Repo

clinical-agent-evals

by Chen-Yang Su · Stanford University

A stateful clinical-agent benchmark and distributed evaluation harness: outcome-based grading against a simulated EHR, repeated trials with cluster-bootstrap confidence intervals, full JSONL traces, and pluggable mock/Messages-API/Agent-SDK backends.

Visit github.com ↗

Built with

Python

Comments · 0

No comments yet. Tried it? Tell Chen-Yang what worked, what didn't, or what you'd want next.

More from members

All projects

See what other members are building and what each project is looking for.