jevVIDEO

jeval checks Jev confidence calibration and fails CI on drift

The open-source jeval tool builds an HTML report from your Jev logs to answer whether 0.9 really means 90% and when a human should take over, and fails CI when the model behind jev-latest shifts calibration.

HOPE | Engineer.

@rlaopeArchived 2026.09.28Originally posted 2026.09.27

HOPE | Engineer. @rlaopeOriginally posted 2026.09.27

Open original on X

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://github.com/rlaope/jeval #jev #skill

x.com/rlaope/status/2104098591308431450Archived 2026.09.28 10:03