AgentForge — Adversarial Evaluation Dashboard

Target: clinical-copilot (OpenEMR Clinical Co-Pilot) ·

Status at a glance

OWASP LLM coverage

CategorySeed cases

Run history

TargetTimestamp (UTC)VersionVerdicts

What is built vs designed

Built and runningDesign only

Cost

Key metrics (definitions in KEY_METRICS.md)