Glean Release Notes

This release expands Glean’s AI capabilities, improves agent administration and collaboration, adds new platform integrations, and strengthens security, privacy, and reliability across connected data sources.

Major Launches

Connect Glean content events to your automations

The experimental Glean Triggers API lets developers subscribe to content events from connected data sources and deliver those events to external platforms and agents. You can register trigger subscriptions, search matching events, manage a trigger’s lifecycle, and receive signed webhook deliveries. This makes it possible to connect Glean activity to automation platforms, developer tools, and custom agent workflows while preserving the permissions of the subscribing user. The API is designed for integration builders who want Glean events to initiate work outside the Glean interface.

How to access: Use the Platform API with a token that has the required trigger scope, and include the experimental opt-in header on requests. The API is intended for developers and integration builders; the surface is experimental and may change.

Developer Platform

See your AI security posture in one place

Guardrails Insights gives security and governance teams a centralized view of AI guardrail activity. Instead of reviewing individual findings one at a time, administrators can use the dashboard to understand trends, policy confidence, topics, and high-risk users. The result is a clearer picture of where AI usage is creating risk and where investigation or policy changes may be needed. This is especially useful for teams responsible for monitoring AI usage, reviewing violations, and communicating security posture across the organization.

How to access: Open the AI Security Guardrails Insights dashboard from Glean Protect. Access depends on your organization’s Protect configuration and administrator permissions.

Protect

Preserve important agent drafts with saved versions

Agent Builder now lets you create named, immutable checkpoints of a draft agent. Saved versions give you a dependable way to preserve a meaningful configuration before making further edits, without changing the existing draft, staged, and published lifecycle. You remain in the editable draft state after saving. When you want to reuse an earlier checkpoint, select it from version history and load it back into draft, then continue editing or publish it through the normal workflow. This helps teams experiment more safely and revisit prior working states without maintaining parallel copies.

How to access: Open an agent in Agent Builder and use the version history or version selector to save, view, load, or delete draft checkpoints.

Agents

Rediscover useful work in the redesigned Library

The redesigned Library makes durable artifacts easier to find and revisit. You can browse artifacts you created, artifacts shared directly with you, and explicitly public company artifacts. New filters help you narrow results by creator team or department, while sorting options make it easier to find recently created or popular content. The experience is designed to move beyond a constantly changing recently viewed list, so high-signal artifacts are easier to rediscover after the original task is complete.

How to access: Open Library in Glean and use the ownership, department, creator, and sorting controls to browse and filter artifacts.

Library

Bring support agents into your browser workflow

Agents in the Glean Browser Extension lets users launch configured support agents directly from supported Zendesk, Salesforce Service Cloud, and ServiceNow pages. The agent can use the current ticket or case context so you can work without copying information into another window. This provides a replacement path for embedded support experiences and gives administrators a dedicated way to configure which agents are available. Starting August 24, 2026, the experience is generally available to eligible deployments with existing embedded-integration usage.

How to access: Install and sign in to the Glean Browser Extension. Eligible users can open the extension sidebar on a supported ticket or case page and select the Agents tab. Admins can configure access from the browser-extension settings.

Learn more

Agents

AI & Model Updates

Choose Gemini 3.7 Flash for fast, capable agent work

Gemini 3.7 Flash is now available as a model option in Assistant and Agents. It is designed for high-volume, low-latency work while supporting stronger reasoning for well-scoped tasks. You can select low, medium, or high thinking levels depending on whether you want faster responses or more deliberate reasoning. The model is available across supported Assistant and Agents surfaces, with access varying by deployment key configuration. Gemini 3.6 Flash remains available under More models, so existing model choices are not removed.

How to access: In Assistant, open the model selector and choose Gemini 3.7 Flash. For Customer Key deployments, an administrator may need to make the model available from Admin Console → Platform → Models.

Assistant and Agents

Get smarter defaults for workflow agents

Workflow agents that use “Let Glean decide” now default to GPT 5.6 Luna when it is available, with GPT 5.1 used as a fallback. This improves the default model choice without requiring builders to update existing agents. Explicit model selections remain unchanged, so teams that have deliberately chosen a specific model keep that configuration. The change applies to the default path only and is intended to improve the baseline experience for workflows that do not specify a model themselves.

How to access: No action is required for existing workflow agents using “Let Glean decide.” Open an agent’s model settings in Agent Builder if you want to review or choose an explicit model.

Agents

Use Anthropic models with your custom key

Custom-key customers can now use supported Anthropic models through Glean for production workloads. This gives teams another provider option when selecting models for their organization’s AI experience and lets customers align model usage with their existing provider and key-management strategy. Availability depends on the models supported by the configured Anthropic provider and the deployment’s permissions and setup.

How to access: An administrator must configure the Anthropic provider and custom key in the model settings available to your deployment. Once enabled, users can select supported Anthropic models wherever the model picker is available.

Models

Use real-time voice more naturally when you are interrupted

Real-time voice now includes a Talk uninterrupted control when Glean detects that you started speaking while it was responding. Tap the notice to switch into a push-to-talk interaction and finish your turn before Glean responds. This gives you a clearer way to continue speaking without losing your thought or competing with the assistant’s response. The control is designed for natural back-and-forth conversations on web, desktop, and mobile, where interruptions are expected and a hands-free interaction should not require restarting the exchange.

How to access: Start a real-time voice session from the waveform button in the composer. If Glean detects an interruption, tap the Talk uninterrupted notice to continue speaking.

Learn more

Assistant

Critical Updates

Review the new Engram Memory billing treatment

Engram Memory usage is now billed for Glean Core Suite plans across supported models. Migration usage remains free. For Enterprise Flex credit plans, usage remains free through September 15, 2026, and begins consuming FlexCredits on September 16, 2026. This change affects how memory-related usage appears in plan economics, but it does not change the underlying memory experience. Review your plan and usage expectations before the Enterprise Flex billing date if your organization relies on persistent Assistant memory.

How to access: No product action is required. Administrators should review their plan and usage reporting, and contact their Glean representative with billing questions.

Assistant Memory

Update integrations that use the Agents subscription schema

The public Agents REST subscription schema no longer includes the allowAllBgWriteActions field. Integrations that referenced this field should remove it from their requests or generated models. Background-run behavior and the internal setting remain unchanged, so this is a schema cleanup rather than a change to how subscriptions execute. The update matters only to integrations that directly consume the public subscription schema and expect the removed field to be present.

How to access: Update any integration or generated client that references allowAllBgWriteActions, then validate the subscription request against the current public schema.

Assistant API

Require HTTPS for dynamically registered MCP servers

Dynamic MCP client registration now requires server URLs that use HTTPS. Registrations that use an http:// URL will fail with a clear error instead of sending registration traffic over plaintext. This protects credentials and registration metadata while preserving the existing dynamic-registration workflow for secure servers. If you manage a custom MCP server that uses dynamic registration, confirm that its public registration URL is HTTPS before attempting to connect it.

How to access: No action is needed for existing secure servers. Update any custom MCP server configuration that uses an http:// registration URL to use HTTPS.

MCP

Limit certificate setup to full administrators

Certificate management APIs now require full administrator permissions to complete the SSL certificate setup flow. This narrows a sensitive configuration path to the role intended to manage organization-wide certificates and reduces the chance that a lower-privilege administrator changes security infrastructure unintentionally.

How to access: Full administrators can continue to complete certificate setup from the administrator experience. Users without full administrator permissions should contact an administrator with the required role.

Admin Console

Keep OneDrive access groups consistent

OneDrive Product Access Group membership checks now use stable datasource user IDs. This prevents inconsistent access decisions caused by relying on identifiers that could vary between checks. Administrators should see more reliable enforcement of the groups that control which users can access OneDrive content through Glean, without needing to change the groups themselves or reconfigure the connector.

How to access: No action is required. Continue managing Product Access Groups through the existing OneDrive administration workflow.

OneDrive

Let users request access to protected chats and artifacts

Users who open a protected chat or artifact they cannot access can now submit an access request instead of relying on an out-of-band message. The requester can optionally include context, while the owner can review and approve or deny the request. Approved users join under the existing participant and permission controls. This creates a clearer, auditable path for collaboration while keeping the owner or authorized administrator in control of access.

How to access: Open a protected chat or artifact. If you do not have access, use the request-access action and optionally add a message for the owner.

Assistant

Give Viewer-shared chats a consistent home in Projects

Chats shared with Viewer access now appear in Projects, including deployments where Multiplayer Chat is disabled. This makes shared conversations easier to find and gives recipients a consistent place to return to chats they can read. The change does not expand the underlying permission: a Viewer can see the chat only when it has been shared with them and continues to have Viewer-level access.

How to access: Open Projects and look for chats that have been shared with you as a Viewer.

Projects

Deprecations & Sunsets

Use the updated Embedded integrations administration URL

The Embedded integrations administration page now uses a URL that matches its page name. Existing Glean Assist links and bookmarks continue to work through redirects, so saved links do not need to be changed immediately. When updating internal documentation, onboarding materials, or bookmarks, use the new Embedded integrations route so future references align with the current product terminology and the browser-extension transition.

How to access: Navigate to Embedded integrations from the Admin Console. Existing Glean Assist URLs will redirect to the updated page.

Embedded Integrations

Enhancements

Find skills faster in Settings

The Skills tab in Settings now includes search by skill name. Use it to filter personal, shared, and platform skills instead of scanning the full list. Search results update within the current tab and show a clear empty state when no skill matches. This is particularly useful for organizations with many shared skills or for users who remember the purpose of a skill but not where it appears in the list.

How to access: Open Settings → Skills and enter a skill name in the search field.

Skills

Understand agent tools at a glance

Agent Builder now separates datasource tools into Read and Write sections. Each section has its own count, search behavior, and Add all tools control, making it easier to understand what an agent can retrieve and what it can change. Approval settings appear only when write tools are selected, so builders can see the relevant safety control in context instead of interpreting a mixed list. The same distinction is available when configuring action packs and MCP servers.

How to access: Open an agent in Agent Builder and expand a datasource, action pack, or MCP tool selection. Use the Read and Write sections to review or change the toolset.

Agent Builder

Make agent version history easier to scan

The version history menu now puts saved-version names first, with the date and author underneath. Only the current version is labeled Published, and empty histories explain how to begin tracking changes. Expanded version groups scroll into view, and hover highlights clear correctly after selection. Together, these changes make it easier to distinguish versions, understand the current lifecycle state, and navigate a growing history without opening each version one by one.

