What it does
A closer look at Jev 1.13.0, with controlled prompts and the raw answers available to inspect.
Benchmarks & research
jev-behavior-study
Bookmark: jev-behavior-study
Keep this in your collection.
Leave a noteWhat would you try with this?
: jev-behavior-study
Only you can see your notes.
Screenshot unavailable. Open the experiment ↗
How you can use it
Your developer can run these pre-written tests to see how the Jev AI handles specific tasks. They can watch the AI plan a travel route or play a grid game. The scripts show how small wording changes alter the AI's choices.
To start, your developer provides an access key. This key connects the scripts to the TypeSafe AI service. The test results reveal an important limit. An AI that passes a simple task might still fail a harder version.