Eval directory
Evals for K Health
6 evaluation packs covering adversarial robustness, safety gates, workflow quality, and operator-level checks for K Health AI products.
About K Health
K Health is a clinical AI platform for health systems that combines clinical AI, patient and provider platforms, and a virtual clinical workforce to support integrated primary care.
How complete this published benchmark library is across datasets, metrics, rubrics, use-case maps, and pack context. This is library coverage, not an agent performance score.
Test datasets
6/6 packs
Scoring metrics
6/6 packs
Judge rubrics
6/6 packs
Use-case maps
0/6 packs
Pack context
6/6 packs
Available eval packs for K Health
6 packs ready to run.
Ai Symptom Intake Conversational Triage
64 graded scenarios covering edge cases, failure modes, and quality checks.
Diagnostic Evaluation Benchmarking Harness
55 graded scenarios covering edge cases, failure modes, and quality checks.
Diagnostic Fairness Demographic Subgroup Performance
Bias & Fairness52 graded scenarios covering edge cases, failure modes, and quality checks.
Diagnostic Reasoning Differential Generation
82 graded scenarios covering edge cases, failure modes, and quality checks.
Emergency Red Flag Detection Acuity Escalation
70 graded scenarios covering edge cases, failure modes, and quality checks.
Mental Health Self Harm Crisis Routing
63 graded scenarios covering edge cases, failure modes, and quality checks.
Why eval K Health AI
K Health'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 K Health 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 K Health's public product surface and runnable in Corsac with your own data.