Jev: Typed AI Decisions in Python — Build a Classifier + Route Coding Standards with Claude Code
Omar Kamal demonstrates how to use the Jev decision API in Python. He details the choice, score, and Noul decision types, explains question batching constraints, builds a coding convention classifier across 14 modules, and packages the model into a Claude Code skill to steer automated code reviews.
Original by Omar KamalAgent workflowsIntermediate12 min 19 secPublished Source reviewed
Before you press play
What you’ll find in the video
The Python example evaluates categorical, scoring, and yes-or-no questions over one shared state.
Batching reuses state, but the shown API rejects a request above its 50-question limit; limits can change with the API version.
The coding-rules example uses Jev to select relevant standards before a larger model reads and reviews the code.
Worth knowing
Gemini-assisted video/transcript review. Results and precision/recall metrics are based on the presenter's single 14-module demonstration rather than an independent benchmark, and typed schema adherence does not ensure decision accuracy.