Whitepaper
Glean Agents
Agents use AI to understand tasks and take action on behalf of users — from answering questions and retrieving information to executing work autonomously. This technical white paper explores how agents go beyond simple LLM calls by integrating with tools, workflows, and memory to reliably perform tasks in the enterprise. You’ll learn how Glean uses search to route queries to the right workflows, evaluates agent performance using LLM-based techniques, and scales adoption by designing around common query patterns.
Download this whitepaper for to learn about Glean designs agents including:
- Personalization: How Glean tailors the agent experience by searching across a library of “golden” workflows — created by both the system and your organization
- Query classes: The design of common enterprise query types — like data analysis (“find all Jira tickets assigned to me”), progress summarization (“what have I worked on this week?”), and request handling (“request a new laptop”).
- LLM judges: How we evaluate agent performance at scale using task-specific LLM judges and real-world eval sets for each query class.
Download this whitepaper for to learn about Glean designs agents including:
- Personalization: How Glean tailors the agent experience by searching across a library of “golden” workflows — created by both the system and your organization
- Query classes: The design of common enterprise query types — like data analysis (“find all Jira tickets assigned to me”), progress summarization (“what have I worked on this week?”), and request handling (“request a new laptop”).
- LLM judges: How we evaluate agent performance at scale using task-specific LLM judges and real-world eval sets for each query class.