Kitaru Integrates jev Judge to Cheaply Catch Agent Hallucinations
Kitaru now integrates TypeSafe's jev judge to score imported agent trajectories cheaply; a demo showed it catching a support agent fabricating a refund timeline that rule-based checks scored a perfect 1.00.
2026-09-24 ~ 2026-09-24 · 2 related posts
- Episode 1: Kitaru Integrates jev Judge to Cheaply Catch Agent Hallucinations(2026-09-24, 2 posts)
- Episode 2: Testing the jev Judge: 8 Hallucinated Refund Timelines Found in 48 Sessions(2026-09-24, 2 posts)
- Kitaru integrates TypeSafe's jev evaluator to score agent traces alongside deterministic checks — strickvl · 2026-09-24
- Rule-based checks scored 1.00 while the agent hallucinated a refund timeline — strickvl · 2026-09-24