AI agent

A system in which a model decides its own next steps, calling tools in a loop until a task is done, rather than following a path your code fixed.

In more detail

Anthropic defines agents as systems where the model dynamically directs its own process and tool use, as opposed to workflows. They suit open-ended tasks whose steps cannot be known in advance, and they cost more, are harder to test and need budgets, permissions and human approval for risky actions.

Related terms

Taught in

References

Certification courses