Closed beta for adults · free
Build agents you can trust
Tool schemas, planning, budgets, observability, sandboxing and evaluation — what separates a demo from something you dare to ship.
Sound familiar?
What you can do afterwards
The goal covers 77 knowledge nodes from the basics up, roughly 64 hours if you start from zero. The diagnostic removes what you already know.
- DBuild a simple agent with one tool
- FAgent architectures
- EBudget, stopping conditions and cost control
- FAgent security: authorisations, the sandbox, confirmation
- EWorking memory: context, summary, window
- FMulti-agent systems
- FEvaluating agents
- FCode agents
- FPlanning and breaking a goal into subgoals
- ETool schemas, validation and error handling
- FMCP and tool protocols
- FObservability for agents
Labs along the way
You write the code in the browser or in a sandbox on the server. Hidden tests decide whether it holds up.
What you get
Diagnosis first
The questions follow the prerequisite chain back from the goal. You skip what you already know.
The shortest path
Only the knowledge you are missing, in the order it builds on itself. The path is recalculated as you learn.
Labs with hidden tests
You write the code. Tests you cannot see decide whether it holds up — not whether it looks right.
Proof of what you can do
Mastery requires several kinds of evidence. The certificate lists them and can be verified.
See where you stand — in ten minutes
No account. You see right away what you already know and where your path would start.
Architecture, planning, observability, safety and evaluation — and the coding agent that gets objective feedback from tests.