Jev-Guard: Fast Routing and Auditing Agent Actions over Editable Policy Trees

Summary

Jev-Guard is a unified model that performs both safety classification and policy routing for agent harnesses, selecting an applicable audit policy from a policy tree before classifying the action. On 7,033 evaluation cases it reports 93.72% safety accuracy, a mean latency of 58ms, and 93.10% hierarchical routing accuracy, with the full pipeline averaging 240ms. Integrated into the Hermes harness framework, its permission gate cut mean review time per task from 4.80s for an SFT-LLM judge to 1.33s.