Release Notes

Connector health metrics in the admin console (Crawl Rate and Change Rate)

Connector metrics related to documents crawled, document updates, and total indexed document counts is captured in data sources in the admin console, providing greater visibility on the overall health of connectors.

New role-based access controls for actions

New role based access controls for actions let admins limit which agent creators can add and configure specific actions by user or department. End users can still run the actions in shared agents.

Increased granular permissions for how agents are shared

Glean now supports granular sharing permissions for agents, allowing admins to independently control whether Default Members can share agents with individual teammates, specific departments, or the entire company, as well as whether Default Members have access to agent publishing options. New toggles in the admin console make it easy to specify sharing scope for agents, helping organizations keep the agent directory clean and relevant for all users.

How to access: Configure agent sharing permissions in the Admin Console under “Teammates” –> “Default Member permissions”

Support Agentic Engine 2 on Claude Sonnet 4.5

Glean Assistant now supports the Agentic Engine 2 on Claude Sonnet 4.5. This enhancement brings advanced agentic reasoning capabilities—such as multi-step planning, tool orchestration, and stateful workflows—to customers using Anthropic models. Users can expect higher-quality responses to complex, multi-step queries, improved accuracy, and more efficient cross-tool workflows when leveraging Claude in Glean Assistant.

Data analysis tool achieves 96% completeness when running on Agentic Engine 2

Glean Assistant now supports adaptive planning and iteration over uploaded files, allowing for greater analysis of structured data including large CSVs and multi-file joins. On internal performance benchmarks, we’ve seen the data analysis tool on Agentic Engine 2 achieve 96% on completeness and a 61% reduction in latency.The data analysis tool performance upgrade is available to customers on either the universal model key or the Glean key for Azure. Data analysis uses OpenAI’s code interpreter functionality.

Simpplr Connector (AWS Version)

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

AWS Bottlerocket for Code Interpreter

We have migrated all remaining AWS Amazon Linux 2 k8s hosts over to the more secure Bottlerocket instances.

How to access: No action required by customers. This is automatic!

Support for AWS IAM permissions boundaries

Glean AWS deployment customers can now create a permissions boundary to further constrain Glean’s IAM permissions. This allows AWS customers to limit the maximum permissions required for Glean to operate in AWS, which improves the security of the deployment.

How to access: Glean Cloud-Prem AWS customers should reach out to their account representative to enable.

Create agents using natural language from within the Agent Builder

Chat is now built into Agent Builder. Create agents through a multi-turn conversation—describe your goal in plain English and let AI draft it—then switch to node-level editing for precision or blend both without losing context. The unified workspace adapts to your style, helping you iterate faster, get better results from advanced reasoning, and avoid choosing between “easy” and “powerful.” Start in natural language, take manual control where it matters, and scale from simplicity to power-user depth on demand.

How to access: Administrators must enable for your organization.

Incorporating adaptive planning into Glean Agents plan & execute steps

Glean Agents now thinks before it acts: Instead of giving you one answer and calling it done, Glean Agents plan & execute steps now work more like you do—it thinks through problems step by step, makes a plan, works through the plan, and adjusts when something doesn’t work all in service of accomplishing the objective at hand.

• Smarter problem-solving: The agent breaks down complex requests into smaller steps and tackles them one at a time
• Course correction: If the first approach doesn’t work, it tries a different strategy instead of giving up
• Asks for help: When unclear about what you need, it asks clarifying questions rather than guessing
• Control level of effort: You can control whether or not plan & execute optimizes for speed or depth in its decision making

Your agent can now handle bigger, more complex tasks that require multiple steps or decisions along the way and anchor more on the objective you want it to accomplish—like analyzing data across different systems, building comprehensive reports, or research projects that need information from various sources.

How to access: Administrators must enable for your organization.

Google Conversational Analytics actions for BigQuery in Agents

Users will be able to query BigQuery data using natural language in Agents.

How to access: Administrators must enable for your organization. Admins to configure Google cloud actions for their instance.

Write actions in interactive agents can run in‑line without requiring user confirmation

Write actions can be set to run in interactive agents without explicit user confirmation. When this occurs, it removed the click for confirmation step cutting the amount of time it takes to complete the action. For a write action to run without user confirmation, it needs to first be configured in the admin console. Agent creators can then choose to enable in-line execution within the agent builder.

Support for Claude Sonnet 4.5 in the model hub (Agents only)

Claude Sonnet 4.5 is now available in the Glean model hub for use with Agents. This update gives organizations access to Anthropic’s latest model via Amazon Bedrock or Google Vertex AI, enabling more advanced reasoning and improved performance for agentic workflows.

Glean in ServiceNow published in app store

The Glean for ServiceNow integration is now officially listed in the ServiceNow Store, making it easier to discover, install, and manage the embedded integrations within your ServiceNow environment. There’s no change in functionality, configuration or permissions.

How to access: Install the app from ServiceNow’s App Store. The Links and Documents section contains detailed instructions on how to set up Glean in ServiceNow for each workspace.

Get notifications when Glean Assistant completes long-running queries

Glean now supports browser notifications for Glean Assistant responses in Chat. When a user receives a reply in Chat and the Glean tab isn’t in focus, a notification will appear, allowing the user to click and jump directly back into the exact thread. This feature helps users stay engaged with long-running queries and ensures they never miss a response.

How to access: Notifications require the user to opt in twice—once in Glean and once in their browser and the user must also enable browser notifications at the OS level on Mac or Windows. The user can turn off notifications at any time via the Preferences tab in their settings page.

Easily access Glean Assistant directly in the Glean Desktop App

Glean Desktop App now offers a chat-first experience, making it easier to access Glean Assistant directly from your desktop. Use quick chat to open a dedicated window and attach screenshots to your chat conversations, streamlining research and collaboration. These enhancements help you find information, summarize content, and interact with your company’s knowledge base more efficiently—right from your desktop.

RSS feed for release notes

You can now subscribe to Glean release notes via an RSS feed. RSS feeds can integrate with Slack, email, or other subscription tools to notify you when our release notes are published.

How to access: Use your favorite RSS reader and the RSS-linked XML page.

Assistant Insights tab to get more detailed insights

Assistant tab on Insights has been revamped to provide richer insights on overall and department level usage of Glean Assistant within your company.

