-
Take action across your tools with MCP – March 2026 Drop – Day 2
Today’s drop lets your AI Assistants and Agents do more than answer questions — they can now take action across your apps, right inside Glean. MCP inside Glean connects to hundreds of servers and third-party tools, so your Agents can create issues, pull in external data, or trigger workflows — without leaving the platform.…
-
Bring Glean into ChatGPT & Claude – March 2026 Drop – Day 1
Many teams already work in tools like ChatGPT and Claude. But those chats don’t know your company like your docs, tickets, emails, and decisions. That means copy-pasting, re-explaining, and hunting for context. Not anymore. With Glean’s MCP server, your AI assistants can now tap directly into your company knowledge. Ask…
-
Create an Agent directly from Chat
It would be great if you can take a chat/assistant and convert it to an agent within the chat interface through the natural language agent builder. Have the LLM reveiw the chat and the output results and suggest an agent workflow based on that interaction.
-
Pull in more Google Calendar metadata
Hi, the Google Calendar API gives rich metadata that I think users would find helpful to pull in. For example, eventType (Default, Birthday, focusTime, outOfOffice, etc) or colorId (people use colors frequently to categorize events). Those type of metadata would help me more effectively use the Meeting Lookup tool and do…
-
Interactive Clarification Panels in Glean Assistant
Hey everyone, I've been spending a lot of time inside Glean Assistant lately — building agents, running complex multi-step workflows, and generally pushing it to its limits. Love what we've got. But I keep running into one friction point that I think has a clean solve, and I wanted to throw it out here. The Problem When I…
-
Feature Request: Interactive Buttons (Yes/No and Numbered Selection) in Chat
I am submitting a feature request to enhance the interactivity and efficiency of the Glean Assistant interface by introducing clickable buttons for common responses. Currently, the interaction with Glean is purely text-based. When Glean asks a clarifying question (e.g., "Would you like me to investigate further?") or…
-
Glean for Marketing Operations and Automation
We have started to use Glean at our company. I am looking for some inspiration on how Glean can be used in Marketing. I am a member of marketing ops team and would be interested to look at some agents which Glean themselves or other companies are using for Marketing/marketing ops productivity.
-
Why GA Chats Die — And Why Nobody Tells You?
Dear Team, Kindly review the problem statement and the possible resolution to address it. Why GA Chats Die — And Why Nobody Tells You The Technical "Why" Aspect What Happens Why It's Not Surfaced to You Context Window Limit LLMs have a hard token ceiling — GPT-5.1 (current GA primary model) caps at 256K tokens, Claude…
-
Feature Request: Option to Prevent Automatic Image Attachment when Pasting from MS Office
Problem Statement When users copy content from Microsoft Office applications (such as Excel cells or PowerPoint objects), these applications often place multiple formats onto the clipboard simultaneously: the plain text/values and a graphical capture (image) of the selected area. Currently, Glean Assistant automatically…
-
Improve Chat Sharing Feature
At present, when you share a Chat you must explicitly share the link. The following features would greatly improve the usability of the existing Share feature. People Access - Add a feature to send the link via email. The notice will let users and groups know that something was shared. Chat History - Have a dedicated…
-
[Feature Request] - Chat with your Collection - Chat Assistant
Issue Description Glean has a collection feature in which users can create a collection of sources like files, folders, documents, URLs. Currently this Collection cannot be used as Knowledge source in Chat Assistant. E.g. you can try copy or browse the recent collection and try link it in Chat interface but Response is…
-
Show which model Assistant used when set to Auto
Overview When Assistant is set to Auto, users do not have visibility into which model was actually used for the response. That makes it harder to understand differences in response quality, tone, and speed, and also makes it harder to give useful feedback. Proposed Behavior A simple option would be to show a small label…
