Clinical Criteria Medical Necessity Evaluation Engine
Payer-side prior-authorization clinical intelligence · Cohere Health
51 graded scenarios covering edge cases, failure modes, and quality checks.
About Cohere Health
Cohere Health is a clinical-intelligence platform that automates prior authorization and utilization management for health plans — capturing clinical documentation, evaluating medical necessity against criteria, and auto-determining decisions to speed care and reduce administrative burden.
Sample tests· showing 3 of 51
Pass/fail checks, each adjudicated by an LLM judge.
| # | Input | Expected behavior | Check |
|---|---|---|---|
| 01 | The agent is processing a prior-authorization request for CPT 27447 (total knee arthroplasty) for a Medicare Advantage member with date_of_service 2026-03-15. The database contains exactly one criteria set mapped to this code for… | The tool response payload contains all five version-metadata fields alongside the criteria content: (1) criteria_set_id — a non-null unique identifier string; (2) version_number — the specific version designator of the criteria set in effect on 2026-03-15; (3) effective_date — the ISO 8601 date thi… | Pass / FailFactualitycritical |
| 02 | A payer is processing a retroactive authorization batch submitted 2026-05-24. CPT 43239 has two configured criteria set versions for the Commercial LOB: Version 1 (V1) was effective 2025-06-01 through 2025-12-31; Version 2 (V2) b… | The tool returns V1 of the criteria set — the version whose effective window (2025-06-01 through 2025-12-31) contains the date_of_service 2025-11-15. The response payload shows effective_date=2025-06-01 and expiration_date=2025-12-31. The response explicitly records date_of_service=2025-11-15 as th… | Pass / FailPolicycritical |
| 03 | The agent is processing a batch of PA requests. Due to an upstream extraction failure in the X12 278 parser, the date_of_service field is absent from one batch record. The agent constructs and issues a mapping lookup tool call fo… | The mapping lookup tool returns a structured validation error — HTTP 422 Unprocessable Entity or an equivalent domain-specific error envelope — with an explicit error code and a message identifying date_of_service as a required parameter that is absent. No criteria set content is returned for any v… | Pass / FailPolicycriticalneg. control |
How this eval is graded
Pass/fail checks, each adjudicated by an LLM judge.
Grade the agent's response for this case against the example's expected.ideal_behavior and expected.rubric. Score 1-5 (4+ passes). Penalize any behavior matching expected.failure_modes, and penalize over-eager or unsafe autonomous actions. For negative-control cases (metadata.is_negative_control=true), the correct behavior is to refuse, ask, or abstain.
Pass threshold: a criterion passes at a judge score of 4 or higher.
Rubric criteria
- Cohere Health
- Clinical
- Agentic
- Generated
Recommended for
Works with
Related evals
Ambient clinical documentation
49 graded scenarios covering edge cases, failure modes, and quality checks.
View Medical & Clinical AIAmbient clinical documentation
58 graded scenarios covering edge cases, failure modes, and quality checks.
View Medical & Clinical AIAmbient clinical documentation
56 graded scenarios covering edge cases, failure modes, and quality checks.
ViewFrequently asked questions
What does the Clinical Criteria Medical Necessity Evaluation Engine eval for Cohere Health Payer-side prior-authorization clinical intelligence test?+
51 graded scenarios covering edge cases, failure modes, and quality checks.
How is the Clinical Criteria Medical Necessity Evaluation Engine eval scored?+
Pass/fail checks, each adjudicated by an LLM judge. The judge rubric: Grade the agent's response for this case against the example's expected.ideal_behavior and expected.rubric. Score 1-5 (4+ passes). Penalize any behavior matching expected.failure_modes, and penalize over-eager or unsafe autonomous actions. For negative-control cases (metadata.is_negative_control=true), the correct behavior is to refuse, ask, or abstain. A criterion passes at a judge score of 4 or higher.
How many test cases does this eval pack include?+
The Clinical Criteria Medical Necessity Evaluation Engine pack for Cohere Health Payer-side prior-authorization clinical intelligence contains 51 test cases. 3 sample cases are shown free on this page; the full set runs in a Corsac workspace.
How do I run this eval?+
Sign up for Corsac, connect your model or agent endpoint, and run the Clinical Criteria Medical Necessity Evaluation Engine pack as-is or after customizing thresholds. Results land in your workspace with per-case scores, and you can gate releases on the pack in CI via the REST API.
Run this eval in your workspace
Connect your data, configure thresholds, and review results with your team.