and “Daily action items”. By removing the need to build or configure, every user can immediately experience the value of automation, boosting productivity and AI adoption across the organization.

How to access: Any user who has permissions to create agents can access these templates by navigating to https://app.glean.com/chat/agents and clicking "Create agent", which will display Glean's library of agent templates. Personal productivity templates will display under the "General" tab.

This feature may use credits. Learn more in Glean's Help Center.

Learn more

Agents ROAD-1134

Agent Builder Header Update: Save, Enable/Disable and Delete

The Agent Builder and Autonomous Agent Builder headers now use clearer labels and a simpler layout, making it easier to manage your agents. The primary button in the top‑right is now labeled Save instead of Publish, and all related messages have been updated (for example, “Draft saved” and “Agent saved”). Disable / Enable and Delete are now grouped in the More actions (⋮) menu alongside Settings, View insights, Duplicate, and Import/Export. Your agents’ behavior, routing, permissions, and versioning are unchanged—only the labels and menu locations have been updated.

Learn more

Agents ROAD-1094

Merge Agent Branches into a Single Node

You can now merge multiple branches into one downstream node in the Agent Builder canvas. The shared node will run regardless of which branch was taken, so you can keep one source of truth for your final response or action. Existing agents can be refactored to converge branches, reducing visual clutter and duplicated configuration.

This feature may use credits. Learn more in Glean's Help Center.

Learn more

Agents ROAD-1093

Support for additional Salesforce Objects

Glean now natively supports a broader set of standard Salesforce objects, including Contract, SBQQ_Quote_c, Product2, SBQQ_QuoteLine_c, SBQQ_Subscription_c, Order, Quote, OrderItem, VoiceCall, and Conversation. This enhancement enables organizations to index, search, and leverage these additional Salesforce records in Glean, making it easier for teams to find and use critical CRM data across sales, support, and operational workflows. With expanded object coverage, users benefit from more comprehensive search results and improved context in Glean Assistant and Agents.

How to access: Administrators must enable for your organization. Enable the desired standard object, ensure the Salesforce integration user has the necessary object-level permissions (read and view all) for each object you wish to index, then save your configuration and start a crawl to index the newly added objects.

Learn more

Connectors ROAD-1082

Admin Features

Gemini: Additional web search provider added in Agentic Looping

Glean now offers Gemini web search as a fully supported provider in the agentic engine, alongside Brave and OpenAI. Customers using Gemini with Agentic Looping can take advantage of Google’s search results while Glean automatically chooses the right web provider per query, improving flexibility and aligning with multi-provider strategies. This makes it easier for organizations standardized on Gemini to power real‑time web lookups in Assistant and agents without custom setup.

How to access: To enable web search with Gemini, an admin should configure a Gemini web search action from the Actions section of the Admin Console.

This feature may use credits. Learn more in Glean's Help Center.

Learn more

Actions ROAD-1146

Analyze Glean usage and adoption with Insights chat

The insights chat allows you to analyze Glean usage across Assistant, Search and Agents to identify trends in usage, find power users by department, understand connector usage, analyze user feedback metrics, and highlight top agents. With insights chat, you can run complex analytics, with Python and SQL tools working under the hood, and also see results displayed in charts or via downloadable reports.

How to access: Insights chat is now GA for admin and insights moderator, so you can ask plain‑English questions about Glean usage and get data-backed answers as summary, tables, charts and downloadable reports

You’ll find it in the Insights chat under Insights page; Ask things like “Compare search vs assistant usage trends over 90 days?” and any follow-up questions to drill down into the specifics. Please try your real questions and log any issues or thumbs feedback so we can keep improving coverage and quality.

Learn more

Actions ROAD-795

Get granular insights into your FlexCredits usage with Billing Credits Dashboard

The Billing credits dashboard in the Admin Console now gives admins a much more detailed view of how FlexCredits are being used across Glean. You can see feature‑level spend for Assistant and Agents (including items like Code Writer and Image Generation), view static system workflows such as Deep Research and Chat as individual line items, and understand which agents are driving the most consumption. Deleted and unsaved agents are now clearly bucketed so previously “invisible” credit usage is accounted for, and a new Credit usage overview with segmented progress bars and overage warnings helps you stay ahead of your credit limits.

How to access: Access to the Billing/Credits dashboard is limited to Admins and Billing Moderators; if you do not see this page, your Glean role may not include billing permissions.

Learn more

Admin Capabilities ROAD-1159

Self-serve VPN setup for on-premises data sources

Glean now enables workspace administrators to self-serve the initial VPN networking setup directly from the admin console. This enhancement streamlines the process for connecting Glean to on-premises or private data sources, eliminating the need for manual coordination with Glean support or Solutions Engineering. Customers can quickly configure VPN connectivity themselves, reducing setup time and accelerating access to internal resources.

How to access: To set up VPN networking for on-premises or private data sources:

• Sign in to the Glean Admin Console with an Admin or Setup Admin role.
• Navigate to the networking or data source setup section and select the VPN setup option.
• Enter the required VPN parameters, such as peer IP, transit/local CIDR range, IKE version, and pre-shared key (PSK).
• Follow the on-screen prompts to complete and validate the configuration.

