What makes something an agent rather than a chatbot?

The loop. A chatbot answers once. An agent decides on an action, runs a tool, reads the result, and decides again, repeating until it judges the goal met. The model is the same. The harness around it is what is new.

What actually goes wrong in that loop?

It repeats an action forever, acts on a bad intermediate result, or misreads a tool's output and confidently continues. Because each step feeds the next, an early mistake compounds. Real systems cap the number of steps and put approval gates on anything irreversible.

Do agents need a bigger model?

They need a more reliable one. Small quality gaps that are invisible in a single answer become failures over ten chained steps, because the per-step success rates multiply. Tool-use reliability matters more here than raw knowledge.

Plain-language explainer

AI agents, explained

What makes an AI agent different from a chatbot?

An agent is a language model placed inside a loop that can take actions. A chatbot writes a reply and stops. An agent proposes a tool call, a harness runs it, the result comes back into the context, and the model decides the next step, repeating until the task is done. The model still only predicts text. The power comes from the loop around it: read a file, run a search, call an API, check the result, try again. That loop is what turns a predictor into something that gets work done.

Last reviewed July 25, 2026

Reading is the slow way. Start with a free lesson you can operate right now.

Start free: The harness: the loop, made real →

Free, no code, no signup.

Then go deeper: Tools & agents: the loop around a frozen model Locked

What people get wrong

The model itself reaches out and touches your systems. A separate harness runs the tools; the model only proposes calls.
An agent is just a longer prompt. The difference is the action loop and tool results re-entering context.
More autonomy is always better. Useful agents verify their work and ask for approval on risky steps.

Where you see it in real products

Coding agents read code, run tests, and iterate until they pass.
Research agents search, read, and compile findings across many steps.
Ops assistants call internal APIs to look things up and take actions.

Common questions

What makes something an agent rather than a chatbot?: The loop. A chatbot answers once. An agent decides on an action, runs a tool, reads the result, and decides again, repeating until it judges the goal met. The model is the same. The harness around it is what is new.
What actually goes wrong in that loop?: It repeats an action forever, acts on a bad intermediate result, or misreads a tool's output and confidently continues. Because each step feeds the next, an early mistake compounds. Real systems cap the number of steps and put approval gates on anything irreversible.
Do agents need a bigger model?: They need a more reliable one. Small quality gaps that are invisible in a single answer become failures over ten chained steps, because the per-step success rates multiply. Tool-use reliability matters more here than raw knowledge.

Related explainers

RAG Context engineering Computer-use agents AI coding agents MCP Agent vs chatbot

One idea at a time, in your inbox

New lessons and explainers, written the way these pages are. Now and then, not daily, and never a sales sequence.

We email you a confirmation link first. Unsubscribe in one click, any time. Privacy.

Part of See How AI Works, a free interactive course, where you learn how modern AI works by operating it, not watching videos.