QA / Test Engineer
3 courses
ยท ~12 hoursยท 2 certifications available
phase 1 โ Understand tool calling
Learn how AI test tools interact with your codebase.
AI test tools use tool calling to interact with your codebase. Understanding this mechanism is how you evaluate and configure them.
4 sections
ยท 10 lessons
- [ ] Foundations (2 lessons)
- [ ] How Models Decide (2 lessons)
- [ ] Advanced Patterns (3 lessons)
- [ ] Security and Production (3 lessons)
[โ start course]
phase 2 โ Build an agent
Build the same kind of agent that generates and runs tests.
Build the same kind of agent that's being used to generate and run tests. You'll understand its failure modes because you built one.
4 sections
ยท 10 lessons
- [ ] Getting Started (2 lessons)
- [ ] The Conversation Loop (2 lessons)
- [ ] Adding Tools (3 lessons)
- [ ] Making It Real (3 lessons)
certification: Certified AI Agent Builder
[โ start course]
phase 3 โ Master context management
Learn how agents manage context when running test suites.
The sub-agents section covers the test-runner problem directly โ how agents manage context when running test suites.
8 sections
ยท 25 lessons
- [ ] Tokens and Inference (2 lessons)
- [ ] The Real Size of Your Context Window (4 lessons)
- [ ] Anatomy of the Messages Array (5 lessons)
- [ ] Dynamic Allocation: Tool Calling (2 lessons)
- [ ] The Ralph Wiggum Loop (3 lessons)
- [ ] Sub-Agents: Managed Runtimes for AI (3 lessons)
- [ ] Message Passing: The Erlang OTP of AI (3 lessons)
- [ ] Context Management Strategies (3 lessons)
certification: Certified Context Engineer
[โ start course]
key terms
Tool CallingยทAgentยทContext EngineeringยทFinite-State MachineยทSub-AgentยทCorrectness Invariant
related reading
โ Pi: the architecture of an AI coding agent