Learn more

Platform Capabilities ROAD-989

Get real-time alerts for data source health issues

Admins will now receive proactive alerts within the Admin console UI when connected data sources experience health or credential issues, such as failed syncs or expired credentials. These alerts help ensure that admins are immediately notified of problems that could impact search completeness or data freshness, enabling faster self-service troubleshooting and reducing downtime. Alerts include details about the affected data source, the specific error, and direct links to relevant documentation for resolution. This enhancement improves visibility and control over data source health, supporting a more reliable and up-to-date Glean experience.

How to access: To view issues requiring attention:

• Go to the Glean Admin Console and navigate to Dashboard.

Learn more

Admin Capabilities ROAD-871

[Action Required] End of Support for Gemini Models on Agentic Engine V1

Glean is ending support for Agentic Engine V1, and customers on Customer Key Gemini must migrate to Agentic Engine V2 by February 15, 2026. After this date, all new Assistant and Agent capabilities will be built on Agentic Engine 2 and Assistant and Agent experiences will no longer be supported for customers who do not migrate.

Agentic Engine V2 represents a significant upgrade over V1, delivering statistically significant improvements in enterprise use cases. The new engine features adaptive planning for more intelligent task handling, iterative reasoning for better problem-solving, and multi-step task execution for complex workflows. The vast majority of customers have already migrated and are benefiting from these enhancements.

No action is required for customers already on Agentic Engine V2, including all Glean universal key customers.

How to access:

Step 1: Configure the LLM Model
Navigate to Admin Console → Platform → LLM
Under "Select models for assistant," choose your provider and set Gemini 3.0 Pro Preview as your thinking mode agentic reasoning model and Gemini 2.5 Flash as your fast mode agentic reasoning model.

Step 2: Enable the Features
Navigate to Admin Console → Platform → Assistant → Settings
Under "New agentic engine features," enable Fast and Thinking modes
Enable for everyone

Learn more

Assistant ROAD-1070

Procore connector

Users can now securely search and access construction project data from Procore directly within Glean. This integration enables project teams, field staff, and back-office teams to find the latest status, review submittals and RFIs, and streamline decision-making across distributed construction projects—helping contractors standardize workflows, save time, and increase adoption.

Learn more

Connectors ROAD-812

Billing Moderator role for credits dashboard access

Organizations can now assign a dedicated Billing Moderator role that grants read-only access to the workspace billing and credits dashboard without making someone a full Glean Admin. This lets finance teams, budget owners, and billing contacts monitor credits usage and spending while preserving least‑privilege access and keeping core admin controls limited to your IT and admin teams.

How to access: Administrators must enable for your organization. To grant someone access to the billing and credits dashboard, a Glean Admin should assign them the Billing Moderator role, either directly on their account or via an identity provider group using group-based permissions. Once assigned, users with the Billing Moderator role can sign in to Glean and view workspace billing and credits information, but they will not have broader admin access to workspace settings.

Learn more

Admin Capabilities ROAD-1142

Sensitive content policies templates

Glean provides a set of categorized templates for creating new sensitive content policies, helping eliminate the cold start around what to include and how to structure a policy.

Learn more

Protect ROAD-964

Original source

User Features

Write better Emails and messages with dedicated Canvases

You can now draft and refine emails and messages in dedicated Canvas templates that feel tailored to Gmail and chat. When we detect you’re composing a communication, Glean opens the right Canvas experience and keeps one-click export to your preferred email or messaging client.

Learn more

Assistant ROAD-903

Model choice in Assistant [Glean Universal Key Only]

Users now have direct control to select which AI model powers their Glean Assistant conversations. Users can choose between leading models such as GPT and Claude for each Assistant chat, unlocking flexibility and allowing teams to optimize for speed, depth, and quality as needed. Organization admins may limit which models are surfaced for users, while Glean continues to provide high-quality defaults for a seamless experience. Available for Glean Key customers only.

Note: With this feature, users will be able to select a model for a chat session, but will not be able to change the default models used for Assistant.

Learn more

Assistant ROAD-853

Re-run workflow agents from a previously executed step in Agent Builder Preview

Agent Builder Preview now lets you re-run an agent from any previously executed step in the workflow. This lets you skip unchanged steps and reuse the preserved states and outputs to speed up iteration and debugging of complex, multi-step workflow agents.

Learn more

Agents ROAD-1046

Auto-generate agent description upon sharing

Agent creators can now generate and confirm agent descriptions when sharing agents with others. If you share an agent that doesn’t have a description, Glean will suggest an icon and an auto-generated description, which you can review, edit, or replace before confirming sharing. You’ll also see a new Enhance icon next to the agent description field (under the agent title and in Settings) that lets you instantly generate or refine the description at any time. Descriptions remain optional, but it’s now much easier to keep your agent library clear and self-explanatory with minimal effort.

