OPEN-SOURCE PROJECT

jev-ood-calibration

Independent calibration test of TypeSafe's Jev on a task it cannot have seen: 900 rule-generated support tickets (choice / score / boolean) plus 3 public benchmarks via Vercel AI Gateway. Raw responses, ECE with noise floor, temperature refit, per-type sign of miscalibration. Reproducible for ~$0.06.

Stars
3
Forks
0
License
MIT
Last commit
2026-09-19

What Jev does here

Jev returns a structured decision for the local program; consult the source for the exact decision policy.

Adds structured choices or scores to the workflow; performance and cost benefits have not been independently verified.

Based on repository metadata and README with rule-based classification; pending human review, with no independent runtime or performance verification.