Eligibility Benefit Auth Requirement Determination
Payer-side prior-authorization clinical intelligence · Cohere Health
57 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 57
Pass/fail checks, each adjudicated by an LLM judge.
| # | Input | Expected behavior | Check |
|---|---|---|---|
| 01 | A payer config update marks CPT 27447 (total knee arthroplasty) as auth-required under plan PLN-4401 effective 2026-05-25. The lookup is performed on 2026-05-24 for a procedure scheduled on 2026-05-30. The lookup engine evaluates… | Agent evaluates the auth requirement against the date-of-service (2026-05-30), detects that the pending config rule becomes effective 2026-05-25—before the procedure date—and returns 'auth-required' citing the effective date of the governing rule. The agent initiates PA case creation and records th… | Pass / FailPolicycritical |
| 02 | Plan config for CPT 71250 (CT thorax) under PLN-9910 specifies: modifier -26 (professional component) = auth-required; modifier -TC (technical component) = auth-not-required; no modifier = auth-required. A FHIR CRD request arrive… | Agent parses the modifier array, identifies code '26' as the professional-component modifier, and performs the lookup keyed on CPT 71250-26. It returns 'auth-required' consistent with the plan rule for the professional component. The CDS card and audit record both include the modifier as part of th… | Pass / FailPolicycritical |
| 03 | Plan config for PLN-2250 contains two overlapping range rules with no explicit precedence: Rule A covers CPT 70010–79999 (all radiology) = auth-required; Rule B covers CPT 73000–73999 (musculoskeletal imaging) = auth-not-required… | Agent detects that multiple conflicting rules match CPT 73721 and returns 'indeterminate' with a structured conflict payload naming both rules by identifier (Rule A: 70010–79999 auth-required; Rule B: 73000–73999 auth-not-required) and the exact config version ID. The agent does not create a PA cas… | Pass / FailPolicycritical |
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 Eligibility Benefit Auth Requirement Determination eval for Cohere Health Payer-side prior-authorization clinical intelligence test?+
57 graded scenarios covering edge cases, failure modes, and quality checks.
How is the Eligibility Benefit Auth Requirement Determination 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 Eligibility Benefit Auth Requirement Determination pack for Cohere Health Payer-side prior-authorization clinical intelligence contains 57 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 Eligibility Benefit Auth Requirement Determination 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.