What an AI agent actually is
An AI agent is software that does four things in a loop: it perceives a situation, decides what to do, acts on that decision, and then looks again and adjusts. That loop is the whole definition, and it is what sets an agent apart from two things people mix it up with.
- Automation is a fixed script. A macro or a scheduled job repeats the same steps in the same order. It is fast and reliable, but it cannot adapt — change the situation and it does the wrong thing confidently, or breaks.
- A chatbot only produces text. You ask, it answers. However good the answer, nothing has happened in the world: no form filled, no order placed, no system touched.
An agent sits above both. It can talk like a chatbot and follow steps like automation, but the defining trait is that it takes actions in real systems and adapts to what it sees as it goes.
The one distinction to keep
If you remember nothing else: a chatbot talks, automation repeats, and an agent acts and adapts toward a goal you set. A chatbot that can also look things up, fill a form, and change course when the first attempt fails has stopped being a chatbot — it has become an agent.
Everything else you will hear about agents — the model, the context window, memory, tools, MCP — is machinery underneath that single loop. This course walks it one plain layer at a time.
See it in kestrel
Kestrel is that loop pointed at the markets — an agent that perceives a session and acts on it. Watch one run on a generic instrument, no signup, no card:
npx kestrel.markets sim fomc-rate-decision-whipsawIt prints a certified proof URL you can recompute yourself. Drop the kestrel.markets MCP server into your client and the capability is there next session — no account in between.