How to access: To use this feature, open the Agent Builder and click the Share button when you’re ready to share your agent. If your agent doesn’t have a description, Glean will automatically suggest one along with an icon. You can review, edit, or replace the suggested description before confirming.

Learn more

Agents ROAD-1044

Bitbucket Server Mirror Project & Global Permissions

The Bitbucket Server connector reflects user and group permissions by incorporating global, project and repository level access controls. This enhancement ensures that users see all Bitbucket Server content they are entitled to, even when permissions are granted at the project or global level a common practice for Bitbucket administrators. As a result, search results in Glean match Bitbucket’s native access model.

How to access: No additional setup is required for permissions inheritance; the connector now automatically crawls and applies both project-level and repository-level permissions. This is automatically supported for Bitbucket Data Center version 8.5 and above

Learn more

Connectors ROAD-1120

Admin Features

Assign Glean roles and permissions using identity provider groups

Use your existing identity provider groups, Azure AD or Google Groups, to assign Glean roles at scale, so users automatically inherit the right permissions based on their group memberships instead of being managed one by one.

Learn more

Admin Capabilities ROAD-860

Manage the rollout of new Beta & Generally Available features

The managed rollouts feature is a centralized place for admins to see major, new features being released, test them, and then manage the timeline and change management surrounding the features.

Learn more

Admin Capabilities ROAD-732

[Action Required] End of Support for GPT and Claude Models on Agentic Engine V1

Glean is ending support for Agentic Engine V1, and customers on Customer Key OpenAI or Claude must migrate to Agentic Engine V2 by January 31, 2026. After this date, all new Assistant and Agent capabilities will be built on Agentic Engine 2 and Assistant and Agent experiences will no longer be supported for customers who do not migrate. No action is required for customers already on Agentic Engine V2, including all Glean universal key customers. Customers on Customer Key Gemini will be asked to migrate once Gemini 3.0 is available on Agentic Engine V2.

How to access:

Step 1: Configure the LLM Model
Navigate to Admin Console → Platform → LLM
Under "Select models for assistant," choose your provider and set GPT-5 or Claude Sonnet 4.5 as your agentic reasoning model

Step 2: Enable the Features
Navigate to Admin Console → Platform → Assistant → Settings
Under "New agentic engine features," enable Fast and Thinking modes
Enable for everyone

Requirements:
If using Customer Key, you must manually configure GPT-5 (via OpenAI Direct or Azure) or Claude Sonnet 4.5 (via Google Vertex AI or Amazon Bedrock)
If using Glean Key, you'll be automatically migrated to GPT-5
For self-hosted deployments, ensure your deployment occurred on or after September 4th, 2025

Learn more

Assistant ROAD-1034

Enable creation of multiple test groups for datasources

Admins can now create and assign multiple test groups for each data source in Glean. This enhancement allows organizations to test and validate different data sources with distinct groups of users, improving control and flexibility during rollout. With this update, admins can ensure that only the right users have early access to specific data sources, streamlining testing and reducing the risk of unintended data exposure.

Learn more

Connectors ROAD-824

Sensitive Findings Insights and Dashboard

The new Findings Dashboard gives administrators a clear, high-signal view of sensitive findings across all policies, info types, and data sources. This dashboard makes it easy to track the progress of sensitive content detection, monitor trends over time, and quickly identify areas of risk. With aggregated insights and flexible filters, large organizations can efficiently manage data protection, demonstrate compliance, and take action to reduce exposure.

Learn more

Protect ROAD-957

Original source

User Features

New user confirmation experience for write actions in Agents

Agents now by default pauses before making changes, summarizing planned updates so users can quickly review, adjust, and approve high-impact write actions. Users can chain outputs from earlier write steps as inputs to later ones which will help your agents deliver faster end-to-end workflows across your systems while keeping humans in control.

Learn more
Actions ROAD-1103-MR

Search results in Chat for keyword-focused queries

Chat in Assistant now surfaces a short set of top search results within your conversation for keyword and search-like queries. This enables you to navigate to relevant documents directly in chat conversations quickly, so you don’t have to switch to the search setting or wait for a full chat response. You’ll get to the information you need faster, improving productivity and reducing context switching.

How to access: No setup is required—this feature is available to all users in Assistant. When you enter a keyword or search-like query in a chat conversation, you’ll see top search results appear directly in the chat window. Click any result to open the document, or continue your conversation as usual. For more details on using chat and search, visit the Glean Help Center.

Release plan:
Dec 2 for customers with chat-first deployments
Jan 15 for other customers

Learn more
Assistant ROAD-1025-MR

Custom actions defaulted to run in scheduled and interactive agents without user confirmation

Configure custom actions to run automatically—without user confirmation—in both interactive and scheduled agents, while giving admins full control over which actions are allowed to run this way. This lets teams safely automate more work while maintaining admin control.

How to access: Administrators must enable for your organization. In the Admin Console, go to Actions, select the relevant custom action, and enable the option to run without user confirmation for agents. This setting determines which actions are eligible to run automatically in both interactive and scheduled agents. In Agent workflow builder, when creating or editing an agent, add the custom action as a step and ensure the “run without confirmation” option is enabled for that step. For scheduled agents, only actions configured for auto-run will be available.