Admin Self-Serve for Auto-Runnable Actions

Admins can now choose which actions run automatically in the background from Actions > [action pack] > Configure in the admin console. Enable trusted automations—like sending a Slack message or creating a Google Doc—without user approval, while keeping sensitive actions under explicit confirmation. This enables admins to balance automation with security based on the organization’s needs.

API support for adaptive planning

Glean Assistant now offers API support for adaptive planning, powered by the new agentic engine. This upgrade enables more flexible, iterative reasoning in chat and API workflows, allowing the Assistant to proactively clarify user intent, accept feedback, and refine responses for higher-quality results. Users benefit from improved answer quality on complex, multi-step queries, with the system leveraging advanced planning to deliver more accurate and context-aware responses.

How to access: Glean Cloud-Prem AWS customers should reach out to their account representative to enable.

Support for AWS IAM permissions boundaries

Glean AWS deployment customers can now create a permissions boundary to further constrain Glean’s IAM permissions. This allows customers to limit the maximum permissions required for Glean to operate in AWS, which improves the security of the deployment.

How to access: Glean Cloud-Prem AWS customers should reach out to their account representative to enable.

Gemini BigQuery Analytics with Context action supports Looker and Looker Studio

In Agents, users will be able to query BigQuery data using natural language via Looker and Looker Studio. These queries will be powered by the Gemini for Google Cloud Conversational Analytics API.

How to access: Administrators must enable for your organization.

Scheduled Triggers: Run agents on schedules

Glean Agents now support scheduled triggers, enabling agents to run automatically on a set schedule (such as daily, weekly, or monthly) without user intervention. This enhancement allows users and teams to automate recurring tasks, receive timely updates, and standardize business processes—improving productivity and reducing manual effort. Common use cases include intelligent reminders, delegation trackers, and weekly work reports, all available as templates in the agent library.

How to access: Administrators must enable for your organization. Admins can turn on the scheduled triggers by going to Admin console → Platform → Agents → Scheduled triggers.

Glean Assistant is now your personal agent

The Assistant is getting major upgrades, including a new all-knowledge mode that merges enterprise and real-time data in one query while giving users the option to choose between faster responses or deeper thinking based on their needs. The system uses an updated agentic engine with adaptive planning that proactively solicits user clarification, accepts user feedback, and refines its responses to deliver higher-quality results.

How to access: Administrators must enable for your organization. The Assistant refresh launched as a managed rollout on Sept 9. Admins can enable this for their users before October 30th via the Admin Portal.

Conduct comprehensive research in Glean Assistant

Deep Research is an AI agent in Glean Assistant that conducts comprehensive research across internal data sources and the web, analyzes that data, and synthesizes the insights into a detailed, citation-rich report. It’s designed for complex, multi-source questions and supports seamless export to Google Docs, OneDrive, Gmail, Outlook, and Slack. This feature is subject to usage-based pricing. For details, please contact pricing@glean.com. This feature is only available for customers on GCP or AWS and the Glean Key. Customer Key availability planned for Q4.

How to access: Administrators must enable for your organization. Turn on Deep Research for your users: Deep Research is turned off by default. Administrators can enable via self-serve in the Admin Console (Assistant → Deep Research) for all users or specific users. Once enabled, users can access Deep Research from the menu below Glean Chat.

Enumeration queries in GleanChat

Glean has improved the quality of enumerate queries in Agentic Engine by 33% and in Agentic engine 2 additionally by 19% on internal evals. On external evals we have seen a similar 19% improvement in quality from Agentic Engine to Agentic Engine 2. In Agentic Engine 2, we additionally are able to better display the enumerate responses in assistant by leveraging a scrollable table format.

Glean in slack now with agentic engine & adaptive planning

Bring the power of adaptive planning to Glean in Slack. The Glean Slack app now supports agentic engine 2, enabling Glean to autonomously plan, use tools, and execute multi-step actions directly within Slack threads. Users can ask complex questions or request help in Slack channels or DMs, and Glean will proactively reason through multi-step workflows—researching, gathering context, and following through on tasks so work keeps moving. This improves response quality and enables more advanced automation for both channel conversations and private sidebar interactions.

How to access: Enabled with agentic engine (Ref FR-4123)

Support for GPT-5 in Assistant (Customer key customers)

Customers can now enable GPT-5 from Azure or OpenAI providers for the new adaptive planning capabilities in Glean Assistant.

Agent library: featured agents

Admins and agent moderators will be able to curate a “Featured” category in the Agent library.

AWS Customers can now bring their own keys for Vertex AI to the model hub

AWS customers using their own LLM key can now configure and use Google Vertex AI models—including Gemini—for Glean Agents and web search. This update expands model choice and enables organizations on AWS to leverage Gemini’s advanced capabilities for both internal automations and real-time web search, all while maintaining control over their own LLM credentials and billing. No additional code changes or manual intervention is required; Gemini web search and Vertex AI models are now available for self-serve setup in the Admin Console.

How to access: To enable Vertex AI (Gemini) models on AWS with your own key: In the Glean Admin Console, navigate to Platform > LLM and click Add LLM. Select Google Vertex AI as the provider and when prompted, upload your GCP service account key JSON and provide the relevant GCP project ID. Note: This service account must have the necessary Vertex AI permissions. Choose the Gemini models you wish to enable, validate the connection, and save your settings. Once configured, these models will be available for use in Glean Agents and web search action packs.

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

Glean has significantly improved the quality of answers related to PDF documents that are referenced in Glean Assistant via uploading files, tagging documents in chat, mentioning a document by @ mention, pasting URLs. The quality improvements also apply to multi-modal PDF documents that include images. This change is available today to GCP customers. Support for AWS will come in a later release.

Salesforce connector now supports draft knowledge articles

Glean’s Salesforce connector now supports draft versions of knowledge articles. This enhancement ensures that both published and draft articles in Salesforce are discoverable in Glean search, making it easier for support engineers and internal users to access the most up-to-date and relevant information—even if it’s not yet published externally.

Support for Glean Agents in Microsoft Teams

Glean Agents are now available as apps in Microsoft Teams. In addition to using the Glean Assistant, organizations can deploy Glean Agents as an app inside Microsoft Teams, along with an ability to trigger any actions associated with the agent.

How to access: Administrators must enable for your organization.

See contextual images in Glean Assistant Responses

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.

How to access: Administrators must enable for your organization. Currently only available for customers with GCP hosted deployments. Will be extended to AWS deployments by October 7, 2025.