How to access: Open an agent in Agent Builder and open its version history menu.

Agents

Start voice with useful context sooner

Voice onboarding is now shorter and more personalized. New users see a concise welcome and can opt into a daily briefing rather than stepping through a multi-screen tutorial. The briefing can help users begin with relevant work context, while returning users continue to receive the standard voice greeting. This reduces setup friction and gets you to a useful voice interaction faster without changing the normal experience after onboarding.

How to access: Start real-time voice from the waveform button in the Glean composer. New users will see the updated welcome automatically.

Learn more

Assistant

Identify inactive agents before cleanup

The inactive agents CSV export now includes a Last edited by email column. Administrators can use this information to identify the person who last changed an unused agent before deciding whether to archive, update, or remove it. The added detail makes cleanup conversations more targeted and reduces the need to investigate ownership through separate systems.

How to access: Export the inactive agents CSV from the Agents administration or insights experience and review the new column.

Agent Insights

Preserve approval settings while editing tool selections

Agent Builder now retains Run without approval settings when you edit actions in a selected action pack or change the tools selected for an MCP server. This prevents an edit to the tool list from unexpectedly resetting an intentional approval choice. Newly added action packs and MCP servers still start with Run without approval turned off, so builders must explicitly enable the setting for new additions.

How to access: Open an agent’s action pack or MCP configuration in Agent Builder, then edit its tools. Review the approval setting before saving changes.

Agent Builder

Complete support-agent forms with less clutter

Support agents now show automatically captured ticket-page content as a compact, non-editable pill instead of placing the full captured content directly in the form. The complete context is still sent when the agent runs. Forms also place focus on the first empty field, so you can begin entering the information the agent actually needs without moving past prefilled context. This makes browser-based support workflows easier to scan and faster to complete.

How to access: Open a supported Zendesk, Salesforce Service Cloud, or ServiceNow page with the Glean Browser Extension, then open the Agents tab.

Learn more

Glean Extension

Make agent status notifications clearer

Agent Builder notifications now state the outcome of the action that occurred. Publishing, sending an agent for review, and approving or rejecting a review each display a corresponding success message. Import failures are now reported as errors instead of warnings, making it easier to distinguish a completed action from a problem that needs attention. These clearer messages reduce uncertainty during publishing and review workflows, especially when several changes are being made in sequence.

How to access: No action is required. The updated messages appear automatically in Agent Builder when you publish, review, approve, reject, or import an agent.

Agent Builder

Search large app lists more easily

The Agent Builder app-selection dropdown now supports search. When many Teams or Slack apps are available, enter an app name to narrow the list instead of scrolling through every option. This reduces the time required to configure an agent for a specific app and makes the selection experience more manageable for organizations with multiple connected workspaces or channels.

How to access: Open the app-selection dropdown in Agent Builder and enter the name of the Teams or Slack app you want to select.

Agent Builder

Run eligible MCP tools in the background

MCP tools now support background execution by default. This allows eligible tool calls to continue without blocking an interactive flow, while administrators retain control through each tool’s Background Execution Policy. You can disable background execution when a tool needs to remain synchronous or requires closer review. The setting is applied per tool, so teams can choose a different execution policy for different connected capabilities.

How to access: Administrators can review each MCP tool’s Background Execution Policy from the MCP server configuration and disable background execution when needed.

MCP

Allow eligible Composio writes to run without a confirmation click

Administrators can now allow Composio write tools to run in the background without manual confirmation by default. Existing policies remain unchanged, and administrators continue to control the behavior through each tool’s Background Execution Policy. This can shorten workflows where a write is already governed and does not need an additional confirmation step, while preserving the ability to require confirmation for higher-risk actions.

How to access: Configure the Background Execution Policy for the relevant Composio write tool. Agent creators can then use the eligible action in an interactive agent.

Actions

Separate host-app setup from MCP server management

The Glean MCP servers administration page now opens with separate Host apps and MCP servers tabs. Host apps show where connected clients are configured and used, while MCP servers provide the server and tool-management workflow. Separating these concepts makes it easier for administrators to find setup information, review usage, and manage the right object without navigating through a combined page.

How to access: Open the Glean MCP servers page in the Admin Console and choose the Host apps or MCP servers tab.

MCP

Add Skills tools to selected MCP servers

Administrators can add Glean’s Skill tools—find_skills, read_skill_files, and run_tool—to an MCP server. Connected MCP clients can then discover relevant skills on demand and run their underlying tools without loading the full catalog up front. The tools are opt-in per server and are not enabled automatically, giving administrators control over which clients can discover and execute skills through each MCP connection.

How to access: Open an MCP server in the Admin Console, choose the Skill tools pack from the tool catalog, and save the server configuration.

MCP

Find Glean content through DocuSign MCP

DocuSign MCP is now generally available through Glean’s managed MCP catalog using DocuSign’s production server and OAuth endpoints. This gives administrators a production connection path for DocuSign workflows through the managed catalog. Connections created during the beta period may still point to the earlier environment, so they may need to be recreated or re-authenticated before they use the production endpoints.

How to access: Open the managed MCP catalog, select DocuSign, and complete the OAuth connection flow. If you connected during beta and experience an issue, recreate or re-authenticate the connection.

Docusign MCP

Make streamed chat responses feel smoother

Chat responses now use a subtle fade-in animation as new text streams into the conversation. The change keeps the existing generation indicator while making the response feel less abrupt as it appears. It does not change the answer content, model behavior, or response timing; it is a presentation improvement intended to make active generation easier to follow and the overall chat experience more polished.

How to access: No action is required. The animation appears automatically while new Assistant text streams into a chat.

Assistant

Give OAuth clients authorized access to Skills APIs

Dynamically registered OAuth clients can now request the Skills scope when they need authorized access to Glean’s Skills APIs. This provides a more precise permission boundary for integrations that discover or use skills, without requiring broader access than the client needs. Existing clients are unaffected unless they need Skills API access; those clients should update their registration request and consent configuration to include the new scope.

How to access: Update the dynamic OAuth client registration to request the Skills scope, then complete the normal authorization flow.

Skills API

Resolve skill access more efficiently

Skill access checks now use an optimized permission filter by default. The change improves how Glean resolves which skills are available to a user while preserving the intended access rules. Users and administrators should see the same permission outcomes, with a more efficient path used behind the scenes when Glean evaluates accessible skills.

How to access: No action is required. Skill availability continues to follow your existing permissions and sharing settings.

Skills

Match exported LLM token counts to billing

Exported LLM event data now reports cache-adjusted input-token counts, matching the values used for billing and Agent event exports. This prevents the raw and cache-related token buckets from overlapping and making manual cost calculations appear higher than the billed amount. The change does not alter the underlying cost calculation; it makes the exported data reflect the same adjusted input count used by pricing.

How to access: No action is required. Use the updated input-token count in exported LLM event data when performing manual usage or cost analysis.

LLM Usage

Fixes

Reduce false positives when reviewing pasted or quoted text

AI Security guardrails now better distinguish a genuine prompt-injection attempt from text you are pasting, quoting, or reviewing. This reduces false positives for configuration files, security documentation, assistant responses, and ordinary business questions while preserving detection for concealed or agent-directed attacks. Findings also provide more useful investigation context by showing the triggering text, its source and location, and the potential impact on an agent.

Protect

Keep ServiceNow search text out of request URLs

ServiceNow search inputs are now sent in the request body rather than the URL. Search behavior and supported inputs remain unchanged, while search text and related parameters are less likely to be retained in load-balancer access logs. This reduces exposure of potentially sensitive business information and personal data during normal ServiceNow searches.

ServiceNow

Prevent GitLab access changes from removing valid memberships

GitLab identity updates now preserve crawl-scope information so memberships populated by a dedicated crawl are not incorrectly removed by a simple identity run. This addresses a race condition that could cause some users to lose access to GitLab documents and makes access updates more reliable when multiple identity crawls are active.

GitLab

Index Notion pages that previously disappeared from search

Some Notion pages could be silently omitted from the search index when an internal document-processing path encountered missing chunk metadata. The parser now handles that case safely, allowing affected pages to be indexed instead of being dropped. This restores discoverability for pages that were present in Notion but did not appear in Glean search.

Notion

Keep SharePoint crawling reliable with many custom columns

SharePoint site-page crawling now selects only the fields required by Glean when custom columns are not configured. This avoids requests that fail when a list contains a large number of unsupported custom columns, allowing the crawl to continue and making site-page content more reliable to index.

Sharepoint

Original source

AI & Model Updates

Get faster, more capable responses with Gemini 3.7 Flash

Gemini 3.7 Flash is now available as a model option in Glean Assistant and Agents. It is designed for high-volume, tool-using workflows where response speed matters, while providing stronger performance for well-scoped reasoning and coding tasks. The model is available across Glean Universal Model Key and Customer Key deployments covered by the supported release version. Gemini 3.7 Flash appears as a premium model, while earlier Flash models remain available in the model picker for teams that need them.

How to access: Open the model selector in Assistant or choose a model when configuring an agent. Administrators can exclude the model from Admin Console → Platform → Models if their organization does not want it available.

Assistant & Agents [ROAD-1647]

Improve Fast Mode responses with GPT-5.6 Luna

Fast Mode now uses GPT-5.6 Luna with low reasoning instead of the previous lightweight model. You should see improved answer quality while retaining the quick response experience that Fast Mode is designed to provide. No workflow changes are required: existing Fast Mode conversations and entry points continue to work, and the model change is applied automatically as the updated default becomes available.

How to access: Select Fast Mode in Assistant as usual. No administrator or end-user action is required.

Assistant

Give admins control over agent default models

Administrators can configure the default model set used by agent steps, giving teams more control over the models selected across agent types and supported modes. This helps organizations establish a consistent baseline for agent behavior instead of relying only on product defaults. The setting applies where the selected mode supports the configured model set; individual agent or step configuration can continue to determine behavior where those controls are available.

How to access: Administrators can use the deployment’s agent model configuration controls to set the default model set. No action is required from end users unless their administrator changes the organization’s defaults.

Agents

Enhancements

Open chat side panels without text reflow

Chat side panels, including artifact and source panels, now open and close with smoother transitions. The panel reaches its final width immediately while its contents animate in place, so the conversation no longer repeatedly resizes or rewraps as the panel appears. Closing a panel also returns you directly to the main conversation view without intermediate layout shifts. This makes it easier to keep your place while reviewing sources, working with artifacts, or moving between the conversation and supporting content on web and mobile.

How to access: Open an artifact or chat source panel from a conversation. The improved behavior is automatic; no settings change is required.

