agent-eval

provenance:github:RudrenduPaul/agent-eval

Statistical regression testing for LLM agents. Run your agent 50x on version A and B, get a p-value and effect size on whether behavior actually changed.

View Source ↗First seen 26d agoNot yet hireable

PUBLIC HISTORY

First discoveredJul 16, 2026

IDENTITY

inferred

Identity inferred from code signals. No PROVENANCE.yml found.

Is this yours? Claim it →

METADATA

platformgithub

first seenJun 19, 2026

last updatedJul 15, 2026

last crawledtoday

version—

README BADGE

Add to your README:

![Provenance](https://getprovenance.dev/api/badge?id=provenance:github:RudrenduPaul/agent-eval)