Agent tooling

LLM Debugger

Points a debugger at your bug and lets Jev decide every next step, so the expensive model only wakes up for the hypothesis and the fix.

Bookmark Keep this in your collection.

Leave a noteWhat would you try with this?

Only you can see your notes.

Source screenshot of LLM Debugger — SOURCE SCREENSHOTFull screenshot ↗

What it does

Breakpoints, stepping, and live variable reads happen in your real debug session; Jev chooses between actions for a fraction of a generation call.

How you can use it

For a price error in your app, start with the amount you expected and what the app actually returned. Give those details to a developer using this tool. It watches the calculation to find the fault. The tool sends program details to outside AI services, so the investigation is not limited to your computer.