Rootly connector

Built by Glean Partner Rootly, the Rootly connector lets Glean users quickly access incidents, alerts, reports, schedules, and escalation policies, enabling faster resolution, trend discovery, and easier reporting.

How to access: Administrators must enable for your organization.

Access Glean from within Augment Code IDE

Glean in the Augment Code allows engineers to pull enterprise context (like PRDs) without leaving their IDE.

How to access: Administrators must enable for your organization. See https://docs.augmentcode.com/setup-augment/agent-integrations#glean-integration for how-to instructions.

Expand daily digest in Slack to include topics across your enterprise knowledge

Glean in Slack daily digest expands to include the ability to receive daily updates on topics that interest you across all your enterprise data sources (not just Slack channels).

How to access: Administrators must enable for your organization.

Enhancing Agent Step Prompts in One Click

We’re bringing the successful Enhance CTA from our one-shot compiler into the agent creation experience. We’ve consolidated prompting best practices from Glean’s internal builders and trusted external sources into one place. From any agent step, the CTA reviews the prompt, pulls the relevant best practices, and generates an improved version. If you don’t like the change, you can undo it to restore the original.

Wait for user input action in Agents

Wait for User Input step lets agents pause mid-process to ask users questions and use that input to inform next steps, enabling human-in-the-loop interaction with agents as they work. Key use cases include letting users choose output types (e.g., research report or spreadsheet) or running role‑play scenarios like sales negotiations and stakeholder briefings.

Autogenerated titles for chat threads

We will automatically update the title of each chat thread in the chat history to display a summary of the topic of the chat. For customers using their own LLM key, this will generate a call to the small model (e.g. GPT-4.1 mini, Gemini 2.0 Flash, or Claude 3.5 Haiku).

Follow-up question improvements in Glean Assistant

Glean is enhancing the Assistant by introducing conversational follow-up questions. As part of this update, users will now see more conversational follow-up questions directly within Glean Assistant instead of “Related Questions” below Assistant responses.

Support Ticket Timeline View in Embedded Integrations

We are introducing a timeline view to the existing Summary feature for support tickets and cases in Glean’s embedded integrations with Zendesk, Service Cloud, and ServiceNow. The timeline view compiles a clear, end-to-end timeline of support interactions related to a ticket, including linked documents and chats. Events are arranged chronologically with accurate timestamps, providing a comprehensive view of all activities associated with the ticket.

Improvements to answer quality for documents uploaded in Assistant

Glean improves the quality of answers for document uploads, @ mentions, and URLs in Assistant by leveraging the OpenAI file upload API. Customers using Glean Key for OpenAI and customers using their own customer key for OpenAI will benefit from these quality improvements.

Note: For this feature, we will be accessing OpenAI file API directly. OpenAI does not use any data for training its models.

New Microsoft Dynamics 365 connector

Glean supports Microsoft Dynamics 365, Microsoft’s unified platform that delivers both customer relationship management (CRM) and enterprise resource planning (ERP) capabilities. Glean’s connector is designed to crawl and index key CRM entities, specifically accounts, contacts, opportunities, and leads within Dynamics 365.

Integration with Palo Alto Networks Prisma AIRS Runtime Security

As part of our Protect+ offering, Glean can now secure Chat and AI agents against prompt injection attacks or jailbreak attempts. Runtime security protects subscribed agents, agents that are scheduled or triggered automatically to run, from indirect prompts or file uploads with malicious instructions.

How to access: Protect+ customers should reach out to their account team to enable this feature.

AI Security for prompt injection, malicious code, and toxic content detection

AI security models that support real-time blocking of prompt injection attacks, toxic content, and malicious code. Glean achieves 97.8% accuracy on prompt injection detection, 93.5% accuracy on toxic content detection, and 94.3% accuracy on malicious code detection on leading benchmarks. AI security is managed in a centralized dashboard complete with the surrounding context, the prompt, source file, agent identifier, user information, and chat session. This feature set is part of Glean Protect+.

Improve latency and quality of AI Answers in Search

AI answers are an AI-generated, permission-aware answer shown directly on the Glean Search results page, synthesizing top relevant documents to see a fully written response. We decreased the latency by 52% at p99 and improved the quality of AI answers, helping more users discover and use Glean Assistant.

Search BigQuery with SQL action

In Agents, users will be able to query BigQuery data using SQL. These queries will be powered by the BigQuery API.

How to access: Administrators must enable this for your organization.

Support for autosaving drafts and versioning agents

Agent Builder will autosave drafts while you edit, let you update drafts without changing your published agent, and will keep the last 30 published versions so you can restore them as new drafts.

Edit queries and regenerate responses in Assistant

We are adding the ability for users to edit their chat queries and regenerate the response. This will be accessible via a pencil icon shown below the user’s chat bubble.

Interrupt ongoing chat queries

You can now interrupt an in-progress Glean chat response and immediately start a new message. This lets you seamlessly pivot conversations and issue new instructions without waiting for the previous query to finish. The experience is more fluid, giving you greater control and flexibility during multi-step research and troubleshooting in Glean Chat.

Access Glean from within Miro workspaces

Glean in Miro allows users to query Glean search results directly into Miro boards and workspaces. It helps in summarizing information, generating insights, and creating action items, thereby enhancing the productivity and efficiency of collaborative sessions.

How to access: Administrators must enable for your organization.

Enable Glean Search and Assistant tabs in Support embedded integrations (opt-out)

We’ve added “Search” and “Chat” tabs directly inside your Support workspace so support representatives can search on Glean or get help from Assistant without switching tools, speeding up case resolution. This is enabled by default; if you’d prefer not to use these tabs, please reach out to your Glean contact to opt-out or turn it off in your Embedded Integrations setting.

How to access: Administrators must enable this for your organization.

Ability to exclude models to be used in agents from the Model Hub

Admins for customers on Glean Key will now be able to individually exclude models to be used in agents from the Model Hub.

World mode quality improvements

World Mode in Glean Assistant has been upgraded to a new architecture aligned with ChatV2. This update introduces a smarter orchestration system (“Strategize”) and an improved response format, delivering higher-quality, more complete, and better-formatted answers when using World Mode. The change also updates the underlying model to GPT-4.1, leading to responses that match or exceed ChatGPT in external benchmarks for information-seeking, writing, and formatting tasks. Users will experience clearer, more structured, and more comprehensive answers in the Public Knowledge World Mode) chat experience.

