Using Jev as a classifier

A Jev classifier picks exactly one of your labels and returns it with calibrated probabilities and a confidence value, so there is nothing to parse and no way to get an invalid class back.

Jev is TypeSafe AI's first System One model, and the choice primitive turns it into a fast, typed Jev classifier. You define up to 255 options, send the state you want labeled, and the Jev classifier returns one key, a probability for every option, and a single confidence score. The output is locked to your type, so the answer is always one of the labels you defined.

How the choice primitive classifies

A call to Jev is a model plus state plus a map of questions, and each question can be a classification. That means one Jev classifier request can label many fields in a single round trip. Because the output is typed, a Jev classifier never returns free text you have to clean up, never invents a class, and never trails off mid-answer. This is what TypeSafe AI means by zero hallucination: the result is constrained to your enumeration, while confidence measures how concentrated the distribution is, not a guarantee of correctness.

• One key: the single label the Jev classifier selected
• Probabilities: a calibrated distribution across all your options
• Confidence: how concentrated that distribution is
• Up to 255 classes per choice question

Jev classifier vs prompting an LLM

Prompting an LLM to classify means writing instructions, parsing the reply, and handling labels the model made up. A Jev classifier removes all of that: it responds in roughly 70–500ms, about 40–200x faster than an LLM, and costs around $0.0004 per decision. Trained with RLCD, the Jev classifier is calibrated, so the probabilities it reports actually track how often it is right.

Confidence-gated routing

Because every Jev classifier decision carries confidence, you can route on it. Auto-handle high-confidence labels and send the low-confidence tail to a human or a heavier model. Pin a model version so your thresholds stay stable, then let the Jev classifier run your triage, tagging, and moderation at scale. Hit the hosted endpoint POST https://jevtypesafeai.com/api/v1/decide with a jv_live_ key, or the official POST https://api.typesafe.ai/v1/systemone, and get a Jev classifier answer in one round trip.

See also: What is Jev · How to use the API · Playground

Related: Jev vs an LLM · Jev models · Jev benchmark