Study
Agentic AI · What is an agent
An LLM agent is a loop: the model decides an action, a tool runs it, the result goes back to the model, until it decides it's done; the loop written in plain Python with a scripted policy.
- A chatbot answers once; an agent loops: decide, act, observe, repeat, until a stop condition.
- The loop needs a step limit, because a model that never says "done" would otherwise run forever.