Chat

Control staged agent review request emails

Moderators can now opt out of staged agent review request emails through their collaboration email notification settings. This gives moderation teams more control over review-request traffic while preserving the messages needed to keep agents reviewed.

How to access: Update collaboration email preferences for moderation notifications in your notification settings. No action is needed if you want to keep receiving these messages.

Notifications

See agent risk posture more clearly in Agent Scan

The Agent Scan experience now gives administrators a clearer view of agent risk. The dashboard separates Critical and High risk counts, combines Medium and Low risk agents into a simpler summary, and exposes the counts needed for the risk overview. Filters are also easier to use: Creator is a compact searchable single-select control, Risk supports multiple selections, and policy status styling is consistent across the admin experience. Policy audiences now show names for individual people or groups and reveal the full recipient list on hover.

How to access: Open the admin Agent Guardrails page and use the Agent Scan dashboard, filters, and policy audience details. No end-user action is required.

Protect

Understand agent permissions before activation

Before you activate an agent, the permissions screen now explains what each tool can do and whether it may act without asking for approval. Tools are identified as read-only, able to run without approval, or requiring approval. MCP servers also show whether all, some, or none of their enabled write tools can run unattended. The display follows administrator approval policies, so a tool that an administrator requires to pause will be shown as requiring approval even when the agent’s own configuration requests otherwise.

How to access: Open an agent that uses tools or MCP servers and review the permissions screen before activating it. No configuration change is required.

Agents

Separate read and write tools for MCP servers

When you build or review an agent, each MCP server’s capabilities are now separated into Read tools and Write tools with individual counts. This makes it easier to see whether a server can only retrieve information or can also change data. The layout also makes the write-tool approval control easier to understand, and the control is hidden when a server has no enabled write tools. Selecting or removing a tool in one section does not change the selections in the other section.

How to access: Open an agent’s Capabilities tab and expand an MCP server. Review or adjust the Read tools and Write tools selections there.

Agents

Share meeting notes and imported summaries directly from the artifact

Artifact owners can now use the Share action directly from the header of meeting notes and imported meeting summaries, even when the original chat thread is no longer available. This gives owners a reliable way to share the artifact itself without needing to reopen or locate the conversation that created it. In cases where no linked chat thread exists, the Chat action remains hidden so the available actions accurately reflect what you can use.

How to access: Open a meeting note or imported meeting summary that you own, then select Share from the artifact header.

Artifacts

Retrieve schemas for Glean-native tools through the Tool Metadata API

Clients can now retrieve input schemas and descriptions for Glean-native tools through the Tool Metadata API. This helps integrations understand the inputs expected by native capabilities such as Meeting Lookup before invoking them. Existing action-pack and external MCP behavior remains unchanged, so current integrations do not need to change how they use those tools. The improvement is especially useful for clients that need to inspect tool definitions dynamically while building or running agent workflows.

How to access: Use the Tool Metadata API when your client needs the input schema or description for a Glean-native tool. No end-user action is required.

Agents

Restore full insights visibility for Insights Moderators

Insights Moderators can again view insights for all agents, including agents they do not own or edit. This restores the broader visibility needed by moderation and oversight teams to review agent activity across an organization rather than being limited to agents associated with their own accounts. Agent owners and regular users do not need to change their sharing settings for this access to work.

How to access: Sign in with an Insights Moderator role and open the agent insights experience. Access is controlled by your organization’s role assignment.

Insights

Keep MCP moderation focused on Glean-hosted servers

MCP Server Moderators are now limited to administering Glean-hosted MCP servers and viewing MCP Insights. Managing third-party MCP connections—including creating, updating, deleting, refreshing, or repairing third-party hosts and accessing their templates—continues to require the existing tool-administration permissions. This keeps moderation responsibilities aligned with the surfaces they are intended to govern while preserving established controls for external connections.

How to access: MCP Server Moderators can use the Glean-hosted MCP administration and MCP Insights surfaces. Ask an administrator for tool-administration permissions when third-party MCP management is required.

MCP

Find recent Outlook mail sooner

New or changed Outlook messages delivered through webhooks are now prioritized ahead of background full-refresh crawls in the mailbox thread queue. As a result, recent mail can become searchable sooner without interrupting other mailbox crawl operations. This is an automatic indexing improvement: it does not change how users search Outlook, and it does not require administrators to reconfigure the connector.

How to access: Search Outlook content in Glean as usual. No user or administrator action is required.

Outlook

Improve OneDrive and SharePoint crawl reliability

OneDrive and SharePoint crawls now use more efficient exact-key batch deletion when cleaning up delta results. This reduces the chance of slowdowns or stalls on large drives and helps keep connector processing predictable as content changes over time. The improvement is applied to the crawl process automatically and does not change the way users search or access content.

How to access: Continue using OneDrive and SharePoint connectors normally. No user or administrator action is required.

OneDrive & SharePoint

Capture user intent for MCP usage analysis

MCP tool calls now capture the user’s intent for usage logging and downstream analysis. This gives organizations better context for understanding why MCP tools are used, supporting more useful operational and adoption analysis. The change does not alter the tool’s result or require users to provide a new form field outside the MCP interaction. Intent capture is handled as part of the MCP tool-call experience and its associated usage logging.

How to access: No action is required. Intent information is captured automatically for supported MCP tool calls.

MCP

Fixes

Hosted Excel, Outlook, SharePoint, and Teams actions are more reliable

Hosted Composio actions for Excel, Outlook, SharePoint, and Teams are now more reliable. An infrastructure issue could previously cause intermittent failures when these actions were used in hosted workflows. Reliability protections have been improved so the supporting service is less likely to become unavailable during periods of platform pressure. Existing workflows continue to work without changes, and no action is required from users or administrators.

Actions

ServiceNow Create Request forms load correctly

ServiceNow Create Request no longer fails with “Failed to fetch action data” after you select a catalog when the action has no catalog restriction configured. The form now proceeds to the catalog-item step when no specific allowlist is set, while configured catalog restrictions continue to be enforced. This restores the expected request-creation flow without requiring administrators to add an unnecessary catalog restriction.

ServiceNow

Sign in to the Android app with Intune MAM policies

Android sign-in now works more reliably for organizations using Intune Mobile Application Management, including BYOD devices that are not enrolled in full device management. The flow handles both permissive and restrictive “Receive data from other apps” policies, uses Microsoft Edge when Intune requires a managed browser, and provides clearer guidance when Edge is missing or not recognized as managed. Users without Intune app protection are unaffected.

Learn more

Glean Mobile

Find identity-provider groups when sharing

Searching for identity-provider groups, such as Azure AD or Microsoft 365 groups, is now more reliable when sharing an agent, chat, or other item. You can search using text from any part of a group name, and matching groups continue to appear consistently in tenants with many groups. Previously, a group could be omitted unless you typed the full name or started with its exact prefix. The sharing flow and group selection behavior remain unchanged once you find the group.

Sharing

Export and import agents without tool-creation permissions

Agent export and import now work for users who do not have permission to create tools when the agent uses datasource actions. Previously, the export could fail because an action could not be resolved to a portable name. Actions are now represented with stable names rather than environment-specific identifiers, allowing the workflow to be downloaded and reused correctly without granting additional tool-creation permissions.

Agents

Original source

New cadence

We’re moving to twice-weekly release notes to match our release cadence, so you’ll know what shipped sooner.

✨ Major Launches

Find and reuse your past Assistant chats without leaving the conversation

You can now ask Glean to find and pick up your earlier Assistant conversations directly from a new chat, so you can continue long-running work without hunting through your history. Only your own conversations that are stored in Chat History are surfaced, and existing retention and privacy controls still apply.

How to access: In a new Assistant conversation, just ask Glean to find a previous chat (for example, reference what you were working on). Glean surfaces matching conversations from your own Chat History. No setup is required.

Assistant

Discover useful next steps directly from Glean Home

Glean Home can now surface personalized Cowork suggestions based on your recent work. Each card recommends a concrete next step, such as preparing for a meeting, summarizing a call, drafting a follow-up, or updating a document, and opens the relevant Assistant workflow with context already provided. This helps you discover valuable Glean capabilities without knowing the exact prompt or navigating through multiple product areas. Suggestions are designed around practical work journeys and include source-backed context so you can understand why a recommendation is relevant.

How to access: Open Glean Home and select a suggested card when one appears. No admin setup is required for supported Glean Key deployments.

Glean Home [ROAD-1444]

Understand usage by department and support internal chargeback

Billing administrators can now see how Glean usage is distributed across departments. The new department view helps you compare consumption, identify teams that are under-adopting or driving the most usage, and export the data for budgeting, chargeback, showback, and internal reporting. Department attribution follows the department metadata available through your identity provider or organization chart, so the view reflects the structure your organization already maintains. This gives finance and platform teams a clearer organizational lens on Glean adoption and consumption.

How to access: Open Admin Console → Usage and select By departments. Use the department table to compare usage or download the data as a CSV.

Learn more

Usage and Billing [ROAD-1340]

Set monthly usage limits for individual departments

Billing administrators can now set a monthly usage limit for each department. This lets you align Glean usage with the way your organization manages budgets, give different teams different levels of headroom, and choose between alert-only monitoring and blocking additional billable usage after a limit is reached. Department limits apply to each member of the department rather than creating a shared pool, and individual user overrides remain available for people who need more capacity. Limits reset at the start of each calendar month.

How to access: Open Admin Console → Usage → By departments, open the department’s actions menu, select Manage usage limit, enter the monthly amount, and save. Confirm that department metadata is mapped in your people data.

Learn more

Usage and Billing

Delegate work to dynamic sub-agents with Task Tool

Autonomous Agents can now delegate work through the Task Tool by default in supported workflows. This gives an agent a consistent way to create and route work to dynamic sub-agents, support follow-up steps, and use model routing suited to the task. You can use the capability to break a larger workflow into focused pieces while preserving the agent’s permissions and error-handling behavior. The change also removes the need for the previous external experiment path for supported Task Tool workflows.

How to access: Create or open a supported autonomous agent and configure a step that delegates work through the Task Tool. The capability is enabled automatically for supported workflows.

Autonomous Agents [ROAD-1622]

Let agents act as themselves with governed service credentials

Agent Identity lets an agent use its own scoped service credentials instead of borrowing the identity of the person who invoked it. Actions can therefore appear under the agent’s own account in connected systems, while Glean records the triggering user or schedule separately for auditability. Admins can limit the credential to the tools and data the agent needs, reducing permission sprawl and preventing the agent from inheriting unintended user access. Scheduled and background agents can also continue running without depending on a person’s OAuth session.

