Overview
Agent

Agent Overview

Agents are AI employees that own evaluatable work. Configure each agent with the instructions, playbooks, tools, and memory it needs to complete tasks consistently.

How agents fit together

An agent combines identity, access, deployment paths, and feedback loops. Start by defining what kind of agent it is, then connect the knowledge and systems it needs, choose where it runs, and improve it with real results.

AreaIncludesUse it to
Define its identityPlaybooks, instructions, skillsSet the agent's role, expertise, rules, tone, and operating style.
Connect knowledge and systemsTools, browser, memoryGive the agent access to integrations, external information, and reusable context.
Choose where it runsSurfaces, orchestrations, triggersDecide where people and systems can reach the agent, and what starts its work.
Improve over timeTasks, benchmarks, evaluationsReview real work, test expected behavior, and measure quality as the agent changes.

Start here