Expanded Model Access for Agents with Cross-Cloud Model Hub in Glean Key (GCP <> AWS)

Glean customers can now select and use large language models (LLMs) across both AWS (Amazon Bedrock) and GCP (Google Vertex AI) platforms in the model hub, regardless of their deployment’s primary cloud. For example, GCP-hosted customers can now enable Bedrock-hosted models for use in agents, while AWS-hosted customers can access Vertex AI-hosted models—significantly broadening choice for Glean Agents and improving flexibility for diverse workflows.

How to access: Glean Key Customers only. Admins can enable any available models directly in the model hub configuration within the Glean Admin Console. This update does not impact the default model for Glean Assistant.

Limit AWS IAM PassRole Permissions on AWS

We have made some improvements to our AWS IAM permissions to scope down the use of iam:PassRole permissions to only be passable to Glean-specific IAM roles in the Glean AWS account. Previously this was not scoped down. Scoping down improves the security of Glean in AWS.

How to access: No action required by AWS customers - this is applied automatically.

Create Jira tickets with Glean actions

Streamline engineering and related workflows by automatically creating Jira issues, speeding up resolution and increasing efficiency.

Note: This complements the existing Jira Service Management (JSM) capabilities to create JSM tickets from within Slack.

How to access: Administrators must enable for your organization.

Agent LLM Model selector now more easily accessible

Model choice plays a critical role in agent performance. Previously, changing the model required navigating through multiple screens to access the advanced settings for each step — making it cumbersome for builders and admins to update. We’ve now moved the model selector directly into the agent step configuration settings, making it more visible and easier to use. This change simplifies model customization for each step, giving customers more control with less friction.

GPT-5 in LLM model hub

Customers can now use GPT-5 to build agents with Glean.

Note: At this time, GPT-5 is only available through OpenAI directly and not via Azure.

How to access: Administrators must enable for your organization.

Move “Agents” nav item to top level navigation bar

Agents is now a top‑level item in Glean’s left navigation menu, making it easier to find and launch.

Assistant supports Salesforce Search with SOQL action

Glean Assistant now lets users ask deeper questions about Salesforce data using natural language, including sorting and filtering records. Assistant interprets the user’s natural language query into Salesforce SOQL to answer the user’s question, using the Search Salesforce with SOQL Action in the Salesforce Action Pack. You can ask Glean a question that includes hints that the answer lives in Salesforce, e.g. “From Salesforce, what are the top open opportunities by ARR?”

Glean will automatically enable the Search Salesforce with SOQL Action for customers as it will improve Assistant response quality. We recommend that admins leave this action on for better Salesforce querying in Assistant.

How to access: Administrators must enable for your organization. Please note that first-time users of the action will have to authorize Glean to connect to Salesforce.

Support tagging of any document in Glean Chat

When using @ to tag a document in the Glean Chat composer, users will now have an option to search and select any document in Glean.

Customize how agents are organized and run in Glean’s embedded integrations for Support (formerly Glean Assist)

Support admins can now easily add, organize and update which agents are available to customer support representatives.  Addtionally, Glean Search and Assistant are now directly accessible in Zendesk, ServiceNow and Service Cloud.

How to access: Administrators must enable for your organization.

Allow users to negate a search operator and term to exclude results from a search

Exclude search results with a minus sign. You can now remove unwanted results right from search. Add a minus sign before a filter to exclude matches.

hides results from you removes results from Engineering

Check the last crawl time of a document based on its URL

Admins can now use the access verification tab in Protect to enter a document URL or ID and view its last crawled time, last indexed time, visibility, and check user-specific access permissions.

Support for custom date ranges in Glean insights

Glean Insights now offers the ability to download data based on a custom date range, giving admins and Insights moderators more flexibility in how they analyze adoption data.

Sunsetting of Bing for web search and automated migration of customers to Brave and OpenAI providers

Bing will retire its Search APIs from the Azure Marketplace on August 11, 2025. To ensure continued service, we will automatically migrate all customers currently using Bing to the Brave and OpenAI action packs—both of which feature zero data retention. This migration will start on July 16, 2025, and is expected to be completed by August 8, 2025.

Enhancements to agentic reasoning engine planning drive Assistant performance gains (Customer Key)

For customers using their own LLM Key: Advancements in the planning aspect of our agentic reasoning engine architecture have improved the quality of complex queries in Assistant. Overall, queries have seen a 1.1% improvement in completeness and approximately 3% improvement in correctness. These performance enhancements come with a 30% increase in latency at p25 and a 13% increase at p50. ~30% token usage increase for the large model and ~70% token usage decrease for the small model.

Note: This was released previously for customers using Glean Key in FR-3718

Sunsetting of the prompt library

As part of the rollout of Glean Agents, we have sunset the Prompt Library. Users will no longer be able to access or create simple prompts. Admins will be able to download a backup of all simple prompts from the Admin Console.

Assistant supports Jira Search with JQL action

Glean Assistant now lets users ask deeper questions about Jira data using natural language, including sorting and filtering records. Assistant interprets the user’s natural language query into Jira JQL to answer the user’s question, using the Search Jira Action in the Jira Action Pack. You can ask Glean a question that includes hints that the answer lives in Jira, e.g. “From Jira, what are the open issues assigned to me?” Please note that first time users of the action will have to OAuth to allow Glean to connect to Jira.

Glean will automatically enable the Search Jira Action for customers as it will improve Assistant response quality. We recommend that admins leave this action on for better Jira querying in Assistant, and encourage them to reach out to their account team if they have questions or concerns.

How to access: Administrators must enable for your organization. Admin > Actions > Jira Actions

Web search enabled by default for all Glean customers

Web search is enabled for all Glean customers unless explicit instructions provided to not enable it. For customers who have not yet set up web search, Brave and OpenAI will be provided as default search providers, both of which offer zero data retention. For customers who have enabled OpenAI or Gemini, Brave will additionally be enabled.

Glean is deprecating the Discover tab in the extension sidebar

Due to limited usage of the discover tab in the browser extension sidebar and our intentions to simplify the product, we are deprecating this tab’s availability. Users will only see the Chat and Search tabs in the sidebar once deprecated.

Improve Agent discovery on Glean Homepage

We’ve added a “Discover Agents” section to the Glean homepage for all users to help them locate and use agents more effectively.

Agents in Search results page

Agents are now returned in Glean Search results for queries that correspond to relevant agents. Additionally, users can filter Agent results by using the operator app:agents in Search.

