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 · about 86 minutes
What you'll go through
- 01The cheapest agent is the one you did not build8 min
- 02An agent is a while loop with an expensive condition8 min
- 03You changed one sentence and it started working9 min
- 04It sent a string where you wanted a date9 min
- 05Forty tools, and it reaches for the wrong one9 min
- 06Returning an error is a conversation, not a failure8 min
- 07It asked for three things at once and you answered one8 min
- 08Give it a shell and you lose the ability to say no9 min
- 09Reversible, and everything else9 min
- 10Designing the set, not the tools9 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
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 · ~91 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