Glossary · Phase 1 · Building with LLMs
Agent loop
The repeating cycle of an agent: think, call a tool, read the result, decide again.
Learn it properly
The agent loop · Model → tool → result → model, until the task is done. About 30 minutes.
Other terms from the same lesson
- agent: A model in a loop that decides what to do next, uses tools, looks at the results, and repeats until the job is done.
- decorator: A line starting with @ just above a function that adds extra behavior to it, such as @app.post("/api/answer").
- side effect: Anything a tool does besides giving back an answer, such as sending an email or changing a record. Asking again can't undo it.