Tutorials
Each volume is 12 animated steps with runnable labs, ending in a procedure: what to build, in what order, and when to stop.
The tutorials open when sales start. Until then, the free concepts are open to read.
Everything below in one purchase. Single volumes you already bought are credited.
Which of these is happening to you?
Each volume starts from a real failure. Choose the closest one.
Deciding what travels with every request, and what gets looked up.
12 steps · labs
Building a search that follows links instead of matching words.
12 steps · labs
Building the code around an agent, and measuring what each layer buys.
12 steps · labs
Choosing how to arrange an agent system: one agent, a pipeline, a router, or more.
12 steps · labs
What to retrieve, how to find it, how much to hand over, and when to return nothing.
12 steps · labs
The go or no-go before anything is built: what a wrong answer costs, what would do the job without a model, and what working has to mean on day one.
12 steps · labs
When to give an agent another attempt, and when to add another agent.
12 steps · labs
When an agent should remember, and when it should look it up again.
12 steps · labs
When an agent writes its own rules, and how to tell if the work got better.
12 steps · labs
What users see when the model provider is slow, limited or down, and which of the usual fixes make it worse.
12 steps · labs
How to tell whether your eval's number means anything.
12 steps · labs
A guardrail’s value is set by where it sits, not by how good it is.
12 steps · labs
Which cost reductions cannot cost you an answer, in what order, and when to stop.
12 steps · labs
What to record, how to release a change safely, how you notice it went wrong, and how you find out why.
12 steps · labs
Which model is good enough for your task, how to prove it, what it really costs, and how to survive the next model change.
12 steps · labs