How to access: An admin creates and scopes a service credential in the target system, registers it in Admin Console → Agent identity, and controls its audience. A builder can then attach the credential to an autonomous agent.

Learn more

Agent Identity [ROAD-1542]

Query Databricks Genie from Glean Assistant

Assistant can now route natural-language data questions to Databricks Genie spaces, allowing business users to ask questions about governed Databricks data without leaving Glean. Glean uses indexed Genie space metadata, such as titles, descriptions, sample questions, and table information, to select the best matching space. Direct Databricks SQL remains available as an explicit fallback when requested or when no suitable Genie space is found. Results are returned in Assistant while Databricks permissions continue to control what each user can access.

How to access: Your admin must configure the Databricks connector and tools, verify that Genie spaces are indexed, and enable the Databricks tools for Chat under Admin Console → Platform → Tools. Then ask Assistant a question about your Databricks data.

Learn more

Databricks in Assistant

Personalize Glean Home with optional interactive pets

Glean Home can display an optional interactive pet that stays on the page, provides lightweight chat and meeting alerts, and lets you run chats in the background while you continue working. You can hide or snooze the pet, switch between pets, and choose which notification types it can show. Some pets unlock as you use Glean Home, turning common actions such as searching, creating an artifact, or visiting People into optional discovery moments. The experience is controlled by your organization’s User Delight setting and may not be enabled everywhere.

How to access: When User Delight is enabled by your admin, open Glean Home and use the pet menu to choose, hide, snooze, or configure the pet and its notifications.

Glean Home [ROAD-1601]

Catch up on the last two minutes of a live meeting in one click

When you join a live meeting late or lose track of the discussion, Meeting Notes can now summarize the most recent part of the transcript for you. After the transcript has more than two minutes of content, select Catch me up above the composer to get a concise recap of what was just discussed. This helps you rejoin the conversation without asking others to repeat themselves and keeps you focused on the meeting instead of on note-taking. The summary is generated from the live transcript already available in the meeting.

How to access: Open a live meeting transcription in Glean desktop. After more than two minutes of transcript are available, select Catch me up above the composer. Meeting Notes access is controlled by your admin under Admin Console → Assistant → Meeting Notes.

Learn more

Meeting Notes [ROAD-769]

🤖 AI & Model Updates

A faster default model for Adaptive Mode, Fast Mode, and Search

Adaptive Mode, Fast Mode, and Search in Chat now use GPT-5.4-mini as their default model, delivering faster, more efficient responses in these modes.

How to access: No action needed — these modes use the new default model automatically.

Assistant

Set the default model for workflow agents

Admins can now configure the default model set that powers workflow agents, giving teams more control over which model is used for workflow-agent steps.

How to access: In the Admin Console, set the default model set for workflow agents in your model configuration.

Agents

Choose GPT-5.6 models across Assistant and Agents

GPT-5.6 Sol, GPT-5.6 Terra, and GPT-5.6 Luna are now available as premium models across supported Assistant and Agent surfaces. The model hub gives admins control over which models are enabled, while users can choose from the models made available to them when model selection is supported. Luna is initially focused on eligible agent workflows, while Sol and Terra are available in supported model-choice surfaces. Premium models may affect usage-based consumption, so administrators can manage availability according to their organization’s needs and billing policy.

How to access: In Admin Console → Platform → LLMs, enable the GPT-5.6 models in the Model Hub. Users can then select supported models from the Assistant model picker or Agent model settings.

Learn more

Models

Configure AI action models by deployment and workflow

Admins can now configure the model used for AI-powered actions with clearer deployment-aware controls. The configuration supports choosing an eligible model, setting visibility for the people who can use the action, and keeping the action aligned with the model availability of the deployment. This helps platform owners balance response quality, cost, and access while giving users a predictable experience when they invoke actions such as summarization, drafting, or other AI-assisted workflows.

How to access: Open the relevant action in Admin Console → Platform → Actions, select its configuration, and review the available model and visibility settings. The choices shown depend on your deployment and enabled models.

AI Actions

Use Claude 4.1 in Assistant

Claude 4.1 is now available for supported Assistant experiences, giving users another model option for tasks that benefit from Anthropic’s latest available capabilities. Administrators retain control over whether the model is enabled and which users or workflows can access it. The model appears alongside other configured models rather than changing every user’s existing selection automatically, so teams can evaluate it within their current model governance and usage-management practices.

How to access: An admin must enable Claude 4.1 in Admin Console → Platform → LLMs. Once enabled for your deployment, select it from the Assistant model picker where model choice is available.

Learn more

Assistant Models

Select models separately for individual applications

Model selection can now be configured at the application level instead of relying only on one broad deployment setting. This gives administrators more control over which applications can use particular models and helps align model access with the needs, risk profile, and cost expectations of each workflow. Users see only the models made available to the application and audience they are using, so the experience remains governed without requiring every application to expose the full model catalog.

How to access: Open Admin Console → Platform → LLMs or the relevant application’s model configuration and review the enabled models and visibility settings. Exact options depend on your deployment.

Learn more

Model Administration

New Glean Key autonomous agents start with GPT-5.6 Luna

New autonomous agents on Glean Key now use GPT-5.6 Luna as their default model, giving new agents a more capable starting point without requiring you to choose a model during setup. Existing autonomous agents keep their current model settings, so this change does not silently alter agents already in use. Workflow-agent defaults are also unchanged. For administrators, the Glean Key model controls now make the transition clearer: Luna can be enabled while it is off, and GPT-5.4 can be disabled after Luna is enabled. Legacy large and small workflow defaults are no longer presented as default choices for Glean Key.

How to access: Create a new autonomous agent to use the new default automatically. To review Glean Key model settings, open Admin Console → Models and select the Glean Key model configuration.

Learn more

Agents and Model Administration

⚠️ Critical Updates

Knowledge Profile searches now surface only company-wide pinned results

For searches performed with a Knowledge Profile, private and department-scoped pinned results are no longer shown as suggested results; only company-wide pins appear. This keeps pinned suggestions aligned with content that is broadly visible across your organization.

How to access: No action needed — this applies automatically. If you previously relied on private or department-scoped pins appearing under a Knowledge Profile, note that only company-wide pins will now surface.

Search

Restrict public links to people who already have access

Public-link settings now make it easier to prevent accidental broad sharing. Administrators can choose whether users may create public links and can restrict link creation to specific groups. When restricted sharing is selected, only people who already have access to the underlying content can open the link. This gives organizations a clearer control point for balancing collaboration with information protection and helps prevent a link from becoming an unintended access path to a chat, artifact, or other user-generated content.

How to access: Admins can review public-link controls in the organization’s sharing and access settings. End users will see the permitted sharing options when they open a chat or artifact’s share dialog.

Sharing and Permissions

Connect MCP hosts with a simpler OAuth consent experience

Connecting a third-party MCP host to Glean now uses a single, clearer user-facing permission instead of exposing a long technical list of OAuth scopes. The consent screen explains that MCP access operates within your existing permissions and the settings approved by your admin, while Glean narrows the underlying scopes to the resources the host needs. This makes the first connection easier to understand without removing the admin and per-tool controls that govern what the MCP host can access.

How to access: Admins who already use the Glean OAuth Authorization Server do not need to change anything. To enable it for a new deployment, open Admin Console → Settings → Third-party access (OAuth) and enable Glean OAuth Server. Users then connect their MCP host and approve the simplified consent screen.

Learn more

Glean MCP OAuth

Plan for the retirement of Claude Opus 4.1

Claude Opus 4.1 is being retired from Glean model availability. Administrators should review agents, actions, and other workflows that explicitly select this model and move them to a supported replacement before the retirement date. Existing workflows may continue to run during the transition window, but they will need a supported model after the model is removed. Reviewing model usage now helps you avoid unexpected changes to production agents and gives you time to test a replacement under your organization’s access and usage policies.

How to access: Open Admin Console → Platform → LLMs and review configurations that use Claude Opus 4.1. Choose a supported replacement and save the updated configuration before the retirement deadline shown in your deployment.

Learn more

Model Administration

Move workflows off GPT-5.1 before it is retired

GPT-5.1 is being removed from supported model choices. If an agent, action, or application explicitly depends on GPT-5.1, update that configuration to a supported model before the retirement date. The change is intended to reduce reliance on an older model version while preserving a clear migration path through the Model Hub. Administrators should also review any model-specific prompts, output expectations, or cost assumptions before switching production workflows to a replacement.

How to access: Open Admin Console → Platform → LLMs, search for GPT-5.1 in your enabled-model and workflow configurations, and select a supported replacement before the retirement deadline shown for your deployment.

Learn more

Model Administration

Control application and tool access with clearer admin settings

Administrators now have more consistent controls for managing who can use connected applications, tools, and agent capabilities. Access settings can be applied to users or groups, and the admin experience includes clearer guidance about where a setting takes effect and how it affects end-user visibility. These controls help teams roll out integrations safely, limit sensitive actions to the right audiences, and troubleshoot access without requiring users to guess whether a feature is unavailable or simply restricted by policy.

How to access: Open the relevant application, tool, or agent configuration in the Admin Console and review its Visibility, Access, or Configuration settings. Use the available user or group controls to define the intended audience.

Admin Access Controls

Admins can control who receives audio artifacts during rollout

Glean Key administrators now have explicit controls for audio artifacts. You can let Glean manage the rollout, enable audio artifacts for everyone, limit them to admins, or turn them off. These controls help you introduce podcast-style audio artifacts at a pace that matches your organization’s privacy, compliance, and adoption requirements. The setting applies to new audio generation; an audio artifact that has already finished generating remains playable even if the setting later changes. If access is revoked while generation is in progress, the generation is stopped cleanly rather than remaining stuck.

How to access: Open Admin Console → Glean Assistant → Settings → Audio artifacts on a Glean Key deployment, choose the audience setting, and save. Customer Key deployments do not show this setting.

Learn more

Audio Artifacts

Delegate MCP administration without granting full admin access

The MCP Server Moderator role is now enabled by default in deployments that do not provide an explicit override. Administrators can use this role to delegate Glean MCP server management and MCP Insights access without granting broader administrator permissions. The role remains governed by the deployment-level feature setting, so organizations that need a stricter permission model can disable it. This change makes it easier to separate day-to-day MCP administration from organization-wide administrative authority while keeping access controlled through existing role management.

