Typesafe · Ai Data

TypeSafe / Jev score -- position on a rubric

Judges state against one score question (Jev's "score" type) and returns a probability-weighted position along an ordered rubric (can land between levels, e.g. 1.6), with the legend and a confidence -- no generated text. Exactly one question per call, 2-10 rubric levels written as concrete situations (not adjectives). Score is for thresholds and ranking, not an exact interpolated number -- do not treat it as ground truth to two decimal places. Pin model to jev-1.13.0 unless told otherwise.

Private Gateway connection

Data below comes from the configured private Gateway. Provider activation remains governed by its evidence and policy gates.

unverifiedRequest shape unavailableUnverified

Published API evidence

Public metadata only. Response bodies, credentials, and internal review notes are never displayed.

No verification date is claimed. No response capture is claimed.

Request parameters

model body · optional
Pinned TypeSafe System One model id.
questions body · required
Exactly one score question. The object's single key is your own name for it; the answer comes back under the same key.
state body · required
The text being judged (the announcement's `text`).

Provider docs How to run it