An agent is an LLM wrecking its environment in a loop

5th June 2025

Solomon Hykes just presented the best definition of an AI agent I've seen yet, on stage at the AI Engineer World's Fair:

Diagram showing AI agent interaction loop on pink background. Title reads "An agent is an LLM wrecking its environment in a loop." Flow shows: Human connects to LLM Call via dotted arrow, LLM Call connects to Environment via "Action" arrow, Environment connects back to LLM Call via "Feedback" arrow, and LLM Call connects down to "Stop" box via dotted arrow.

An AI agent is an LLM wrecking its environment in a loop.

I collect AI agent definitions and I really like this how this one combines the currently popular "tools in a loop" one (see Anthropic) with the classic academic definition that I think dates back to at least the 90s:

An agent is something that acts in an environment; it does something. Agents include worms, dogs, thermostats, airplanes, robots, humans, companies, and countries.

Posted 5th June 2025 at 5:03 pm

Simon Willison’s Weblog

Recent articles

Monthly briefing