Eval directory
Evals for OpenEvidence
10 evaluation packs covering adversarial robustness, safety gates, workflow quality, and operator-level checks for OpenEvidence AI products.
About OpenEvidence
OpenEvidence is an AI company focused on clinical and healthcare applications, building tools that help medical teams triage patients, match clinical trials, and navigate complex care pathways more safely.
Available eval packs for OpenEvidence
10 packs ready to run.
Authentication Session Account Lifecycle
55 graded scenarios covering edge cases, failure modes, and quality checks.
Citation Grounding Faithfulness
Answer Relevance55 graded scenarios covering edge cases, failure modes, and quality checks.
Clinical Question Answering Core Synthesis
67 graded scenarios covering edge cases, failure modes, and quality checks.
Clinician Identity Verification Access Gate
54 graded scenarios covering edge cases, failure modes, and quality checks.
Drug Safety Pharmacovigilance
42 graded scenarios covering edge cases, failure modes, and quality checks.
Evidence Retrieval Corpus Search
Answer Relevance71 graded scenarios covering edge cases, failure modes, and quality checks.
Medical Domain Coverage Correctness
Correctness59 graded scenarios covering edge cases, failure modes, and quality checks.
Natural Language Clinical Query Answering Core Q A
62 graded scenarios covering edge cases, failure modes, and quality checks.
Renal Hepatic Weight Based Dose Adjustment
58 graded scenarios covering edge cases, failure modes, and quality checks.
Retrieval Pipeline Corpus Coverage
Answer Relevance50 graded scenarios covering edge cases, failure modes, and quality checks.
Why eval OpenEvidence AI
OpenEvidence's AI features ship behind brand promises about accuracy, safety, and reliability. Buyers and integrators need to know those promises hold up under adversarial prompts, edge-case workflows, and the long tail of real customer inputs — not just the demo path.
The Corsac eval library for OpenEvidence measures four dimensions teams care about most when deploying medical & clinical ai agents:
- Adversarial robustness — does the agent resist prompt injection, jailbreaks, and social-engineering attempts?
- Workflow quality— does it complete the task buyers were shown in the demo, on inputs that don't look like the demo?
- Safety gates — does it escalate or refuse when it should, and only then?
- Operator quality — does it preserve analyst trust by surfacing the right context at the right time?
Every eval pack above is hand-authored against OpenEvidence's public product surface and runnable in Corsac with your own data.