Independent · unofficial · English only
Developer intelligence for Jev
jev.pro explains TypeSafe AI's Jev System One model for working engineers: what it is, which primitives it exposes, how to call it, and where the public docs already draw hard limits.
This is not a TypeSafe property. We rewrite public documentation into durable, linkable English pages and keep a factory ready for a larger programmatic inventory. Primary source of truth:https://docs.typesafe.ai.
Disclaimer. This is an independent unofficial site and is not affiliated with TypeSafe AI; official documentation is available at https://docs.typesafe.ai.
Researched seed pages: 55. Inventory pages:500. Factory:npm run generate:inventory readscontent/inventory/urls-500.jsonl.
Explainers
What Jev is, what System One means, and how the model is meant to be used. 30 pages.
Primitives
Choice, Score, Noul, confidence, and how questions compose in code. 8 pages.
Access
Waitlist, console keys, Vercel AI Gateway, pricing, and rate limits. 16 pages.
API
Endpoint, request shape, SDKs, aliases, and the first working call. 49 pages.
Use cases
Support triage, routing, guardrails, and other documented workflows. 288 pages.
Comparisons
Jev versus structured outputs, classifiers, and known jagged edges. 64 pages.
Open
Independent reproductions and public eval surfaces — clearly labeled. 52 pages.
Glossary
Short definitions for the terms that show up in Jev requests and answers. 28 pages.
Channels
How teams typically deliver a System One decision — REST, queues, review — around the official API. 10 pages.
Errors
Documented HTTP failures and application-level failure classes you handle in code. 10 pages.