For the complete documentation index, see llms.txt. This page is also available as Markdown.

Agent Foundations

What an agent is, and the ideas the builder screens configure.

The Agent Builder documents what you do — each screen, each field, each setting. This section documents what an agent is: the ideas those screens configure, and how they fit together.

Read a concept page when you want to understand why a setting exists and what it trades off. Read the builder page when you want to know what a specific control does and what its default is. Each concept links to the screens that configure it.

The parts of an agent

An agent is a small number of things working together. Every request it handles moves through all of them.

  • Steering & Reasoning — How the agent decides what to do. Instructions, autonomy, how deeply it thinks, and how the planner turns a request into a sequence of actions.

  • Skills & Tools — What the agent can do. The planner can only ever choose from this set.

  • Knowledge & Context — What the agent can read. Retrieval from your documents and data.

  • Memory & Learning — What the agent carries forward, across a conversation and across users.

  • Guardrails & Validation — The automated checks that inspect what goes in and what comes out.

  • Human-in-the-Loop — The points where a person stays in the decision.

  • Protocols — How the agent talks to the outside world, and how your product talks to it.

How they fit together

A request arrives. Guardrails inspect it. Steering decides how to approach it — the planner reads your instructions, consults Memory for what it already knows about this user, and builds a plan. The plan calls Skills, which may retrieve from Knowledge or reach outside through Protocols. Guardrails inspect each step and the final answer. Where you've asked for it, a human approves before the agent commits.

For the end-to-end workflow, see How Agents Work.

Two catalogs, one idea. Several concepts here appear in more than one place in the product — for example, an agent's connectors are configured per-agent in Apps & Services, while the workspace-wide catalog lives in Integrations. Same idea, different altitude. The concept pages say which is which.

Last updated