Learn more
Actions ROAD-1087

View all agent runs in chat history

Background agents (e.g. scheduled agents) now also appear directly in Chat History alongside your conversations with Assistant and manual agent runs, under the Chats on your left navigation bar. You can quickly scan results, open full run details in one click, and use filters to see only Assistant chats or runs from a specific agent.

How to access: Administrators must enable for your organization. Chat history must be enabled by admins for users to use this functionality.

Learn more
Agents ROAD-1063

Updated preview experience for agents

The Agent Builder now features a flexible, dockable preview panel you can move and resize to view results alongside step configuration for faster iteration. This combined with real-time indicators showing which node is running, paused for input, or completed to make debugging simpler and more transparent.

How to access: Administrators must enable for your organization.

Learn more
Agents ROAD-1009

85 new actions available in Glean Assistant & Agents

Glean has expanded its agent actions library, delivering over 85 ready-to-use actions across GitHub, Google Calendar, Jira, Confluence and Salesforce. The actions are currently supported in Glean Agents and Glean Assistant.

How to access: Administrators must enable for your organization from within the Admin console.

Learn more
Agents ROAD-761

Enhancements to reports and dashboards in the Salesforce connector

Glean uses hybrid search for Salesforce dashboards and reports. It indexes dashboard metadata to understand how metrics are defined, then performs a real-time fetch at query time to pull the latest chart and table values. Users can ask questions like “Read the GTM dashboard and tell me our current ARR” and get real-time answers.

How to access: Administrators must enable for your organization. To use federated fetch for Salesforce Reports and Dashboards in Glean Chat:

Ensure admin has connected Salesforce data source in Glean with the required permissions, including access to Reports and Dashboards objects.
Each user must individually authenticate their Salesforce account in Glean to enable live data access for reports and dashboards.
When a user asks a question in Glean Chat that references a Salesforce report or dashboard, Glean will automatically fetch the latest data directly from Salesforce, provided you have the necessary permissions. If users are not authenticated, Glean will prompt them to connect their Salesforce account. Then they can interact with live Salesforce data in chat.

Learn more
Assistant ROAD-1081

Personalization and memory in Glean Assistant (GCP)

Glean is adding personalization functionality to Assistant so it can remember details from your conversations and work history to tailor future interactions, making it feel like an intelligent coworker that retains the context that matters most to you. Personalization combines implicit and mined memories from chat sessions and past work activity (within retention guardrails) with explicit, user‑controlled saved memories.

Learn more
Assistant ROAD-828

New experience for user confirmation for actions in Assistant

Glean Assistant can now execute multiple actions, taking the input from a previous action and applying it to the next action in a single run. Users can chain outputs from earlier write steps as inputs to later ones, supporting more complex Assistant queries while keeping users in control.

Learn more
Actions ROAD-1095

Update to admins on Adaptive Planning in Agents

Adaptive Planning is now available for Glean Agents, enhancing agent workflows with improved reasoning and flexibility. Starting with the January 20, 2026 release, all agents using the Plan & Execute step were automatically upgraded from Basic to Thinking mode, enabling deeper, more iterative problem-solving. Agents will continue to use the best available model within their configured model family, and those previously set to "Same as Assistant" will now use "Best," ensuring optimal performance for each request. No customer action is required—this upgrade ensures agents benefit from the latest planning and reasoning capabilities while preserving existing model preferences.

This feature may use credits. Learn more in Glean's Help Center.

How to access: No customer action is required for this upgrade. The transition will occur automatically for all deployments with Agentic Engine enabled.

Learn more
Agents ROAD-1098

Image generation in Glean Assistant with Nano Banana Pro now supported for AWS and Azure (Glean Key)

Bring your ideas to life directly in Glean Assistant with Nano Banana Pro. You can now ask Assistant to create images from natural language prompts and it will respond with visuals in your chat response. This accelerates creative cycles and unlocks fast iteration for drafts, diagrams, social posts, and more. Image generation in Assistant allows you to include design direction in prompts based on internal documents and avoid switching tools. Now available for customer key on Azure and AWS.

This feature may use credits. Learn more in Glean's Help Center.

Learn more
Assistant ROAD-1102

Make your writing shine with Editing Shortcuts within Canvas

The Editing Shortcuts feature in Glean Canvas lets you apply common rewrites—like fix grammar, make concise, or change tone—with a single click instead of re-prompting in chat. When you highlight text and hit the shortcut button, a small menu of actions (Polish, Length, Tone) appears; choosing one sends a hidden, tuned prompt to the model and replaces just that selection with the improved version. This turns repetitive editing prompts into fast, in‑place adjustments so you can quickly polish, resize, and retune your writing without leaving the document.

Learn more
Assistant ROAD-902

Admin Features

Admin chat for help setting up and configuring Glean

Glean offers admin chat, a natural language chat for help setting up and configuring the admin console, using data from Glean documentation, website, developer docs, and the Gleaniverse. If self-serve support isn’t enough, the admin chat can escalate to Glean's support team.

