An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
A chatbot answers and stops. An agent gets a goal ("fix this bug", "book the flight"), picks an action, looks at what happened, and keeps going until the job is done or it gives up. The loop is what makes it an agent.
Actions usually mean tools: running code, editing files, calling APIs, browsing. Coding agents like Claude Code are the ones this site tracks most — they edit real repositories, run the tests, and iterate on failures the way a junior engineer would.