Read the first two lessons free.
These two lessons together explain how an AI agent actually reasons, why context windows and tool calls matter, and the prompt-to-response loop that changes how you use AI once you see it. Read them at your own pace, plus an optional activity at the end of Lesson 1.1.
What is an AI agent, really?
The four parts — model, loop, tools, state — and how they combine to turn a chatbot into something that can do real work. Chatbot vs. agent through a concrete Dust Bowl research example.
How the model thinks (and why confidence ≠ correctness).
Next-token prediction under the hood, why fluent output can still be wrong, and the practical implications for how you direct an agent. Lays the groundwork for trace-reading in Lesson 1.3.
The full course is 10 modules, ~120–150 student hours, one credit's worth of work. See pricing → See the full curriculum →
We don't run a newsletter or auto-enroll anyone in email sequences. The only time we'll email you is for sign-in links and receipts after you create an account.