AI Agent

A software system that uses an LLM to perceive context, decide actions, invoke tools, and complete tasks toward a goal.

An AI agent is a system built around a large language model that reads a goal, plans steps to reach it, invokes external tools (APIs, search, code execution), observes results, and iterates until the goal is met or it fails. The defining trait is decision autonomy: the agent chooses the next action rather than executing a fixed script.

In production, “AI agent” covers a wide spectrum — from a tightly scoped customer support agent answering tickets to a long-horizon coding agent committing pull requests. The boundary with classical workflow automation is fuzzy. Anthropic’s Building effective agents distinguishes workflows (predefined sequences) from agents (the LLM picks its own path). Both are valid; the choice is operational.