Start with however long you have
Two of these three need nothing but a browser.
Watch it work on your own words
Walk into the fictional shop, tell its support desk something went wrong, and watch a live model categorise it, rank its urgency, and decide whether a person needs to see it.
Start from zero
Make one small Claude API request, change it, and learn what a model, message, response, and token actually are before building anything bigger.
Build the whole service
From your first API call to an eval harness with an LLM judge, against one coherent codebase you can read end to end. Solutions included for every lab.
Or let me walk you through it
Two minutes: the queue, the ticket that sat for three days, and what you build to catch it.
Four routes, four capabilities
One domain. Each route introduces exactly one new idea and builds on the one before it.
POST /v1/triageThe model's output contract is your type system
POST /v1/resolveClaude queries your systems and shows its work
POST /v1/draftToken-by-token delivery over SSE, with real cost accounting
POST /v1/estimateKnow the bill before you pay it
Poke at it before you commit to it
Eight interactive tools, all of them running in the page. Three worth starting with:
The labs
Roughly four hours end to end. Solutions included. You need Node 20 or newer, an API key with billing enabled, and about $2–4 of tokens for the whole sequence.