Foundation track of the AI series. Adds the primitives of working with LLMs: calling a model, prompt principles, the four core task verbs, structured (JSON) output, conversation history, system prompts, token cost, refusals, batch, helpers, retry on bad output, self-consistency, cost-aware batching. Each lesson demonstrates ONE primitive on the smallest possible input — no products, no inboxes, no knowledge bots. 30 lessons across 4 weeks. Requires Python Foundations (or equivalent fluency). Max tier (Sandbox + OpenRouter).
Week 1
Week 2
Week 3
Week 4