How to access: This feature is released to all customers who have Agents deployed.

Support for OpenAI as a web search provider for Glean key customers

Support for a managed OpenAI web search is now available to key Glean customers as an action pack, powering world knowledge mode in Assistant and web search in Agents. When enabled, Glean will leverage OpenAI web search directly via OpenAI and not via Azure. Customer data is not used by OpenAI for training its models and data sent to OpenAI is not retained by OpenAI

Revamped overview and department level Insights (AWS Only)

The Insights page now has an “Overview” tab with key usage metrics of Glean Search, Assistant and data sources. A new “Departments” tab shows department-level usage. These features, once limited to GCP customers, are extending to AWS customers.

Check the last crawl time of a document based on its URL

Admins can now use the access verification tab in Protect to enter a document URL or ID and view its last crawled time, last indexed time, visibility, and check user-specific access permissions.

Insights now display only users who have signed up for Glean

The “All users” view on the Overview page of Insights now only includes people who have actually signed up for Glean, instead of everyone in your organization. This makes it easier for admins to see meaningful data and avoids confusion from showing users with no activity who never joined Glean.

Admins can download backups of existing prompts and apps

From Agents section of the admin console, admins will now be able to download backup copies of their existing simple prompts and apps.

Support for Brave for web search

Glean adds the ability to use Brave, a search engine that emphasizes user privacy and has zero data retention, for world knowledge. Brave is available as an action pack and can be enabled in Assistant and/or Agents.

Introduction of knowledge graph concepts in Glean Chat to improve Chat quality

Glean Chat now leverages knowledge graph concepts to deliver more accurate, contextual answers. It better selects tools like Code Search when appropriate and pulls more relevant context, resulting in smarter, more targeted responses.

Enhancements to agentic reasoning engine planning drive Assistant performance gains (Glean Key)

Advancements in the planning aspect of our agentic reasoning engine architecture have improved the quality of complex queries in Assistant. Overall, queries have seen a 1.1% improvement in completeness and approximately 3% improvement in correctness. These performance enhancements come with a 30% increase in latency at p25 and a 13% increase at p50.

Support for Claude 4 in Glean Assistant

Glean now supports Claude 4 for use with Glean Assistant.

Reduce citations formatting errors in Gemini and Claude

Citations formatting errors when leveraging Gemini models with Glean have been reduced by 50-80% bringing error rate in the 1-2% range. Citations formatting errors when leveraging Claude models with Glean have been reduced by 20-50% bringing error rate in the 4-6% range.

Support for Wiz sensor in GCP deployments

Customers using GCP can deploy Wiz sensors on their compute resources, particularly for GCE instances and GKE nodes. This enables Wiz to monitor Glean deployments, enhancing security.

How to access: Please reach out to your account team for help enabling this feature.

Manage hidden content in a centralized dashboard

Content hiding in Glean allows users to manage document visibility by hiding specific documents—manually or via CSV—so they are excluded from search. Glean is now adding the capability to track, review, and unhide content through a centralized interface.

How to access: Available only to sensitive content moderator or superadmin role.

Snowflake actions include SQL validation, semantic views, and custom role support

Snowflake Actions now feature enhanced SQL query validation, support for querying both semantic views and semantic model files, and more flexible permission management by allowing any custom Snowflake role to be specified in setup.

How to access: Administrators must enable for your organization.

Debug Mode for Agent Creation

Agent builders can now use the debug mode when they are building and previewing agents with Glean. The debug mode shows which steps were run and the input and output for each step, allowing agent builders to rapidly build, debug and iterate on agent creation

How to access: Administrators must enable for your organization.

Agentic reasoning engine update for ‘Plan and Execute’ step in Glean Agents

This update includes quality optimizations that improve response completeness, context handling, and enhance instruction-following within the ‘Plan and Execute’ agent step.

Answer boards are migrating to collections

All existing answer boards will be migrated to collections using the same name. Your answers—and their permissions—will be fully preserved in the new collection. We will no longer be supporting answer boards moving forward.

Design updates to improve Glean Assistant experience

Glean Assistant design changes improve the user experience with Chat, intermediate steps, and citations.

Chat interface improvements include a lightweight chat-bubble to make the experience more conversational.

Intermediate steps will now appear in a collapsed UI, without the previously prominent steps with borders. This allows users to see more of the actual chat response and remove unnecessary visual clutter.

Citations user experience has been improved to focus on clarity including:

Clustering citations when there are more than three cited sources.Scrollable citation previews for easier navigation.“View sources” option is hidden when no sources are explicitly cited.Removed unused sources from citation drawerAdditional polish and refinements to improve overall citation presentation.

How to access: Note: These changes were previously available via admin preview and may have already been enabled by your administrator.

S3 connector for GCP deployments

The S3 connector (GCP platform) enables customers to index text-based documents from their S3 buckets into their Glean instance.

How to access: Administrators must enable for your organization.

S3 connector for AWS deployments

The S3 connector for AWS lets customers index text-based documents from their S3 buckets into Glean.

How to access: Administrators must enable for your organization.

Glean browser extension sidebar support for unindexed pages

Use the new extension sidebar on unindexed pages, including summarization, Doc Q&A, and any other chat features. The extension will automatically contextualize the page’s contents even when the document is not within your company index.

Analyze images, PDFs, presentations, and specific pages with screenshots in extension sidebar

Users can now capture screenshots directly from the extension sidebar to include visual content in their chat sessions. This enables analysis of images, PDFs, presentations, and specific page sections that weren’t previously accessible through text-only capture.

Non-critical logs for AWS deployments

We are relaunching non-critical AWS logging infrastructure to enable improved support and debugging for customers on AWS. Note that change may result in up to 2% increase in AWS infrastructure costs.

Block invalid headers on AWS ALBs

For AWS customers, we have enabled a feature on the primary AWS ALB to block invalid headers. This is a security feature that should not have any noticeable impacts to Glean.

Admins and agent moderators can filter the agent library to see agents shared with departments and everyone in their organization

Admins and agent moderators will now see a “Shared with” filter in the Agent library. This allows them to filter the library to only see agents that are shared with the entire company or shared with a specific department. Users will not see the “Shared with” filter.

Allow admins to customize the embedded integrations (formerly Glean Assist) features in the admin console

Adds a new tab called Embedded Integrations (formerly Glean Assist) in the admin console for admins to customize Glean in Zendesk, Salesforce, and ServiceNow.

