What it does
Reads completed Claude Code or Codex sessions and assigns typed judgements to each turn for later analysis.
Agent tooling
Only you can see your notes.
Screenshot unavailable. Open the experiment ↗
Reads completed Claude Code or Codex sessions and assigns typed judgements to each turn for later analysis.
Your developer can install this tool to review past work from AI assistants like Claude. It reads saved sessions to see where the software succeeded or wasted effort. The tool then suggests changes to improve how your project instructs the AI.
The developer runs a starting command in your project folder to begin. They must provide an access key that connects the tool to the Jev service.