What Is an AI Agent? A Rigorous Definition
Moving beyond the hype to a precise, useful definition
TL;DR
An AI agent is a system that uses an LLM to perceive, reason, plan, and act autonomously. Unlike chatbots, agents maintain goals across multiple steps, use tools, and adapt their approach based on feedback from the environment.
Introduction
The term 'AI agent' is used everywhere in 2026, but rarely with precision. This primer provides a rigorous definition that separates genuine agents from chatbots with extra steps.
The Three Properties of Agency
A true AI agent exhibits three properties: autonomy (it decides what to do next), tool use (it can interact with external systems), and goal persistence (it maintains objectives across multiple reasoning steps).
Agents vs. Chatbots
A chatbot responds to messages. An agent pursues goals. The distinction matters because it determines architecture, evaluation, and trust boundaries.