Design updates to improve Glean Assistant experience (admin preview)

Glean Assistant is getting a design refresh, including Chat, intermediate steps, and citations.

Chat interface improvements include a light weight chat-bubble to make the experience more conversational.

Intermediate steps will now appear in a collapsed UI, without the previously prominent steps with borders. This allows users to see more of the actual chat response and remove unnecessary visual clutter.

Citations user experience has been improved to focus on clarity including:Clustering citations when there are more than three cited sources.Scrollable citation previews for easier navigation.“View sources” option is hidden when no sources are explicitly cited.Removed unused sources from citation drawerAdditional polish and refinements to improve overall citation presentation.

How to access: This is an admin preview.

Enhancements to agentic reasoning engine planning drive Assistant performance gains (Glean Key)

Advancements in the planning aspect of our agentic reasoning engine architecture have improved the quality of complex queries in Assistant. Overall, queries have seen a 1.1% improvement in completeness and approximately 3% improvement in correctness. These performance enhancements come with a 30% increase in latency at p25 and a 13% increase at p50.

Glean Assist is now called Embedded Integrations in the Glean admin console

The Glean Assist tab is now called Embedded Integrations within the admin console. Admins can configure Glean in Zendesk, ServiceNow, and Service Cloud within this tab.

Glean leverages the larger context window of GPT 4.1 to improve performance

When necessary for improved quality, Glean fully leverages the larger 1 million token context window of GPT 4.1 model as opposed to being restricted to 128K tokens for improved quality. This impacts customers using the Glean key for Assistant.

AWS WAF default blocking for the core rule set

Glean has been working on improving the security of our AWS deployments. We are rolling out AWS WAF controls for all our AWS customers that have been tested and will harden the security of the Glean deployment. In this release, we are enabling by default the AWS Managed Rule Groups for Known Bad Inputs

How to access: Customers are opted in by default. Please reach out to your account team if you wish to be opted out.

Estimate time needed to complete the initial data source crawl

An estimate of the initial crawl time is added to the data source setup page in the admin console.

Create conversational agents with natural language

Agent creators can now use the Use AI to generate a draft option to generate conversational agents from natural language instructions.

Reorder steps in the agent builder using drag & drop

Agent creators can reorder steps in the agent builder by dragging and dropping them. Steps can also be moved between branches in the same manner.

Migration of apps and advanced prompts to Agents for remaining customers

Since we made Glean Agents generally available on May 20, we have provided a transition period for admins to preview and decide when to launch Glean Agents for their deployment. The transition period will end on July 15, and we will automatically launch Glean Agents in all remaining deployments.

When Glean Agents are launched, all existing advanced prompts and apps will be automatically migrated to become Agents. The Prompt Library will then only contain simple prompts and we will offer users the ability to convert their simple prompt into an agent. We will begin showing a warning banner that the Prompt Library will be deprecated by Aug 5.

Agents with chat triggers that use conversation starters containing placeholders will now display an input form

Agents with chat triggers that use conversation starters containing placeholders (e.g., I would like to file PTO for [[start date]] to [[end date]]) now prompt users to fill in the required placeholders. This update restores the previous experience for conversation starters in apps.

Improvements to the quality of OpenAI web search

Glean has improved OpenAI web search performance by upgrading the action pack to use the OpenAI Responses API. This change will only impact -Glean Key customers- customers on their own key.

How to access: Administrators must enable for your organization.

Formatting improvements for Glean Assistant responses

Glean Assistant responses use a more structured format, with dividers, headers, and tables to organize the information.

Keep track of what you’ve accomplished and prepare performance self-evaluations in Glean Assistant

Ask Glean Assistant questions like “What did I work on last week?” or “Help me prepare for my upcoming performance review,” and you’ll get an AI-generated summary of your key accomplishments—drawing from the Glean Personal Knowledge Graph, which connects your daily activities to higher-level tasks and initiatives.

Allow users to select toggle preference between Search & Chat

Users can now set their default experience on the homepage to Chat or Search or Sticky (last used mode) based on how they use Glean. This new setting provides flexibility and lets them choose their preferred starting mode.

How to access: Select the user preference selector located in the user menu on the right-hand settings panel on the home page, and choose the default landing experience to Chat or Search or Sticky (last used mode).

AWS WAF default blocking for Linux and Unix rule set

Glean has been working on improving the security of our AWS deployments. We are rolling out AWS WAF controls for all our AWS customers that have been tested and will harden the security of the Glean deployment.

In this release, we are enabling by default the AWS Managed Rule Groups for Linux and Unix rules.

You don’t need to do anything at all. If you do not want to opt-in for any reason, please let us know and we will opt you out.

How to access: Customers are opted in by default. Please reach out to your account team if you wish to be opted out.

AWS WAF default blocking for SQL injection rule set

Glean has been working on improving the security of our AWS deployments. We are rolling out AWS WAF controls for all our AWS customers that have been tested and will harden the security of the Glean deployment.

In this release, we are enabling by default the AWS Managed Rule Groups for SQL Injection rules.

How to access: Customers are opted in by default. Please reach out to your account team if you wish to be opted out.

Logging of data source configuration changes in the admin console

Logging of changes to data source configurations will be made available in the admin console.

New action to deliver agent results to your email inbox

The “Send email from Glean” action lets Agents automatically email their output—text, tables, links, etc.—directly to the user who ran or subscribed to the agent (ie: send me a daily email summary of action items).

How to access: Administrators must enable for your organization.

1. Go to Platforms > Actions in Glean.

2. Click on “Add” and select “Email automation” action pack

3. Update your Publish Settings to include new action in Google pack.

Create Go Links on unindexed pages from extension sidebar

Glean has added the ability to create Go Links on any page a user is working in, even if the page does not contain an indexed document.

How to access: Open the extension sidebar, and navigate to the “Layers” icon in the sidebar sticky tab then create a name for your Go Link in the input field.

New actions to update Salesforce opportunity records from within Glean

Users can now update Salesforce opportunity records without leaving Glean, helping sales teams keep their CRM data up to date.

How to access: Salesforce Actions Setup

Validate action pack authorization from within Glean actions setup

Admins can now verify their authentication setup and receive guidance on resolving any issues encountered during action setup.

