Category

Giving AI the ability to act

A language model on its own can only write text. The agent layer turns that text into action: models that call tools, follow multi-step workflows, coordinate with other agents, remember what happened last time, and operate real software. These entries explain the agent loop, the protocols that connect models to the outside world, and the guardrails and human checkpoints that keep autonomy honest.

Entries in this category

Where this layer fits

Agents sit on top of everything else in the stack. They are built from core concepts like context windows and inference, they reach into the retrieval layer when they need your data, and because they act on their own, evals are how you find out whether they can be trusted.

Not sure where to start? AI agents is the entry the rest of this category builds on. Or browse everything at once in the A-Z index.