How to access: From the Admin Console, open the Help menu and select Admin chat to start a conversation.

Learn more
Admin Capabilities ROAD-829

Turn Deep Research Default On for Glean Key customers

Deep Research was enabled by default for all customers on Glean Key for OpenAI and Glean Key for Azure OpenAI on January 15th, 2026. As previously shared in Coming Soon notes, Admins could pre-opt out by contacting their Account Manager and going forward, Admins have full control over which users have access to Deep Research and their usage quotas. Admins can set monthly query limits per user, restrict usage to specific users or departments, or turn off the feature entirely in Admin Console → Assistant → Deep Research.

This feature may use credits. Learn more in Glean's Help Center.

How to access: Administrators can access deep research in the Admin Console (Assistant → Deep Research).

Learn more
Assistant ROAD-1023

Crawl JavaScript websites (AWS)

You can now use the Glean Website connector to crawl and index JavaScript-enabled websites in AWS deployments. This update brings feature parity with GCP deployments, allowing organizations on AWS to make dynamic, JavaScript-rendered web content discoverable in Glean search. Teams can now access more complete and up-to-date website content, improving search coverage and knowledge discovery for sites that rely on client-side rendering.

How to access: To connect a JavaScript-enabled website as a data source in an AWS deployment:

In the Glean Admin Console, go to the Data Sources tab and select “Add Data Source,” then choose “Website.”
Enter the display name and provide either a sitemap URL or seed URLs for the site you want to index.
For JavaScript-heavy sites, enable Client-Side Rendering (CSR) in the advanced settings. CSR should only be used for public pages that do not require authentication, as it cannot be combined with cookies, authentication headers, or Single Sign-On (SSO).
Save the configuration and trigger the initial crawl. Review the results and adjust settings as needed to ensure all desired content is indexed.

Learn more
Connectors ROAD-1086

Crawl preview during web data source setup

The web crawl preview allows admins to preview the content and child links of web pages(configs determining crawl logic)-such as authentication, site fetch, and advanced settings-before running a full crawl. By surfacing potential misconfigurations and showing a sample of indexed pages in real time, admins can verify and correct their setup immediately, reducing delays and improving the onboarding experience for web data sources.

Learn more
Connectors ROAD-1038

Faster indexing for newly greenlisted Jira projects

When a Jira project is added to the greenlist, Glean now triggers a targeted crawl for that project instead of requiring a full content crawl. This enhancement reduces load on Jira servers and ensures that newly greenlisted projects are indexed and searchable more quickly. The update is especially valuable for large enterprises using project-level greenlisting, improving both efficiency and data freshness.

Learn more
Connectors ROAD-880

Redlist content in Microsoft O365 SharePoint and OneDrive Hide with sensitivity labels

Glean now supports redlisting content using Microsoft Purview sensitivity labels for SharePoint and OneDrive. This ensures that items tagged with selected labels are not surfaced in search, chat, and agent experiences. Admins can configure which sensitivity labels to redlist, and updates to these labels are propagated rapidly—typically within a few hours.

How to access: This feature is not currently self-service and cannot be configured directly from the Glean Admin Console. Configuration must be completed with assistance from Glean. To enable redlisting of content via Microsoft Purview sensitivity labels for SharePoint and OneDrive, an admin must:

In Azure, locate the app registration connected to your SharePoint/OneDrive instance.
Add the SensitivityLabels.Read.All Graph API application permissions and grant admin consent.
Provide your Glean representative with the list of sensitivity label priority numbers, specifying which labels should be redlisted for SharePoint and OneDrive.

Learn more
Connectors ROAD-746

Details on sensitive and non-sensitive logs for AWS Customers

Glean now tags all AWS CloudWatch log groups and S3 buckets created by Glean as either sensitive or non-sensitive using the glean-sensitive: true|false tag. Additionally, an object in an S3 bucket within the Glean AWS account provides a comprehensive list of these resources. This enhancement makes it easy for customers to identify where sensitive data resides, improving transparency and supporting security and compliance needs. Sensitive data refers to data that can contain raw indexed document details or user queries. This data can contain any data that is stored or entered in, such as PII if present.

Learn more
Platform Capabilities ROAD-1019

Export sensitive findings via UI and API

Glean Protect administrators and developers can now download sensitive findings from weekly and continuous scans, filtered by data source or policy, directly from the Glean Protect user interface or programmatically via the Governance API. This enhancement streamlines remediation workflows by making it easy to share, triage, and automate actions with source system owners. With flexible export options, security teams can quickly access, filter, and distribute sensitive data findings for compliance, incident response, or integration with external tools.

How to access: To export sensitive findings:

In the Glean Admin Console, navigate to Glean Protect → Sensitive findings.
Use dashboard filters to select findings by datasource, policy, or other criteria.
Click the export button to download filtered findings as a CSV file. Only one export can be in progress per user at a time; completed exports are available for download in the export drawer.
For programmatic access, use the Governance API to export findings for integration with SIEM, SOAR, or other security tools. Refer to the Glean developer documentation for API usage and authentication details.

