1.0.0
·
223 commits
to main
since this release
a002456
This commit was signed with the committer’s verified signature.
frederikprijck
Frederik Prijck
Built an eval framework to answer that- a system that runs real AI agents through real Auth0 integration tasks, then scores the output across 7 dimensions including correctness, security, and hallucination. We measured the agent experience across 5 models, 12 frameworks, and 60 configurations and made the results public on https://auth0.com/agent-experience