Skip to main content

Release Notes

Welcome to the Glean Release Notes. Here, you'll find information on recently launched features and improvements.

Coming Soon

Learn about upcoming features and improvements in Glean

Product and feature retirements

Information about deprecated and sunset features in Glean

Glean Betas

Learn about Glean Betas in the Gleaniverse's Admin Hub (Glean Admins Only)

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.

  1. 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.
  2. 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

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

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 pricing@glean.com 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

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

  1. Navigate to Admin Console → Platform → LLM

  2. 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

  1. Navigate to Admin Console → Platform → Assistant → Settings

  2. Under "New agentic engine features," enable Fast and Thinking modes

  3. 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

→ View
→ View
→ View
→ View
→ View
→ View
→ View
→ View
→ View
→ View
→ View
→ View
→ View
→ View
→ View
→ View
→ View
→ View
→ View
→ View
→ View
→ View
→ View
→ View
→ View
→ View
© 2026, Glean Technologies, Inc.
Last updated on