Tutorials
Learn Jev by building with it
Read them in order and you will go from a first typed decision to a confidence-gated production path. Read one in the middle and it will still stand on its own — every page cites its sources and flags what is TypeSafe's claim rather than a measured fact.
Foundations
3Your first Jev call
Get a key, send one request, and read a typed answer back — in cURL, Python and TypeScript.
ReadNoul, Choice and Score
Jev has exactly three question types. Picking the wrong one is the most common early mistake — here is how to tell them apart.
ReadDesigning state Jev can actually use
State is not a prompt. Shape it like a record you'd hand an expert, filter it in code first, and name the parts your questions point at.
ReadPatterns
7Ask every question at once
Questions run in parallel and output tokens are free, so asking something you might not need is close to free. Branch in code afterwards.
ReadConfidence-gated routing
The answer tells you what. Confidence tells you whether you're allowed to act on it without asking anyone.
ReadComposite scoring: move the weights into code
Stop asking one model one big question. Ask several small ones and own the weighting yourself.
ReadAsk for features, not answers
The one lesson every practitioner reached independently in launch week: Jev is a bad judge and an excellent sensor.
ReadThe cascade: Jev in front of an LLM
Let a fast, cheap decision decide who handles the work — plain code, a specialist model, or a person.
ReadBuilding an agent harness
Tool selection, dangerous-action gates and loop detection — the control layer that every coding agent already has, and nobody could build cheaply until now.
ReadReal-time loops: the Doom lesson
Ten decisions a second for about $7 an hour. What that unlocks, what it does not, and the discipline a control loop demands.
ReadReliability
3Read this before you ship
The nine documented ways jev-1.13 gets things wrong, and what to do instead of each one.
ReadWhat the numbers actually say
193.6× faster, 445× cheaper, 100×, 200×, 40×, 20× — six multipliers from one vendor, and what independent testers measured instead.
ReadShipping it
Errors, retries, rate limits, version pinning and the request ID you will wish you had logged.
Read