Skip to content
Agent YAP

What is it?

Agent

In this material, an AI agent is a system that uses a large language model (LLM) as its reasoning engine to decide what to do next, usually by calling tools in a loop. The key difference from a plain chatbot is that an agent does not just answer once. It can take an action, look at the result, decide on the next action, and keep going until the task is done. A good mental model: a chatbot answers a question, while an agent works on a task.

From the AI agent glossary

As the Planning and Reasoning glossary puts it

An agent is an AI system that pursues a goal through a series of actions, rather than producing a single response and stopping. An agent might search the web, read the results, run some code, check a file, and only then answer, looping through steps as needed.

The ReAct loop of Chapter 2 (Thought, Action, Observation) is the foundational pattern behind essentially every modern agent. When people talk about AI that can "use a computer" or "complete tasks," they mean agents built on this kind of loop.

See it in the Planning and Reasoning glossary

Where Agent is explained

  1. Deep Research Agents and How They Are TrainedBuilding Coding Agents and Harnesses · A taxonomy worth knowing
  2. What Is an Agent Harness?Building Coding Agents and Harnesses · Real code: pi plugs a coding harness into a generic loop
  3. The Taxonomy of Agentic RAG SystemsAgentic RAG · Multi-agent agentic RAG
  4. The Case For Multi-Agent: Anthropic's Research SystemMulti-Agent Systems · Prompt engineering becomes the main control lever
  5. The Agent LoopBuilding Coding Agents and Harnesses · Real code: pi's two loops, and how a user steers mid-turn

Every term, A to Z