AI agent

An AI agent is a system that pursues a goal across multiple steps, choosing actions and using tools rather than returning a single response. Where a model answers a question, an agent decides what to do next, acts on that decision, observes the result, and continues until the goal is met or it stops.

The practical difference is autonomy over a sequence. Asking a model to draft an email produces text. Asking an agent to resolve a support ticket may involve reading the account record, checking a policy, drafting a reply, and routing it for approval.

That capability is also what makes agents a governance problem distinct from models. Each individual step may be unremarkable while the sequence is consequential, so controls have to evaluate the sequence rather than the steps.