Course catalog

Browse all published courses.

Lesson 1 of every course is free. One whole course is free. One payment of $10 opens all 19 courses in the catalogue today. What's included →

3 courses in Build with AI

The Prompting Playbook: Debug a Production Prompt

Your production prompt worked, then you moved to a new model and the test cases started failing. This is the repair method, in order. Build a small eval suite of control, edge and capability-boundary cases, so you can tell a real improvement from a feeling. Strip the pasted-website cruft and the untrue persona. Carve the prompt into tagged sections so role, policy, guidelines and tone stop competing. Add an output contract and enforce it in the harness with a stop sequence. Then isolate one failing case at a time and find the instruction that made the wrong answer the compliant one. Worked end to end on a messy customer-support prompt for a fictional telco, then run on a prompt of your own. Based on “The Prompting Playbook” by Margot van Laar, Code with Claude.

7 lessons

Agents That Remember: Context Engineering & Memory

Build agents that remember. An agent's memory is just plain markdown files it reads, searches and updates for itself. Set that up and the agent gets better at your work every time it runs. You will keep deep detail out of the context window with progressive disclosure. You will stop two agents overwriting each other, using hashing and versioning. And you will decide what stays read-only and what an agent may rewrite. Predict, drag and decide your way through.

7 lessons

Write the Loops: Your Job After AI Writes the Code

AI writes the code. What is left is the job around it: framing the problem, steering the agent, and validating what it produces. You will also find where the work piles up once coding stops being the slow part. Predict, drag and decide your way through nine short lessons. For engineers and the people who manage them.

9 lessons