The Handbook
Eleven illustrated sections on who decides the next step at run time — writing code, prompts, context, loops, graphs, harnesses, evaluation and security. Twenty diagrams you can click through.
Read the handbook→Every program is a list of steps. The only question is who picks them.
A complete course on building systems that use AI — written for people who are new to software engineering. Three parts, about four hours, and you finish having built a working agent with an eval suite that scores it.
No account. No ads. Anonymous page counts only. MIT licensed.
So what is agentic engineering?
Every program is a list of steps. The only question is who chooses the next one, and when.
You write the steps in advance. The computer follows them exactly, every time — fast, predictable, and blind to anything you did not think of.
You describe the goal and let the model choose the next step while the program is running. Flexible, surprising, and it has to be checked.
Almost every real system is a mixture of the two. Choosing the mixture is the whole job — and it is what you will practise here.
Your learning path
Each part asks a little more of you than the last. Start at the top.
The Lab
Four hands-on stages in this browser. Make a real model call, extend a rule-based till until it breaks, write your own prompt, then score it against twenty real cases and watch the number move.
Open the lab→Build an Agent
Five more stages, on your own machine. The agent loop written by hand, tools that fail on purpose, a permission gate, a reviewer that cannot be skipped, and an email that tries to give your agent orders.
↗ Opens on GitHub. You will need a computer and a code editor.
Open the course↗What you will be able to do
Tell which problems need a model and which do not
The most valuable judgement in the field, and the cheapest to get wrong.
Write a prompt and prove it works
Not by reading its answers — by scoring it against cases and watching a number.
Build an agent loop that survives failure
Tools break. The loop has to read the error and adapt, not crash.
Put a fence around what a model can do
Permission gates, mandatory review steps, and limits enforced in code.
Who this is for
Complete beginners
Parts 1 and 2 assume no programming at all.
Students and self-learners
A full curriculum you can finish in an afternoon.
Teachers
A 90-minute lesson plan, free to reuse and translate.
Where you are
Nothing yet. Your progress is saved in this browser only — no account, nothing sent anywhere.
Common questions
Is it really free?
Yes. The whole course is MIT licensed and there is no account, no email capture and no advertising. The only thing measured is an anonymous page-view count, with no cookies and no profile of you. Parts 2 and 3 call a model, so you bring your own API key — the entire course costs a few cents of tokens.
Do I need to know how to program?
Not for Parts 1 and 2. Part 3 assumes you can read and write basic TypeScript — functions, objects, a for loop, await. If you cannot yet, do Parts 1 and 2 and come back. A Python version of Part 3 is also kept in the repository.
Which AI model does it use?
DeepSeek or Anthropic's Claude, your choice. The code is written so that not one line of any exercise changes between them, which is itself one of the lessons.
Is my API key safe?
Your key is held in the browser tab only and is erased when you close it. It is sent to the model provider and nowhere else. This site has no server, so there is nowhere for it to go — and the page-view counter never sees it.