Learn more
Protect ROAD-948

Original source

User Features

Code Writer: In Assistant, Slack and Agent actions

Code Writer is an AI-powered code action in Assistant and Glean Agents that edits code and opens draft PRs end‑to‑end, built with enterprise‑grade security and controls. It’s ideal for small features, refactors, tests, and docs, and can be triggered from Assistant, Agents, or Slack.

How to access: Administrators must enable for your organization. Available for GCP and AWS customers using GitHub

This feature may use credits. Learn more in Glean's Help Center.

Learn more

Actions ROAD-785

Run Deep Research in existing chat conversations

Glean Assistant users can now run Deep Research in a pre-existing conversation, rather than only at the beginning of a brand new one. When a user's query would benefit from deeper, multi-source synthesis, they can now follow up in Deep Research mode. This makes it easier to discover and benefit from Deep Research, helping users access more comprehensive, citation-rich analysis directly when needed and improving satisfaction and outcomes for complex research tasks.

To learn more about Deep Research pricing for flex credits, please visit our pricing documentation: [/glean-enterprise-flex-pricing|/glean-enterprise-flex-pricing].

How to access: Administrators must enable for your organization. Administrators can enable via self-serve in the Admin Console (Assistant → Deep Research) for all users or specific users.

This feature may use credits. Learn more in Glean's Help Center.

Learn more

Assistant ROAD-1072

Glean in Webex

Glean is now embedded within Webex through the Cisco AI Assistant in the Webex ecosystem. Users can query Glean directly from within Webex—whether in meetings, messaging, or elsewhere—to discover knowledge and boost productivity. This integration enables seamless access to your connected Glean instance, helping you find information and get work done without leaving Webex.

How to access: Administrators must enable for your organization.

Learn more

Embedded Integrations ROAD-986

Zoom: participant access for cloud recordings

Glean now allows access for cloud recording transcripts to participants and invitees of a meeting. Previously, only meeting organizers could access Zoom meeting transcripts in Glean. With this update, Glean will surface transcripts to users who have access to recordings via glean participant role OR individual role, making it easier for teams to find, search, and summarize meeting content directly in Glean.

Learn more

Connectors ROAD-1010

Admin Features

Improving metric granularity on Overview page of Insights

We're bringing in upgrades to the overall usage-related metrics reported on the Insights Overview page.

Learn more

Admin Capabilities ROAD-1050

Configure actions during data source setup - Expand to all eligible datasources

Access and configure actions directly from the data source setup flow via clear “Go to setup” links. This new experience introduces an optional Actions step in the datasource setup UI, making it easier for admins to discover and enable relevant pre-built actions and (soon) MCP tools for select apps—all while configuring the datasource, without context switching. With this latest update, the combined setup is supported for all actions - Google, Microsoft, Salesforce, Jira, etc.

Learn more

Admin Capabilities ROAD-1037

Display indexing status in the admin console

Admins can now view the indexing status of all connected data sources directly in the Glean admin console. This enhancement provides clear visibility into which data sources are fully indexed and which are still in progress, helping admins monitor the health of their deployment and ensure that content is discoverable as expected. With this update, admins can quickly identify and address any issues that may impact search completeness or data freshness.

How to access: To view the indexing status for your data sources:

Go to the Glean Admin Console and navigate to the Data sources section.

The table of configured apps will display the progress of each crawl, including the number of documents indexed and any errors encountered.

You can monitor crawl and indexing status at any time to ensure your data sources are up to date and troubleshoot as needed.

Learn more

Admin Capabilities ROAD-848

Native connectors that are hybrid are configured in data sources in the admin console

Native connectors that are hybrid—combining indexed and federated access—are configured in the Admin Console under the Data sources tab. From there, you can now manage Confluence Cloud access to both indexed and federated data.

Learn more

Admin Capabilities ROAD-846

Improvements to answer quality for multi-modal PDF uploads in Assistant (AWS)

Now available for customers on AWS, Glean has significantly improved the quality of answers related to PDF documents that are referenced in Glean assistant via uploading files, tagging documents in chat, mentioning a document by @ mention, pasting URLs. The quality improvements also apply to multi-modal PDF documents that include images. This feature was previously released for customers on GCP.

How to access: To experience the improved quality, admins need to enable the AWS Bedrock model amazon.titan-embed-image-v1 in the us-west-2 region via the AWS Management Console. To do this, log in to the AWS Console, navigate to the Bedrock service, select the us-west-2 region from the region selector, locate the amazon.titan-embed-image-v1 model in the list of available models, and enable it for your account. Once enabled, the model will be available for use in your Bedrock applications.

Learn more

Assistant ROAD-742

Simpplr Connector (AWS Version)

Glean now offers an all-new Simpplr connector built specifically for Simpplr’s AWS platform. As Simpplr transitions all customers from Salesforce to AWS, this connector ensures your organization can seamlessly index and search core Simpplr content—Pages, Sites, and Events—within Glean. The connector honors granular Simpplr permissions, supports efficient incremental crawls, and delivers a streamlined intranet search experience throughout and after your Simpplr platform migration.

