Coming soon
For developers building with AI
6 modules · hands-on

Level up your career or business with provable AI engineering skills.

A full course, hands-on builds and a whole kit of tools for developers who want AI agents that hold up with real users, not just in demos. It isn't ready yet. Get on the list and you'll be first through the door.

Join the course waitlist See the curriculum

support-agent.eval.tsevals/

1// "It worked when I tried it" isn't proof.23const results = await runEvals(agent, {4  dataset: "real-tickets.jsonl",5  graders: [correctness, toolUse, tone],6  trials: 3,7});89expect(results.passRate).toBeGreaterThan(0.95);10expect(results.p95Latency).toBeLessThan(2_000);

correctness482/50096.4%

tool use497/50099.4%

tone491/50098.2%

p95 latency1.42s

4 passed · 1,500 runs · ready to ship

01What you'll learn

The whole agent stack, end to end

Whether you've never shipped an LLM feature or you're already running agents in production, there's a next step for you. It's all hands-on: you write the code, run it, and break it.

01Module

Foundations

Prompting, tool calling and structured output: the building blocks every agent is made of, and how they fail.

02Module

Agent design

Agent loops, planning, multi-agent setups, and knowing when a simple workflow beats an agent.

03Module

Tools & integrations

Designing tools a model can use well, connecting APIs and MCP servers, and keeping permissions tight.

04Module

Context & memory

Retrieval, context engineering and memory that holds up as conversations and codebases grow.

05Module

Evals & reliability

Testing non-deterministic systems: evals, guardrails, tracing, and catching regressions before users do.

06Module

Shipping to production

Latency, cost, security and deployment: everything between a working prototype and a product.

02The course waitlist

Get in before the doors open

Drop your email to save your spot. If you've got a minute, tell me a little about yourself and what you want to build. I read every one.

First access the moment the course opens
Behind-the-scenes looks at what's being built
A say in what gets covered: your answers shape it