Upgrading WORKFLOW events with WORKFLOW_RUN event logs for easier analytics

Launching a new event type called across all customer-facing event logs. Admins who use Glean’s event logs will now have the ability to comprehensively track and analyze usage across all Glean AI products. These include Agents, which are the most frequently requested feature for these logs, AI Answers, Summarization, Deep Research, Daily Digests, and more.

Support for Wiz sensor in AWS deployments

Customers using AWS can deploy Wiz sensors on their compute resources, particularly for EC2 instances and EKS nodes. This enables Wiz to monitor Glean deployments, enhancing security.

How to access: Please reach out to your account team for help enabling this feature.

Set a green-list of countries that are allowed to access Glean via AWS WAF

Add country green-lists to AWS WAF. This configuration enables you to restrict requests to Glean so that only those originating from countries where your company operates are permitted, while blocking requests from all other countries. Note: Only data sources that are able to operate in (i.e., serve data from or to) countries on this green list may be used. Any traffic or data requests originating from countries not on the green list will be blocked.

How to access: Reach out to your Glean representative to enable this capability.

Block access to high sensitivity debug endpoints in AWS WAF

Glean provides the capability in AWS WAF to disable high sensitivity endpoints; endpoints that have high_sensitivity and actas_sensitivity in them.

How to access: Please submit a support ticket request to enable this feature.

Track metrics for the Glean agents you’ve created directly in Insights.

Agent creators can now see metrics on active users, agent runs, and upvote/downvotes for their agents in Insights.

Sunset the ability to create answer boards

We have sunset the ability to create new answer boards for legacy customers, as we transition to collections, a single tool to store answers as well as other enterprise artifacts. To ensure a seamless transition, legacy customer answer boards will be automatically migrated to collections in mid-July.

Glean Agents run on the agentic reasoning engine

Glean is upgrading its underlying architecture from a RAG-based system to an agentic reasoning engine, providing greater access to tools and multi-step workflows across both the Assistant and Agents.

How to access: Accessible as part of Glean:Go Agents updates (June 1, 2025)

Support for Claude Sonnet 4 in the model hub

Glean supports Claude Sonnet 4, hosted on both Amazon Bedrock and Google Vertex AI, as part of its model hub. Customers can select Claude Sonnet 4 for each agent and for individual agent steps.

How to access: Glean admins can enable Claude Sonnet 4 from the admin console in the LLM section.

Create Jira Service Management tickets from within Slack

Automate IT support with Glean’s ability to create Jira Service Management tickets directly from Slack, streamlining ticket resolution and improving overall efficiency.

How to access: Admins need to enable the Jira action pack, and add the Jira create request action to an app to use this feature.

Export to CSV option for Admin-facing insights (GCP Only)

Our new Insights Overview page will now have an export to CSV functionality that was available previously for downloading a snapshot of usage at a user level.

Wiz sensor support for AWS

Customers using AWS can deploy Wiz sensors on their compute resources, particularly for EC2 instances and EKS nodes. This enables Wiz to monitor Glean deployments, enhancing security.

How to access: Please reach out to your account team for help enabling this feature.

Content hide and unhide APIs for sensitive content protection

The ability to hide or unhide sensitive documents from being accessed within Glean using APIs. These APIs empower administrators to programmatically control document visibility, ensuring compliance with data governance policies and reducing the risk of accidental data exposure.

Create and manage weekly or continuous policies for sensitive data using developer APIs

Sensitive insights(ie: dashboards) run weekly or continuously to identify and automatically hide sensitive data from within Glean. The sensitive insights APIs enable organizations to automate the detection of sensitive data and integrate it with downstream processing systems to enhance governance capabilities.

How to access: Please reach out to your account executive team to learn more about sensitive insights APIs and Glean Protect+.

Enable the deletion of data sources from the admin console

Glean provides the ability to delete data sources directly from within the admin console. When a data source is deleted, all of the data is also deleted from Glean indexes.

Highlight text and revise, explain, or summarize content anywhere with the Glean companion for the browser extension

The Glean companion is a floating widget that contextualizes any text the user highlights on their screen, enabling them to instantaneously access company knowledge and insights wherever they work. Users can ask the companion to explain highlighted text, find relevant documents, summarize writing, and more without navigating away from the document or application they are working in.

How to access: Glean companion is accessible by downloading the Glean browser extension. For troubleshooting, please contact your Glean representative.

Glean action to send a message to a Slack channel

New action to post messages and updates to Slack channels from Agents, enhancing collaboration by automating communications and notifications

Setup and manage web search under actions in the admin console

Glean enables web search to be setup and managed in the admin console under actions. You can now enable Microsoft Bing actions, Google Gemini actions, and OpenAI actions.

Execute SQL queries directly against Databricks from within Glean

Glean’s Databricks action pack now supports executing SQL directly against your warehouse.

Send a direct message to Slack using Glean actions

New action to send a direct message on Slack is helpful for sharing daily reports, preparing for upcoming meetings, or staying on top of changing sales metrics.

Adds a row to a Google sheet using Glean actions

Add new rows to Google Sheets using Glean actions, making it easier to automate and consolidate data in spreadsheets.

Glean supports Jira JQL actions

Glean is introducing a new functionality that allows users to query Jira data using JQL and/or natural language queries.

Glean supports Salesforce SOQL actions

Glean is introducing a new functionality that allows users to query Salesforce data using SOQL and/or natural language queries.

Glean supports Snowflake Cortex for SQL actions

Glean is introducing a new functionality to enable users to query Snowflake data using SQL and/or natural language queries. These queries will be powered by the Snowflake SQL API and the Cortex Analyst API. Glean users will be able to ask follow up questions to combine Snowflake data with their other connected apps and documents.

Glean Agents

Glean Agents is our new platform for building conversational and task based agents. This features a visual agent builder with advanced capabilities like branching, response style control, and the ability to choose from large language models from OpenAI, Anthropic, Google, Amazon, and Deepseek. Access agents from where you work – run agents on the Glean website, embed agents in your website, or call agents via an API.

How to access: If you have an existing deployment with prompts or apps, Glean will not enable the agents feature immediately. Instead, Glean will provide a transition period and a migration path for your existing prompts and apps. You can choose to preview or launch agents any time between May 20 and July 15.

Use OpenAI as a web search provider

Glean integrates OpenAI as an additional web search provider.

Use Google Gemini as a web search provider

Glean integrates Google Gemini as a web search provider.