How to access: Assign the MCP Server Moderator role through your deployment’s Admin Console role and permissions controls. If your deployment explicitly disables the role, it will remain unavailable.

MCP Server Administration

Departmental moderators now see the publish action they can actually use

Departmental agent moderators now receive an action that matches their publishing scope. When an agent was created outside the departments a moderator oversees, the builder previously displayed Publish, even though the publish request would be rejected. The action now appears as Request to publish, making the next step clear and avoiding a failed publish attempt. Moderators can still publish agents created within their departments, and organization-wide agent admins are unaffected. This change makes agent governance more predictable for teams that use department-scoped moderation.

How to access: Open an agent in the builder as a departmental moderator. The available action is shown in the agent’s publishing controls and reflects the creator’s department and your assigned scope.

Agent Permissions

Notifications work without customer-specific enablement

Notifications delivered through Glean’s Notify platform now work by default, removing the need for customer-specific enablement before supported notification workflows can operate. This reduces setup friction for organizations using notification delivery and makes behavior more consistent across deployments. There is no change required for customers who already use the platform. Existing notification configuration and delivery paths continue to apply; the improvement is that the underlying delivery capability is available by default instead of requiring an additional customer-level activation step.

How to access: No action is required. Use supported notification workflows as usual; delivery is available automatically through the Notify platform.

Notifications

Tableau connections work with older supported REST API versions

The Tableau connector now starts with REST API version 3.23 instead of 3.27. This improves compatibility for Tableau Server and Tableau Cloud environments whose maximum supported API version is below 3.27, reducing setup and crawl failures caused by a version mismatch. The change is backward-compatible for environments that support newer Tableau APIs, and it does not require you to change your existing Tableau configuration. Glean continues to use the connector’s supported setup and authentication flow while requesting an API version that works across a broader range of Tableau deployments.

How to access: No action is required. Use the Tableau connector setup and crawl workflows normally. Existing configurations continue to use the compatible default.

Tableau Connector

🌅 Deprecations & Sunsets

Gemini 3 Pro has been removed

Gemini 3 Pro has been removed following its March 25, 2026 deprecation date and is no longer available for selection in Assistant or Agents.

How to access: If your organization used Gemini 3 Pro, switch any affected Assistant or agent configurations to another available model in the Admin Console.

Models

🎨 Enhancements

Consistent meeting titles across chat, transcripts, Notes, and Summaries

Meeting titles now stay in sync across chat, transcripts, Notes, and Summaries after you rename a meeting or generate a Summary, so you see the same title everywhere.

How to access: No action needed — titles stay consistent automatically.

Meetings

Faster data refresh in Canvas artifacts

Refreshing data in a Canvas artifact is now faster and skips an unnecessary agent interaction when the artifact supports deterministic refresh.

How to access: No action needed — refresh is faster automatically for supported artifacts.

Artifacts

Spot chats that ran into an error from the left navigation

Conversations that hit an error before finishing now show an error indicator in the left navigation, making it easier to find chats that may need to be retried or reviewed.

How to access: No action needed — the indicator appears automatically next to affected chats.

Assistant

See read and write tool counts for external MCP servers at a glance

When choosing external MCP tools in the Admin Console, each server now shows how many read and write tools it provides before you expand it, and servers that provide no tools are no longer listed.

How to access: In the Admin Console, open external MCP tool selection to see per-server read and write tool counts.

MCP

Choose whether to notify teammates when sharing an agent

When you share an agent with new teammates, you can now decide whether to notify them. A "Notify teammates" checkbox appears whenever you add teammates, so you can alert them to their new access or share quietly.

How to access: When sharing an agent, use the "Notify teammates" checkbox to control whether new teammates receive a notification.

Agents

LumApps connector now captures deleted and archived content

The LumApps connector now supports webhooks for deleted and archived content, keeping search results more accurate as content changes in LumApps.

How to access: Available automatically on the LumApps connector; no additional setup is required.

Connectors

Clearer GitLab Cloud connector setup guidance

GitLab Cloud setup now guides admins to use either a Group Access Token or a Service Account token scoped to a single top-level group, with links to official GitLab documentation and clearer notes on when webhooks are created automatically versus configured manually.

How to access: In the Admin Console, follow the updated GitLab Cloud connector setup flow.

Connectors

Export historical user spend, including zero-usage and deleted users

Billing moderators can now export historical user spend, including users with zero usage and deleted users, for more complete cost reporting.

How to access: In the Admin Console billing area, billing moderators can export historical user spend.

Billing

Per-app and per-user spend limits with the AI gateway

When the AI gateway is enabled, monthly spend limits are now enforced per connected app and per user within each app, so a budget set on one app is evaluated independently of others. Deployments that do not use the AI gateway are unaffected and continue to enforce workspace-wide, per-user, and per-agent limits.

How to access: With the AI gateway enabled, set per-app and per-user monthly spend limits in the Admin Console.

Billing

Splunk MCP server is now connection-verified with a setup guide

The Splunk MCP server template now appears as "Connection verified" in the MCP catalog and ships with step-by-step instructions for connecting Splunk using a dedicated service account, a least-privilege role, and an encrypted MCP token.

How to access: In the MCP catalog, select the Splunk template and use "Show setup instructions" to complete service-account setup.

MCP

Support for the latest Model Context Protocol revision

Glean's MCP servers now support the 2026-07-28 revision of the Model Context Protocol specification. Clients that speak the newer revision negotiate it automatically, and clients on earlier revisions continue to work unchanged.

How to access: No action needed — supported clients negotiate the new revision automatically.

MCP

More resilient Slack tools under heavy concurrent use

Slack tools used by Assistant, voice, and agents are now more resilient when many requests run at once. Glean no longer opens a new Slack connection for every skill lookup and tool dispatch, so Slack per-account connection rate limits no longer reject requests mid-turn and cause an assistant or scheduled agent to abandon its remaining steps.

How to access: No action needed — this reliability improvement applies automatically.

Slack

Zendesk Extension Tools action pack is now available to set up

Resolved an issue where the Zendesk Extension Tools action pack did not appear in the list of supported action packs and therefore could not be configured. It is now available to set up.

How to access: In the Admin Console under Actions, add the Zendesk Extension Tools action pack.

Actions

Filter Glean Home suggestions by assistant capability

Glean Home suggestions can now be filtered by the assistant capabilities they use. This gives admins and product teams a more focused way to evaluate or manage suggestion experiences when a deployment exposes only selected workflows. The filter separates suggestions based on the underlying capability rather than requiring you to inspect each card individually, making it easier to understand what types of actions are being promoted and to keep the Home experience aligned with the workflows available to your organization.

How to access: Open the Glean Home suggestion management or configuration view and use the assistant-capability filter when reviewing available suggestions. The filter appears automatically where suggestion controls are enabled.

Glean Home

Review and export expense data from Glean Expenses

Glean Expenses now supports a clearer review workflow for expense information, including improved access to the relevant expense records and exportable data. This helps finance and operations teams inspect expense activity in one place and move the information into their existing reporting processes when needed. The update focuses on making expense data easier to retrieve and use without changing the underlying expense source or approval process.

How to access: Open Glean Expenses from the application area available to your organization, review the expense records, and use the available export action when you need a report.

Glean Expenses

Upload more text-based file formats safely

File uploads now support more than 50 additional text-based formats, including TSV, TOML, RST, and Markdown. Glean continues to block unsafe or unsupported files such as executables, archives, scripts, and audio or video formats where applicable. This makes it easier to bring structured text and configuration files into Assistant for analysis, summarization, and content generation without weakening the existing security checks that validate file types before processing.

How to access: In Assistant, choose the file-upload control and select a supported text file. If your organization has file upload disabled, an admin can enable it from the Glean section of workspace Settings.

Learn more

File Upload

Keep working with AI in full-screen artifacts

Full-screen artifacts now include a floating composer so you can ask for edits, answer clarifying questions, and continue iterating without returning to the side-by-side chat layout. The composer opens by default the first time you view an artifact in full screen. If you prefer an uncluttered view, minimize it; that choice stays in effect for the current artifact editing session. This is especially useful for dashboards, interactive pages, slide decks, and MCP apps where the full-screen view is the main working surface.

How to access: Open an artifact and select full-screen view. Use the floating composer to ask for changes or questions, or minimize it when you want to focus on the artifact.

Learn more

Artifacts and Canvas

Read Assistant more comfortably with updated typography

Assistant now uses Inter typography with updated spacing and visual hierarchy across the core chat experience. Responses, controls, and structured content have a more consistent appearance across operating systems, making dense workflows easier to scan and giving the product a more predictable visual rhythm. The update does not change how you start chats, use tools, or access existing content; it improves the readability and polish of the surfaces you already use.

How to access: No action is required. The updated typography and spacing appear automatically in Assistant.

Assistant

Open Assistant with the new application URL

Assistant now has a dedicated application URL, making it easier to bookmark, link to, and open the Assistant experience directly. The new URL supports a clearer entry point for users who want to move straight into chat rather than starting from a general Glean surface. Existing navigation continues to work, so teams can adopt the direct URL gradually without changing links or workflows immediately.

How to access: Open the Assistant application from your existing Glean navigation or use the direct Assistant URL provided for your deployment.

Assistant

Use more skills and configure their visibility

Skills now support additional setup and access controls so organizations can make reusable agent capabilities available to the right audiences. Admins and builders can configure skills as part of their agent workflows, while visibility settings help prevent a skill from appearing to users who should not use it. This supports more consistent reuse of approved instructions and capabilities across agents without requiring each builder to recreate the same behavior.

How to access: Open the Skills area in Glean or the relevant agent builder, then review the skill’s setup and access controls. Your admin may need to enable or grant access to the skill.

Skills

Show more connected sources and actions in the Assistant app

The Assistant app now exposes additional connected sources and actions from the application experience, making it easier to discover what Glean can use to answer questions or complete work. The expanded surface helps users find supported integrations without memorizing connector names or navigating through separate configuration pages. Availability still depends on the connectors and actions enabled for your organization, so users see a governed set of options aligned with their deployment.

How to access: Open the Assistant app and use its sources or actions controls to review what is available. If an option is missing, ask an admin to verify connector and action visibility settings.

Assistant App

Export and review uploaded files with clearer format support

The file-upload experience now better communicates which text-based formats can be selected and processed. This complements the expanded format support by reducing confusion when a valid file does not use one of the most common extensions. Glean validates files after selection and continues to apply server-side security checks, so the broader format support improves compatibility without treating every file type as acceptable. You can upload supported files to analyze them, ask questions, or create content from their contents.

