jev-guardrails
deepansh-saxena/jev-guardrails
Comparing LLM-as-judge vs TypeSafe Jev for agent guardrails: same rules, same agent, measured on cost, latency, calibration and coverage.
Python
- Stars
- 3
- Forks
- 1
Why it is listed
A mock support agent benchmarks two guardrail backends—an LLM judge and typed Jev judgments—on the same rules; its reported measurements are project results.