Learn more

Connectors ROAD-423

Adjust info types thresholds for better defaults in sensitive findings

Admins can now customize the detection threshold (likelihood) for each info type in Glean Protect+ sensitive findings policies and reports. This enhancement provides more granular control over data loss prevention (DLP) results, helping organizations balance coverage and accuracy for sensitive data detection. Improved default values for common info types reduce false negatives and make it easier to surface relevant findings, increasing the reliability and transparency of DLP for diverse environments.

How to access: Glean Admin Console and navigate to Protect → Sensitive findings.

Learn more

Protect ROAD-973

Original source

User Features

Company search improvements in Agents

Santa release FOO BAR BAZ

How to access: Available to all Agent Builders.

Learn more

Actions ROAD-1045-MR

Changes to Glean Assistant: Retiring datasource filtering and source removal

Glean Assistant will retire two features: the ability to filter specific sources in chat and the option to remove sources from existing Assistant responses. These features are being removed to streamline the user experience and because the latest generation of Glean Assistant, powered by advanced LLMs like GPT-5 and Claude Sonnet 4.5, now provides more accurate, context-aware answers without requiring manual source selection.

With improvements in Assistant, users can simply describe what they need in natural language—including whether it should focus on or exclude a specific data source—and Assistant will automatically execute. Users can continue to filter specific sources in search.

Change date: December 4, 2025

How to access: Customers in our Managed Feature Beta may have additional controls.

Learn more

Assistant ROAD-938-MR

GPT 5.2 in Agents

GPT‑5.2 is available in the model hub for Glean Agents. It's a supported model for both the Glean universal model key and customer keys on OpenAI and Azure OpenAI.

GPT‑5.2 delivers stronger long‑horizon reasoning, tool calling, and complex quantitative analysis, making it especially well‑suited for agentic data analysis, operational investigations, and complex document/knowledge‑work agents.

How to access: Admins can enable GPT‑5.2 via Admin Console → Platform → LLM, and creators can select it per‑agent or per‑step in the Agent Builder.

This feature may use credits. Learn more in Glean's Help Center.

Learn more

Assistant ROAD-1060

Admin Features

Detect and prevent sensitive data exposure from screenshots

Glean Protect now detects and prevents sensitive data exposure from screenshots when agents or Assistant use the vision API. Glean Protect triggers real-time blocking and alerting through continuous scanning, ensuring that screenshots and images attached to prompts are checked for sensitive data before being processed or sent to the model provider. As an admin, you can configure where images are sent and which policies are enforced based on your organization's security requirements. Admins can configure policies and exemption lists based on apps or connectors. This functionality is turned off by default.

How to access: Configure via Admin Console → Glean Protect → Continuous scanning.

Learn more

Governance & Compliance ROAD-1012

Original source

User Features

Company search improvements in Agents

Company Search is now easier to configure and debug in Agents. Glean now surfaces a clearer view of the underlying query and highlights key operators (such as app and date filters) so you can quickly verify the scope and behavior. You can inspect what actually ran during a preview, copy the query, and adjust it if needed—reducing guesswork and making it faster to tune agents that depend on company-wide search.

How to access: Available to all Agent Builders.

Learn more

Actions ROAD-1045-MR

Changes to Glean Assistant: Retiring datasource filtering and source removal

Glean Assistant will retire two features: the ability to filter specific sources in chat and the option to remove sources from existing Assistant responses. These features are being removed to streamline the user experience and because the latest generation of Glean Assistant, powered by advanced LLMs like GPT-5 and Claude Sonnet 4.5, now provides more accurate, context-aware answers without requiring manual source selection.

With improvements in Assistant, users can simply describe what they need in natural language—including whether it should focus on or exclude a specific data source—and Assistant will automatically execute. Users can continue to filter specific sources in search.

Change date: December 4, 2025

Learn more @ /release-notes/sunset/assistant

How to access: Customers in our Managed Feature Beta may have additional controls.

Learn more

Assistant ROAD-938-MR

GPT 5.2 in Agents

GPT‑5.2 is available in the model hub for Glean Agents. It's a supported model for both the Glean universal model key and customer keys on OpenAI and Azure OpenAI.

GPT‑5.2 delivers stronger long‑horizon reasoning, tool calling, and complex quantitative analysis, making it especially well‑suited for agentic data analysis, operational investigations, and complex document/knowledge‑work agents.

How to access: Admins can enable GPT‑5.2 via Admin Console → Platform → LLM, and creators can select it per‑agent or per‑step in the Agent Builder.

This feature may use credits. Learn more in Glean's Help Center.

Learn more

Assistant ROAD-1060

Support GPT 5.1 on Glean Assistant

We're launching GPT 5.1 as Glean Assistant's primary model for the Glean key on Dec 12, 2025 for both Thinking and Fast Modes. GPT 5.1 delivers nearly 50% faster responses in Thinking Mode (~14 seconds saved per query). This model delivers significant quality improvements, with 52% more upvotes and 30% fewer downvotes. We fine-tuned GPT 5.1's system prompts to be more proactive and autonomous, eliminating unnecessary clarifications while improving parallel tool execution. GPT 5.1 will also be available on Customer Key (Azure OpenAI and Direct OpenAI). GPT 5.1 is the same average cost per query as GPT 5.