How to access: In Assistant, select the upload control and choose a supported file. If a file is rejected, check its format against the supported file types in the public file-upload guidance.

Learn more

File Upload

See generated image batches more naturally on native mobile

When Glean generates several images in native mobile chat, the preview now uses one large hero image with supporting thumbnails instead of desktop-style artifact framing. The whole preview is a single accessible tap target, so you can open the full image canvas without hunting for a small control. The layout is designed for mobile screens and keeps the available images visible at a glance. Desktop and mobile web previews are unchanged, so this improvement is focused on making generated image results easier to scan and open in the native mobile experience.

How to access: In the Glean mobile app, generate or open a chat response containing multiple images. Tap the hero image or thumbnail area to open the full image canvas.

Mobile Chat

Find artifact types faster with clearer filter names and icons

Search filters now use friendlier names and an icon that matches each artifact type. In artifact-focused searches, documents, interactive artifacts, meeting notes, images, and other supported types are easier to distinguish than when every row used the same generic artifact icon. The With artifact filter also uses clearer wording in Assistant search. These changes reduce the time needed to understand what a filter represents and make it easier to narrow results when you are looking for a specific kind of artifact.

How to access: Open Search, optionally scope to Assistant or Artifacts, and open the With artifact or Type filter. The updated labels and icons appear in the filter list automatically.

Search and Artifacts

Review all agent versions in one timeline

The agent builder’s version picker now presents drafts, saved versions, staged changes, and published versions in one time-ordered timeline instead of splitting them between Drafts and Published tabs. This gives you a single view of an agent’s history and makes it easier to understand which version is current, which changes are ready to publish, and what was saved previously. Existing version actions remain available, including selecting a version and managing staged or saved versions where those actions apply.

How to access: Open an agent in the builder and open the version picker. Review the timeline from the current version through earlier drafts, saved versions, and published checkpoints.

Agent Builder

Search, sort, and evaluate agents more easily when configuring an MCP server

Admins configuring a Glean MCP server can now use a more capable agent picker. Search and familiar filters help you find the right agents, sorting and usage metadata provide more context, and descriptions are available without leaving the picker. Agents that cannot be selected, including disabled human-in-the-loop agents, remain visible with an explanation rather than disappearing and leaving you unsure why they are unavailable. The staged selection model remains in place, so your changes are applied when you save the MCP server configuration.

How to access: Open Admin Console → Glean MCP servers, edit an MCP server, and open its Agents section. Use the search, filters, sorting controls, and agent details in the picker before selecting Save.

Glean MCP Server

Review every configured GitHub extension in one place

The GitHub connector setup page now shows all configured file extensions used for indexing instead of limiting the visible list to a small fixed number. When many extensions are configured, they appear in a scrollable area so you can review the full configuration without losing access to the search and add controls. This makes it easier to verify that the connector covers the file types your engineering and documentation teams rely on and reduces the risk of overlooking an extension that was configured earlier.

How to access: Open the GitHub connector’s setup page in the Admin Console and review the configured file extensions. Scroll within the extension list to see entries beyond the initially visible rows.

GitHub Connector

Usage tables now label model spend by the selected period

The Models tables in the Admin Console now use the same period-aware labels as the users and departments tables. For the current month, the column is labeled MTD usage; for a previous month or all-time view, it is labeled Usage. The same wording is used in relevant application breakdowns and CSV exports. This makes it easier to interpret the numbers you are reviewing and avoids confusing a month-to-date value with a historical or all-time total.

How to access: Open Admin Console → Usage → By models and choose the current month, a previous month, or All time. The table and CSV export header update to match the selected period.

Usage and Billing

Open directory details without leaving AI Security Insights

The AI Security Insights user list now supports directory person cards. When you need more context about a high-risk user, you can hover over the user in the list and view the available directory details without navigating away from the insights dashboard. The existing user, department, pagination, and risk information remain in place, so the person card adds context without disrupting the review workflow.

How to access: Open /admin/agent-guardrails/insights and hover over a user in the user issues panel to open their directory person card.

AI Security Insights

MCP server lists now count inherited managed tools correctly

MCP server lists now include tools inherited from Glean-managed toolsets when showing the enabled tool count. Previously, a server could show zero tools in the list even though its detail page contained inherited tools. The count now reflects the union of enabled built-in tools and available managed-toolset members without double-counting overlaps or including unavailable tools. This gives admins a more accurate at-a-glance view when comparing servers and deciding which configuration to open.

How to access: Open the MCP server list in the Admin Console. The corrected tool count appears automatically for servers that use Glean-managed toolsets.

MCP Server Administration

Sharing language now makes restricted access explicit

The restricted-access option in sharing dialogs now says Restricted to only people with access. The wording clarifies that choosing this option does not grant access to new people; it limits access to people who already have it. Sharing behavior and the dialog layout are unchanged. The clearer label helps you choose the right sharing scope, especially when you are sharing a chat or artifact with a group and need to understand whether recipients must already be permitted to view it.

How to access: Open a chat or artifact sharing dialog and select the restricted-access option. The updated explanation appears in the sharing controls.

Sharing and Permissions

Assistant Replies preferences stay with each chat

Your Assistant Replies preference is now saved separately for each chat. If you turn Assistant Replies off in one conversation, leave it, and reopen it later, that chat remembers your choice. A different chat can keep a different setting, so changing the preference in one conversation does not change it elsewhere. The preference is stored locally in the web experience and does not modify the backend chat data, preserving the existing chat history and collaboration behavior.

How to access: Open any chat, change the Assistant Replies preference, and return to the conversation later. The setting is restored for that chat automatically.

Assistant Chat

Connect Zendesk MCP with service-account credentials

Admins can now configure a Zendesk MCP server using a confidential OAuth client’s service credentials instead of relying on a user’s Zendesk connection. Enter the Zendesk subdomain and the client credentials in the service-account template; Glean exchanges them for short-lived access tokens and exposes the existing Zendesk read tools to agents that use the server. This supports service-identity workflows while keeping the existing per-user Zendesk OAuth path available for customers who need it.

How to access: In the Admin Console, add the Zendesk MCP (Service Account) template, enter the Zendesk subdomain, and provide the confidential OAuth client credentials in the credential field. The service-account template may need to be enabled for your deployment.

Zendesk MCP

Customer log streams include LLM response latency metrics

Customer event streams now include per-call time-to-first-token and total latency for LLM calls. Time-to-first-token measures how long it takes before the model begins responding, while total latency captures the full duration of the call. These fields give administrators and platform teams more context when monitoring AI responsiveness, investigating slow experiences, or comparing performance across usage patterns. The change adds observability to customer-visible LLM call events without requiring application changes or changes to the way users submit Assistant or agent requests.

How to access: No action is required. Review LLM call events in your existing customer log stream; the latency fields are included automatically for new events.

Customer Event Logs

🐛 Fixes

Reliable indexing of OneDrive and SharePoint updates

Fixed a rare crawling issue in OneDrive and SharePoint where a failure between fetching an update and storing it could result in a permanently missed update. Updates are now stored before the crawl position advances, so changes are no longer lost.

How to access: No action needed — the fix applies automatically.

Connectors

OneDrive documents that previously failed to index are now processed correctly

Fixed an issue that prevented some OneDrive documents from being indexed. OneDrive documents are now processed correctly, with SharePoint handling unchanged.

How to access: No action needed — the fix applies automatically.

Connectors

Glean Chat recovers from errors on follow-up turns

Fixed an issue where Glean Chat could fail with a "Something went wrong" error on follow-up turns when the underlying AI provider could not decrypt a prior reasoning context. Glean now clears the invalid context and recovers the conversation turn.

How to access: No action needed — the fix applies automatically.

Assistant

Zoom recordings open directly from search results

Zoom meeting recording search results now link directly to the recording's share URL with the play passcode included, so the recording opens without a separate passcode prompt. Links to the older recording details page continue to resolve to the same result.

How to access: No action needed — recording links open directly.

Zoom

Slack direct messages reliably appear in federated search

Fixed an issue where Slack direct messages found through federated search could be missing from results on deployments that index Slack but exclude private messages from native search.

How to access: No action needed — the fix applies automatically.

Slack

Prevent connector reindexing from leaving stale or broken results

Connector reindexing could leave affected customer content in an inconsistent state after source changes, including results that pointed to missing pages or returned 404 errors. The reindexing flow now handles those changes more safely so refreshed content is available from the connector without leaving stale references behind. This improves trust in search results after large updates, deletions, or connector maintenance and reduces the need for customers to retry indexing or investigate broken links manually.

Connectors and Search

Avoid request failures after a usage limit is reached

Some customers could receive HTTP 429 errors on every response after reaching a configured usage limit, even when the request should have returned a clear limit message or allowed a non-billable experience to continue. The usage-limit handling path now returns the correct response behavior instead of repeatedly surfacing a generic rate-limit failure. This makes limits easier to understand for end users and gives administrators a more predictable control mechanism when a user, agent, or organization reaches its configured threshold.

Usage Limits

Keep Deep Research jobs from running out of memory

Large or complex Deep Research jobs could consume too much memory and fail before producing results. The workflow now handles the research execution more efficiently so longer investigations are less likely to terminate because of an out-of-memory condition. This helps users continue using Deep Research for substantial questions while preserving the context and intermediate work needed to produce a useful response instead of forcing them to restart with a smaller request.

Deep Research

Keep AWS connector links working after deployment changes

Some AWS-hosted connector experiences could generate links that pointed to an unavailable endpoint, resulting in 404 errors when users opened a connector result or management path. The URL handling now uses the correct AWS deployment context, so connector links resolve to the expected destination. This restores normal navigation for affected AWS-hosted customers and reduces the need to repair links or retry connector actions manually.

AWS Connectors

Apply connector permissions consistently through hierarchy changes

Connector permissions could be applied incorrectly when access was inherited through parent and child connector relationships. The permission evaluation path now preserves the intended hierarchy so users receive the correct access to indexed content, including after connector configuration changes. This reduces the risk of users seeing content they should not access or losing access that an administrator intended to grant, and it makes connector governance more predictable for organizations with layered source configurations.

Connector Permissions

Long Deep Research chats are less likely to fail before answering

Deep Research sessions with very long histories could fail with an error instead of returning an answer. The route now handles large conversation histories without sending the entire history inline in the request, allowing the session to continue while preserving earlier context. This is especially helpful when you return to an extended research thread and need to build on prior findings rather than start over.

