Learning Sets
Pick a skill to practice. Each set holds every problem on that topic, easiest first.
- AI Basics
Where AI fits into existing work: whether a task should use AI at all, which kind of AI suits it, and when it is safe to use.
No problems yet - Cost Control
Spend less per request without losing quality: what to send, which model to call, and what to stop paying for.
1 problem - Token and Cache Economics
Tokens are what models read and bill by. Learn to count them, price them, and reuse them with prompt caching.
1 problem - Memory
What a system remembers between turns and sessions, and how to recall the right facts cheaply.
No problems yet - Context Engineering
Choose what goes into the model's input, in what order, and what to leave out.
No problems yet - Prompt Engineering
Write instructions that get the output you need, reliably.
No problems yet - Model Selection
Match each step to the right model: large and capable, or small and cheap, and know when each pays off.
No problems yet - Evals and Regression Testing
Test AI output automatically, and catch a change that makes something worse before it ships.
No problems yet