Context Engineering

Token budgets, prompt caching and what silently breaks it, pruning versus summarising, memory between sessions, and keeping tool output out of the window.

10 lessons · about 91 minutes

What you'll go through

• 01Everything it knows this turn, you paid for9 min
• 02Estimating them is how the bill surprises you9 min
• 03One timestamp at the top, and the cache is gone9 min
• 04It cached yesterday and it does not today9 min
• 05Writing to the cache costs more than missing it9 min
• 06Turn forty is expensive because of turn three9 min
• 07Two ways to forget, and they lose different things9 min
• 08The agent that learns nothing between Mondays9 min
• 09The tool returned 40,000 rows and you needed three9 min
• 10Designing for turn one hundred10 min

Included in this pack

AI Agents — Tool design, context and cost, and how to evaluate an agent without fooling yourself. Three courses, 30 lessons.

Also in this pack

Agent Tools

The agent loop, tool descriptions and schemas, error handling, parallel calls, and how to design a tool surface you can still say no to.

10 lessons · ~86 min$19.90

Evaluating AI Agents

Building a test set, deterministic checks before model judges, rubrics that discriminate, measuring the trajectory, and cost and latency as results.

10 lessons · ~92 min$19.90