Which one?
Pick from options you define.
billing | technical | sales | otherJev understands language and returns answers your code can use. A choice. A yes/no probability. A score. No generated paragraphs. Just the judgment you need.
See it in action ↗3-minute tour · 8 demos · No key needed“I was charged twice.
Can I get my money back?”
Jev is TypeSafe’s first System One model: built for focused judgments, not writing or long-form reasoning.
A message, a document, or structured text. This is the state.
Define what to judge and what the possible answers mean.
Route, rank, flag, or ask a human. Your application stays in control.
Pick from options you define.
billing | technical | sales | otherReturn the probability of yes.
refund_requested → 0.98Rate against descriptive, ordered levels.
severity → 1.94 on a 0–2 scalePick an application. Follow the path from language to a useful action.
Demo policies use 0.70 confidence for Choice/Score, 0.20/0.80 Noul cutoffs, and 1.50 for high scores. These are teaching defaults, not validated production thresholds.
Not a text generator. Pair it with a generative model when you need a written answer.
Not a calculator. Keep arithmetic, dates, permissions, and side effects in code.
Not infallible. Typed answers guarantee shape, not truth. Validate on your data and send uncertain cases for review.
One state, many questions. Batch independent judgments together. They run in parallel, without seeing each other’s answers.