JevMade field notes / Video guide

JEV Tutorial: System 1 AI, Structured Outputs & Python Examples

Mohamed Naji Aboo introduces TypeSafe AI's Jev model as a fast System 1 decision engine. He walks through the Python SDK using Noul, Choice, and Score in a single API call to classify customer support message topics, tone, and urgency.

Original by Mohamed Naji AbooGetting startedBeginner12 min 10 sec Published 21 September 2026

Bookmark Keep this in your collection.

Leave a noteWhat would you try with this?

Only you can see your notes.

Before you press play

What you’ll find in the video

Jev functions as a fast System 1 decision engine designed to output structured judgments rather than long conversational text.
The TypeSafe SDK provides Noul, Choice, and Score question primitives that can be evaluated together in a single request.
Urgency scoring maps against an ordered rubric, returning a continuous score relative to rubric criteria indices.

Worth knowing

Demonstrated latency and calibration reflect a single interactive notebook call and should not be treated as a controlled multi-sample benchmark.

All video guides →Prefer to read? Written guides →