Jev Calibration Reports and CI Checks
jeval analyzes Jev logs to assess confidence calibration and when a human should take over. It produces an HTML report and can fail CI when a new model behind jev-latest shifts calibration.
Using Jev? Every answer comes back with a confidence.
But is 0.9 really right 90% of the time, and at what confidence should a human take over?
jeval answers both from your own Jev logs in a single HTML report, and fails your CI when a new model behind jev-latest shifts calibration.
Don't want to learn the CLI? It ships with agent skills: hand it to your coding agent and get the report back.
https://t.co/ycFYZ5bdNs
#jev #skill
It also ships with agent skills, so a coding agent can run it and return the report without requiring users to learn the CLI.
Also filed under Tools & apps
- Search Telegram Channels by Topic
Sanyi built a tool using JEV that lets people search Telegram channels in his community by topic, question, or vibe. Matching channels rise up in seconds.
- Jev Omni MCP Build
eureka-pd/jev-omni-mcp is an MCP build for Jev.
- Jev Verbose Couscous Build
Beliato's `jev-verbose-couscous` is a build made with Jev.
- Build a Twilio IVR with Jev
This project uses Jev with Twilio to build an interactive voice response system.