What is Jev?
TypeSafe Jev is a System One evaluation model: it returns typed Choice, Score, and Boolean answers with probabilities — not free-form prose.
typesafe-ai/jev returns Choice, Score, and Boolean answers with probabilities. High confidence → auto-suggest; low confidence → human queue. Suggestions only — never money or refunds.
TypeSafe Jev is a System One evaluation model: it returns typed Choice, Score, and Boolean answers with probabilities — not free-form prose.
Choice picks one named option; Score places state on an ordered rubric; Noul (boolean) estimates P(true). Confidence comes from the option distribution.
Low confidence → human queue with no default action. Money, refunds, and irreversible side effects stay human-owned — suggestions only.
Pick one named option. Returns the key, full probability map, and confidence.
Place state on an ordered rubric. A level index — not an accuracy promise.
Keep act / confirm / human bands in your code. Calibrate on your labeled data.
TypeSafe Jev is a System One evaluation model on Vercel AI Gateway. It returns typed Choice, Score, and Boolean answers with probabilities instead of free-form text.
No. This Jev tutorial teaches calling AI Gateway directly from your app or serverless function. A custom relay is out of scope and discouraged.
No. Templates and examples only suggest routes or labels. Money and refund decisions stay with humans or other systems.