Deep Research

GitHub code search results now open the correct file

GitHub federated code search results could lead to 404 pages when the result URL used an invalid reference. Results now resolve through the repository’s default branch, so selecting a file opens the expected GitHub page instead of an error. This restores the basic workflow of searching code in Glean and jumping directly to the matching file for inspection.

GitHub Search

New Slack Real Time Search connections can complete authorization

New Slack Real Time Search connector setups could fail before OAuth began because the authorization URL was not generated. The setup flow now handles newly created instances correctly, allowing the authorization URL to be created and the OAuth process to start. Existing Slack Real Time Search instances continue to use their saved MCP scope settings.

Slack Real Time Search

Long-running Spaces chats can continue past large-history limits

Long-running Spaces conversations could fail when their history became too large for the request sent to the AI workflow. The conversation history is now read directly from stored chat events for this route, avoiding the request-size limit while preserving the context needed for follow-up turns. This helps you continue an established Spaces discussion instead of losing the thread when the conversation grows.

Spaces

Tools work correctly across multiple Microsoft 365 instances

When multiple Microsoft 365 instances were connected, tool selection could use the wrong identity mapping, causing tools to be missing or unavailable in some contexts. Tool selection now respects the identity mapping for additional Microsoft 365 instances, so the tools exposed to an agent match the configured connection. This improves reliability for organizations that separate Microsoft 365 environments or maintain more than one connected instance.

Microsoft 365 Tools

Original source

User Features

Model Selector in Builder Assistant

Builder Assistant now includes a model selector so agent builders can choose which large language model powers each compiler chat. The chat bar shows the current model, and every response clearly indicates which model was used, matching the Assistant experience. This gives admins more control over cost and quality when Builder Assistant usage is billed, while keeping the default "Auto" model for new sessions.

How to access: Administrators must enable for your organization. Builder Assistant with model selection is available to all customers who can access the Agent Builder and use Builder Assistant. Admins should ensure that any premium models they want builders to use are enabled in their model settings. No additional configuration is required beyond existing model and billing setup. This feature may be subject to usage-based pricing. Learn more in Glean's Help Center.

Learn more

Agents [ROAD-1566]

Call Third-Party Agents from Glean Agents via A2A

Glean agents can now call external third-party agents that support the A2A (Agent-to-Agent) protocol, so complex workflows can seamlessly span Glean and other agent platforms. Admins register external A2A agent servers in the Admin Console with OAuth credentials, and agent builders can add those external agents as sub-agents in Plan & Execute and Auto Mode workflows. This lets Glean agents delegate specialized tasks to domain-specific agents built on any A2A-compliant platform, while preserving per-user authentication, permissions, and governance across systems. This feature is available for all customers using Glean Agents and may be subject to usage-based pricing.

How to access: Administrators must enable for your organization. To enable this capability, a Glean admin must go to the Admin Console and register one or more external A2A agent servers, including their A2A agent card URL and OAuth client credentials, under Settings → Third-party agents. Admins should then configure which external agents are available to use in agent workflows via Settings → Assistant → Agent orchestrator. Once configured, agent builders can select and add these third-party agents as sub-agents in the agent builder; no additional setup is required for end users beyond any standard sign-in or consent flow enforced by the external platform. This feature may be subject to usage-based pricing. Learn more in Glean's Help Center.

Learn more

Agents [ROAD-1560]

Adaptive Reasoning [Customer key]

Adaptive reasoning dynamically decides how long to reason based on the user's query. This makes Glean Assistant feel faster for easy queries while preserving its quality for more difficult ones.

Learn more

Assistant [ROAD-1376]

Glean Assistant can now query BigQuery with natural language or SQL

Glean Assistant can now query BigQuery directly through BigQuery MCP, Google's official MCP server for BigQuery, 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 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.

Learn more

Connectors [ROAD-1165]

Claude Opus 5 in Assistant and Agents

Claude Opus 5, Anthropic's latest premium Opus-class model, is now available in Glean Assistant model choice and in Agents. It delivers Anthropic's highest-quality performance for coding, agentic workflows, and long-horizon enterprise tasks, giving teams a powerful new option when they need stronger reasoning than standard models can provide. Customers already using Opus-class models can adopt Opus 5 as their new Anthropic premium choice without changing how they work in Assistant or the agent builder. This feature may be subject to usage-based pricing; see your plan details for how premium models are billed.

How to access: Administrators must enable Claude Opus 5 for your organization before users and agent builders can select it. In the Admin Console, go to Platform → LLMs (Model Hub), make sure your Anthropic provider configuration is set up, and turn on the Claude Opus 5 model for Assistant and Agents. If you want to limit access, you can hide premium models from model pickers or restrict Claude Opus 5 to specific departments using the existing model governance controls. Once enabled, end users can pick Claude Opus 5 from the model picker in Assistant, and builders can select it in the agent builder for eligible agents and steps. This feature may be subject to usage-based pricing. Learn more in Glean's Help Center.

Learn more

Agents [ROAD-1592]

Gemini 3.6 Flash in Assistant and Agents

Gemini 3.6 Flash is now available in Glean Assistant model choice and in the Agents model hub. Gemini 3.6 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 3.6 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 3.6 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-1584]

A simpler setup flow for end users connecting to Glean MCP

We've refined the end-user setup experience so the default Glean MCP server is the clearest path for most users, while still preserving access to additional servers for advanced use cases. The updated flow also makes connected apps and authorization wording easier to understand, and gives users clearer setup options depending on the host.

How to access: End users can go to Settings → Third party apps and MCP and use the Glean MCP setup flow to pick a host and connect to Glean. The default server is highlighted as the recommended path, while additional servers remain available for advanced use cases.

Learn more

Assistant [PACT-331]

Assistant typography refresh and visual polish

Assistant now uses Inter typography with updated spacing and visual hierarchy for a consistent, easier-to-read experience across all devices.

Learn more

Assistant [ROAD-1526]

Glean Assistant on external AI platforms via A2A (Cross-platform)

Introduces a cross-platform A2A foundation that lets Glean Assistant run as a governed, first-class agent inside external AI platforms and agent runtimes, starting with Gemini and expanding to other ecosystems over time. The shared protocol and packaging model reuse Glean's enterprise context, permissions, and guardrails so users can ask Glean from their preferred AI surface without duplicating configuration or exposing extra data. Admins get a consistent way to authorize external platforms, manage which Glean capabilities are available where, and monitor usage across environments.

How to access: From the Glean admin console, enable external AI platform access/A2A and connect each supported platform using its service account or OAuth configuration. Use the A2A settings to choose which Glean agents (including Glean Assistant) can be invoked from each external platform and which user groups are allowed to use them. Refer to the Help Center setup guide for per-platform steps (for example, registering Glean Assistant in Gemini or other A2A-capable marketplaces). This feature may be subject to usage-based pricing. Learn more in Glean's Help Center.

Learn more

Connectors [ROAD-1463]

Simplified MCP OAuth consent and scope surface

Connecting third-party MCP hosts to Glean now uses a single, clear consent screen instead of a long list of technical OAuth scopes. The new experience groups MCP access into one user-facing permission, aligns that approval with each person's existing permissions and admin-approved settings, and narrows the underlying scopes to only the resources the host needs. Additional instrumentation on consent approvals and declines helps admins monitor rollout safety and refine their MCP strategy over time.

How to access: Admins already using the Glean OAuth Authorization Server for remote MCP servers do not need to take any action; users will automatically see the updated consent screen the next time they connect a host. To start using OAuth with remote MCP servers, open the Admin Console, go to Settings → Third-party access (OAuth), and enable the Glean OAuth Server. Then configure the MCP hosts you want to allow, and users can initiate the connection from their host and complete the simplified consent flow in their browser.

Learn more

Connectors [ROAD-1448]

NetSuite MCP support

NetSuite MCP support lets teams use Glean Assistant and agents to run live, permission-aware workflows against NetSuite on top of the existing indexed NetSuite connector. Users can ask Glean to look up customers, invoices, purchase orders, and other NetSuite records in natural language and pull the latest data into their conversations without switching tools. This capability is initially available to a small set of customers while we validate quality and coverage across common NetSuite use cases.

How to access: Admins can configure NetSuite MCP from the Glean Admin Console under Platform → Actions by adding the NetSuite MCP server as an action pack. During setup, provide the NetSuite MCP server URL and OAuth details so Glean can connect as an MCP host. Once the action pack is connected and its tools are enabled, eligible users can invoke NetSuite MCP actions from Glean Assistant and agents, with access governed by their NetSuite permissions.

Learn more

Connectors [ROAD-1336]

Get trusted Glean answers directly in Slack channels

Glean can now share trusted answers directly in Slack channels.

Glean can now post high-quality answers directly into Slack channel threads, so everyone can see them immediately without first clicking "view response." These public replies are generated only from content that's broadly visible in your company (such as public Slack channels and org-wide documents), so they're safe to share and easy to trust. Teammates can still personalize the answer with their own private context when they need a more tailored response.

How to access: To use public answers in Slack, first set up the Slack Real Time Search connector from the Glean Admin Console and install the Glean app in your Slack workspace or Enterprise Grid. If you have already done this, you can jump to the 'Embedded Integrations' tab to view the Glean in Slack setup page.

On this setup page, enable Gleanbot to respond in channels publicly and/or proactively. You can enable it for all public channels by default, or choose specific channels where you want Glean to participate.

Once enabled, channel members can ask questions in Slack and Glean will search across your company's public corpus (including public Slack channels) to generate shared responses, while still respecting each user's permissions for any follow-up personalization.

Learn more

Embedded Integrations [ROAD-908]

Persistent extension install button on Glean Home

Users who are actively using Glean but have not yet installed the browser extension will now see a persistent "Finish setup" style button on Glean Home that guides them to install the extension. This makes it clear that setup is incomplete and gives people a simple, always-available way to add the extension and unlock features like sidebar search, new tab page, and integrated search in apps like Google Drive and Box. The prompt appears only for eligible users and does not affect usage or billing.

Learn more

Glean Extension [ROAD-1581]

Admin Features

Admin dashboard now offers personalized recommendations of connectors, tools, and features to enable

The admin dashboard has been updated to include recommended connectors, tools, and features, alongside the existing notifications widget. The goal is to help admins discover the features that will open up new use cases for their users.

Learn more

Admin Capabilities [ROAD-1549]

Greenhouse connector migration to Harvest v3 APIs

Greenhouse connector Harvest v3 migration lets admins update their existing Greenhouse connector from legacy Harvest API credentials to Harvest v3 (OAuth) ahead of Greenhouse's August 31, 2026 deprecation deadline. Admins can add the new client ID and client secret in the Glean admin console without re-indexing or downtime, preserving existing search results and permissions. In beta: opt in from the admin console.