Learn more

Assistant ROAD-1028

Image generation in Glean Assistant with Nano Banana Pro (Glean Key)

Bring your ideas to life directly in Glean Assistant with Nano Banana Pro. You can now ask Assistant to create images from natural language prompts and it will respond with visuals in your chat response. This accelerates creative cycles and unlocks fast iteration for drafts, diagrams, social posts, and more. Image generation in Assistant allows you to include design direction in prompts based on internal documents and avoid switching tools.

Note: This feature will consume Flex Credits and will be turned on by default for all Glean Key customers on GCP for all users. Admins will have the ability to limit access to the feature from within the console.

This feature may use credits. Learn more in Glean's Help Center.

Learn more

Assistant ROAD-834

Deep linked citations - Claude and OpenAI Models on Agentic Engine V2

Deep linked citations instill trust and improve the usability of Glean Assistant. When Glean Assistant cites a source, users can now verify and explore the exact relevant excerpt in the original document, making it easier to validate claims and gain immediate context. This update provides more transparent, verifiable, and actionable information within AI-powered conversations.

How to access: This feature automatically turned on.

Learn more

Assistant ROAD-757

Admin Features

Reduced latency in the data analysis tool for customers on the universal model key

Glean's data analysis tool in thinking mode is 40% faster while staying consistent on accuracy and completeness. The data analysis tool is invoked when a structured file is uploaded or a link is tagged. This latency improvement impacts customers on the universal model key or using OpenAI customer keys.

How to access: You can turn the feature on or off via the admin console by going to Settings -> Assistant -> Data Analysis.

Learn more

Assistant ROAD-979

Support Gemini on Customer Key for Agentic Engine 2

Glean Assistant now supports the Agentic Engine 2 on Gemini for customers using their own key. Thinking mode will use Gemini 3.0 Pro Preview, while Fast Mode will use Gemini 2.5 Flash. This update enables advanced multi-step reasoning and adaptive planning in Glean Assistant, powered by Google’s most advanced Gemini model. With Gemini 3.0, users benefit from improved answer quality, greater completeness, and more relevant responses, as the Assistant can continuously re-plan and adapt until your query is fully addressed. Organizations can now select Gemini as their LLM provider for agentic reasoning, broadening model choice and optimizing performance for diverse workflows.

Learn more

Assistant ROAD-915

Increasing Chat History Retention Period Options

We are introducing a unified, admin-controlled chat history policy with retention options of Off, 30 days, 90 days, six months, or one year. One year is the new default for all new deployments. The updated interface clearly displays what data is retained. Policy changes are applied retroactively: reducing the retention period will permanently delete older conversations (with confirmation), while increasing it will extend retention for existing and future chats. All assistant and agent conversations, as well as features like conversation search and personalization, will adhere to this unified retention window, providing teams with improved continuity and streamlined governance. Existing configurations will remain unchanged unless customers choose to upgrade.

Learn more

Assistant ROAD-772

Improved freshness for Gong calls

Glean now uses incremental crawls for the Gong connector so new calls become searchable in Glean within minutes after Gong finishes processing them, instead of hours or even days on large deployments. This greatly improves workflows that depend on recent calls—like post‑call follow‑ups or content‑triggered agents—so teams can act on the latest conversations much sooner. End‑to‑end freshness still depends on Gong’s own processing time (typically 10–60 minutes after a call ends). Manually uploaded, very long, or deleted calls may still take longer because they rely on periodic full crawls.

How to access: No action needed

Learn more

Connectors ROAD-1065

GitHub Enterprise - multiple GitHub Enterprise Server instances

Organizations can now connect and manage multiple GitHub Enterprise Server instances within Glean. This enhancement allows teams with separate production, development, or geographically distributed GitHub Enterprise environments to index, search, and enforce permissions across all their instances—without workarounds or manual configuration. The update streamlines onboarding for complex organizations and supports more flexible, scalable GitHub integrations.

Learn more

Connectors ROAD-913

New Docusign connector

The Docusign connector enables Glean to fetch and summarize DocuSign documents, envelopes and templates when a user shares a URL, so teams can quickly review agreements and ask follow‑up questions without leaving Glean.

Learn more

Connectors ROAD-747

Support groups in shared with and support exclusion filter as not shared with users and groups

Sensitive findings policies and reports now support a new exclusion filter for “not shared with” users or groups. This enhancement allows organizations to flag documents that are shared outside a designated set of users or groups (such as HR or Finance). By adding users or groups to the exclusion list, admins can ensure that only documents shared beyond the specified audience are scanned for sensitive content, improving compliance and reducing unnecessary findings.

How to access: Configure in the Glean Admin Console: Glean Protect → Sensitive findings

Learn more

Protect ROAD-949

Original source