New data source connector for Databricks that indexes AI/BI dashboards

Glean data source connector for Databricks indexes AI/BI dashboards.

New version of the Gmail connector

The Gmail connector now supports both data crawling and indexing as well as data fetching to improve search and assistant quality.

How to access: Gmail can be upgraded to the latest version by going to data sources > Gmail > Enable both data crawling and indexing as well as data fetching.

Support for indexing Workday knowledge base articles

Index public articles from Workday using the new connector, making it easier for HR and IT teams to access and utilize knowledge base articles within Glean.

New version of the Outlook connector

The Outlook connector now supports both data crawling and indexing as well as data fetching to improve search and assistant quality.

How to access: Outlook connector can be upgraded to the latest version by going to data sources > Gmail > Enable both data crawling and indexing as well as data fetching.

Glean supports Databricks Genie for SQL actions

Glean is introducing new functionality to enable users to query their Databricks workspaces using natural language queries. The natural language queries are powered by the Databricks Genie API. The SQL queries are powered by the Execute SQL API.

Workday connector for people data

Index People data from Workday to Glean via people data connector.

Support for Nova Pro 1.0 in the model hub

Glean now supports Nova Pro 1.0 which is hosted on Amazon Bedrock as part of its model hub. Customers can select Nova on a per-agent and per-agent step basis.

Support for Deepseek-R1 in the model hub

Glean supports Deepseek-R1 hosted on Amazon Bedrock. Deepseek-R1 is available in the model hub to be used as the model for an agent or agentic workflow step.

Weekly and continuous sensitive insights dashboards in Glean Protect

Glean sensitive insights continuously scans and flags overshared sensitive content across your applications. Create customizable policies, run continuous reports, and auto-hide sensitive data from a centralized dashboard in Glean.

How to access: Please reach out to your account team to learn more about sensitive insights (ie: dashboards) and Glean Protect.

Personal activity action added to Glean Agents

New action for Glean Agents that allows for the retrieval of all personal activities. This action can be used for self-assessments or to show strategic impact over a period of time.

Agents API

With Agent API, you can programmatically list, retrieve details, and run agents your team creates in Glean.

How to access: To use the Agent API, you must have access to Glean’s Client API. For details, see the Glean developer experience.

Search nested content within Notion

Notion arranges information in ‘Blocks’ and allows users to create ‘Toggles’ which are sub-blocks within these blocks. Notion users can create many toggles inside a block which Glean was previously unable to retrieve. This feature recursively retrieves information from child blocks in Notion and deepens Glean’s integration with Notion.

Revamped overview and department level Insights (GCP Only)

The Insights page will now include a new “Overview” tab replacing the Teammates tab; it features key metrics including usage across search and chat as well as data source usage. A new tab for “departments” will provide a table view of each department’s usage, enabling you to understand the departments driving adoption and those at risk. This will only be available to GCP customers as part of this release.

New Azure DevOps connector

Glean has developed a connector for Azure DevOps that enables users to search and query Azure wikis from within Glean.

Improvements to the setup of Salesforce objects

We are streamlining the additional objects self serve experience for Salesforce. This should make adding additional objects (standard + custom) to Salesforce a much smoother experience.

Glean browser extension update

Glean has updated its browser extension sidebar (Command + J on Mac, Alt + J on Windows) with a new tab called Discover, which intelligently analyzes document content to generate personalized prompts that help users quickly understand, explore, and make informed decisions without leaving their workflow.

Access Glean from within the Zoom workspace via Zoom Custom AI Companion

Customers with both Zoom and Glean subscriptions can now access their organization’s knowledge directly within Zoom Workplace applications via the Zoom Custom AI Companion paid add-on. This enables users to search across 100+ enterprise data sources indexed by Glean throughout their Zoom Workplace, while maintaining all existing security permissions and data ownership.

How to access: For setup instructions, please select the Zoom Support article below.

Create automated daily summaries in Slack of key channels

Glean in Slack now lets you receive daily summaries of slack channels, delivered at a time you choose.

How to access: This will be enabled by default for Glean LLM key customers.

Glean can respond to workflow-based messages in Slack

In addition to channels and threads, Glean will respond in workflow-based messages in Slack.

How to access: Enable this feature in Slack channels by running /glean configure.

Glean is releasing updates to improve citation quality

Glean is introducing a new approach to citation generation using LLM-based citations. With this method, the same LLM that generates the response also provides citations for the claims it makes—ensuring that references are directly tied to the information presented. This update is designed to improve citation accuracy, clarity, and trustworthiness by aligning responses more closely with their original sources.

Analyze multiple files in Glean Assistant

Glean supports the analysis of multiple-file uploads of CSV, XLS/XLSX, and JSON formats in Assistant, 5 files up to 64MB each.

Ability to enable new actions in existing action packs

New out of the box actions provided by Glean will now appear in existing action packs where relevant, and the admin will be prompted to enable these newly available actions.

Glean key on Amazon Bedrock

Glean Key for Amazon Bedrock enables AWS customers to achieve consistent performance without the need to manage models directly. Additionally, it ensures enterprise data security by keeping models hosted within AWS.

Support for indexing Confluence attachments

Glean will support the ability to index Confluence attachments.

Separate data source setup and management of Microsoft SharePoint and OneDrive

Glean separates data source setup and management of Microsoft OneDrive and SharePoint to allow for finer-grained controls, easier troubleshooting, and ability to manage each data source individually.

New Hubspot connector

Glean’s Hubspot connector enables sales and services teams can get the insight to progress deals forward and resolve customer support issues. Glean indexes the following Hubspot content: contacts, deals, companies, tickets.

How to access: Please setup HubSpot via Glean admin console > data sources.

Improvements to the setup of Salesforce objects

We are streamlining the additional objects self serve experience for Salesforce. This should make adding additional objects (standard + custom) to Salesforce a much smoother experience.

Fast execution query path for information-seeking queries

Glean establishes an efficient execution pathway for straightforward information-seeking queries, while also providing an advanced planning mechanism to handle more complex queries effectively. With this architectural change, we expect information-seeking queries to experience lower latency.

Analyze multiple files in Glean Assistant

Glean supports the analysis of multiple-file uploads of CSV, XLS/XLSX, and JSON formats in Assistant, 5 files up to 64MB each.

Voice-to-text support is available for Glean mobile users on Android

Go hands-free with voice-to-text support for Android devices. The new speech-to-text feature lets you dictate questions and messages—no typing is required.