How to access: In the Glean admin console, open Connectors > Greenhouse > Setup and add Harvest v3 (OAuth) credentials (client ID and client secret). Keep the existing Harvest API Key and Webhook Secret in place, then save and wait for validation to complete.

Learn more

Connectors [ROAD-1393]

Granular controls for who can manage MCP servers

Admins can now delegate MCP server administration without giving full admin access. The new MCP Server Moderator role lets designated users create and manage MCP servers and view MCP Insights, making it easier to put ownership closer to the teams actually running AI workflows.

How to access: A Glean administrator can assign the MCP Server Moderator role to designated users so they can manage MCP servers and view MCP Insights without receiving broader admin permissions. Learn more in Glean's Help Center.

Learn more

Assistant [PACT-345]

More precise access control for MCP tools

Admins can now configure tool-level access controls directly from the Glean MCP server experience. This makes it easier to control which tools different users can access, while keeping permissions aligned across the broader tools and admin surfaces.

How to access: In the Glean Admin Console, open a Glean MCP server, click Add tools, go to External Tools, and open Tool advanced settings for a tool pack. From there, admins can set access for individual read and write tools, and those changes stay synchronized with the Tools admin experience. Learn more in Glean's Help Center.

Learn more

Assistant [PACT-344]

Glean is now available through the ChatGPT app marketplace

Glean's remote MCP server can now be enabled through the ChatGPT app marketplace, making it easier for admins to roll out Glean in ChatGPT and connect users to enterprise search and other Glean-powered workflows from that surface.

How to access: ChatGPT workspace admins can add the Glean MCP server from the ChatGPT admin connector experience and authenticate it with Glean OAuth. Once configured, users can enable Glean in individual ChatGPT conversations from the tools menu when they want to use it. Learn more in Glean's Help Center.

Learn more

Assistant [PACT-14]

Original source

User features

GPT-5.6 Sol, Terra, and Luna in Assistant and agents

OpenAI GPT-5.6 Sol, GPT-5.6 Terra, and GPT-5.6 Luna are now available in Glean Assistant and agents as premium models.

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

Learn more about premium models in Assistant

Agents [ROAD-1562]

Mix and match existing slides to create a new presentation with Glean

You can now build new presentations by mixing and matching slides from decks you already have in Glean, instead of starting from a blank prompt. Choose one or more source presentations, then let Assistant suggest which slides to keep, drop, or reorder based on the story you want to tell, while generating only the missing title, transition, and summary slides needed to make the deck feel cohesive. The final presentation is exported through the existing slide generation pipeline to PowerPoint or Google Slides, preserving your company's branding and template settings.

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

Learn more about mixing and matching slides

Assistant [ROAD-1537]

Trigger agents by events

Automatically run Glean Agents in the background when content changes across your connected data sources — Gong, Jira, Salesforce, Google Calendar, email, and more — no manual intervention required. Use triggers to scale repetitive processes, ensure timely actions, and keep work moving: agents can send Slack notifications, generate summaries and kick off downstream workflows, all within your organization's existing guardrails and permissions. It is Generally Available and enabled by default for all users. Admins can scope access from the admin console and check out the Glean Docs for supported sources and setup.

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

Learn more

Agents [ROAD-731]

Interactive artifacts are now generally available

With interactive artifacts, users can create visual proposals, rich analysis, and refreshable dashboards. Each artifact lives natively in Glean with a stable URL, shows up in Glean search, and can be shared at private or org-wide visibility without exposing the underlying chat.

This release moves interactive artifacts out of preview and includes several improvements:

• Start from templates. Ready-made templates surfaced under the Create artifacts button in the library to help you spin up artifacts for common workflows.
• Style your artifact. Change the look and feel of an artifact so it matches your team's or company's visual style.
• See source citations. Artifacts now surface citations to the underlying sources, so you can trust the data being presented.
• Higher-quality output. When in auto mode, interactive artifacts will be generated by a model that is optimized for creating polished visualizations, such as Claude Opus 4.8 (if enabled in your deployment).
• Improved triggering. Glean is better at recognizing when a request is a good fit for an interactive artifact, so more users discover the feature naturally.

How to access: Interactive artifacts are available automatically in Assistant when the Interactive artifact setting is turned on in your Glean admin console. If Interactive artifact is turned off, Assistant will respond with standard text-only answers.

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

Learn more

Assistant [ROAD-1540]

iOS shortcuts on home screen and lock screen

Launch a Glean Chat or Voice chat directly from your iPhone home screen or lock screen — one tap and you're live. Add the Glean Chat or Glean Voice widget, and on iOS 18, use the new Lock Screen and Control Center controls for even faster access. No app navigation required.

Learn more

Assistant [ROAD-1539]

Full-screen and navigation buttons on Glean-generated slides

Present Glean-generated slides directly inside Glean with built-in full-screen and navigation controls.

Learn more

Assistant [ROAD-1538]

Queue a follow-up chat during long-running Assistant chats

Queue your next prompt while Glean Assistant is still working. If a chat is already in progress, you can add a follow-up message to run automatically as soon as the current response finishes, so you can keep moving without interrupting the task or coming back later to retype it. Queued follow-ups also carry over composer settings, including file attachments and model selection. You can also review, edit, or remove queued follow-ups before they run.

Learn more

Assistant [ROAD-1507]

Render charts, diagrams, and visualizations in Assistant responses

When you ask for a chart or a diagram, Glean can render it as a compact, interactive widget right inside the chat response. You can then copy the widget's output as an image to drop into a doc, slide, or message.

How to access: Inline artifacts are available automatically in Assistant when the Inline artifact setting is turned on in your Glean admin console. If Inline artifact is turned off, Assistant will respond with standard text-only answers.

Learn more

Assistant [ROAD-1468]

Create interactive artifacts from templates

Templates help end users quickly create interactive artifacts for common workflows. Users can start from ready-made templates surfaced in the library under the "Create" button, then customize the generated artifact to fit their work.

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

Learn more

Assistant [ROAD-1344]

Share artifacts with your entire organization via the share button

Artifacts can now be shared with your entire organization, making them discoverable via the library and search. This is in addition to existing sharing options like specific people or departments and anyone with the link, giving teams a clearer way to control how broadly their content is published.

Learn more

Assistant [ROAD-1331]

Group your chats, sources, and artifacts with Glean Projects

Glean Projects help users organize chats and content in Glean so related work is easier to group, revisit, and share.

How it works: Create a folder to keep relevant chats and artifacts together in one place. folders are private by default and can be shared when needed. Existing Collections will automatically migrate to folders, with existing permissions preserved.

Assistant [ROAD-909]

Writing profile removed from Personalization

The writing profile section has been removed from Settings → Personalization. A more detailed memory experience - with improved ways to view and manage your memories, writing style, and more - is coming soon.

Assistant

More streamlined chat conversation search

Use the new chat history search dialog to quickly find past Glean chats and agent runs from the left sidebar. Search by thread title keywords and filter between Assistant chats and specific agents so you can jump back into ongoing work without scrolling. Open chat history search from anywhere in Glean with the Cmd+K keyboard shortcut.

How to access: Admins: In the admin console, go to Platform → Assistant → Settings and, under Chat history, select a retention period (for example 90 days or 1 year) instead of Off, then save. End users: open Glean, use the Chats panel in the left sidebar, and either type in the chat history search bar or press Cmd+K to open the chat search dialog.

Learn more

Glean Home [ROAD-1499]

Admin features

Admin Capabilities [ROAD-1531]

Model governance by department for LLMs (Glean key and Customer key)

Admins can now configure model governance policies at the department level for LLMs, giving organizations more granular control over which models are available to different teams.

Learn more

Admin Capabilities [ROAD-1339]

Per-user usage visibility in Billing Console

Admins can now see AI and model usage at the individual user level in the Billing Console, not just as aggregate workspace totals. The per-user view helps billing and finance teams explain where spend is coming from, spot outliers or power users early, and export user-level usage to support internal chargeback or governance workflows. This update adds richer visibility only and does not change how limits or usage controls are enforced.

How to access: Admins and billing moderators can access per-user usage from the Admin Console by going to Usage and choosing the By users view. Access to these views is limited to roles with billing permissions. If you don't see Usage in the admin console, your Glean role may not include billing or admin access.

Learn more

Admin Capabilities [ROAD-1185]

Per-user, per-agent FlexCredit usage limits in admin console

Admins can now set per-user monthly usage limits directly in the Admin Console, with global defaults and per-user, per-agent overrides to match different roles and departments. When a user reaches their usage limit, Glean automatically pauses access to billable features. This gives customers more predictable AI costs, stronger governance controls, and a safer path to scaling usage.

How to access: From the admin console, go to Usage → Manage usage limits to configure cost guardrails.

Learn more

Admin Capabilities [ROAD-731]

Search and filter MCP servers in the Admin Console

Admins can now quickly find specific MCP servers in the admin console using a search bar on the Glean MCP server page.

How to access: From the Admin Console, go to Platform → Glean MCP server and use the Search by server name box above the server list to filter servers as you type. No additional configuration is required.

Learn more

Connectors [ROAD-1533]

Original source

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
Admins can now import and sync Skills from public and private GitHub repositories into Glean. This makes it easier to manage shared Skill libraries in Git and keep Glean up to date with community, open-source, and internal Skills that follow the open Agent Skills standard.
Users can paste a GitHub repo URL, and Glean will fetch compatible .skill and .md files for import. Imported repositories stay up to date through a daily refresh, and users can refresh a GitHub-imported Skill before the next automatic refresh from the Skill's three-dot menu.
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, so you can import compatible Skills from any public or private repository that follows the standard and tailor them to how your organization works. Admins can manage Skills rollout, sharing, and organization-wide governance with role-based controls, while personal Skills remain private unless users choose to share them.
How to access: Administrators must enable for your organization. Admins can manage shared and organization-wide Skills from the Admin console. End users can create personal Skills and use shared or admin-published Skills directly in Glean Assistant. Private Skills remain invisible to admins unless users choose to share them.
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]
Projects: organize chats and content in one place
Projects help you organize chats and content in Glean so related work is easier to group, revisit, and share. Create a project to keep relevant chats and artifacts together in one place. Projects are private by default and can be shared when needed. Existing Collections automatically migrate to Projects, with existing permissions preserved.
How projects work
Platform [ROAD-909]
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