Eval Library
Notable Health
For Notable HealthMedical & Clinical AIDoc Agent

Insurance Eligibility Benefits Verification

Workflow automation + documentation agents · Notable Health

63 graded scenarios covering edge cases, failure modes, and quality checks.

About Notable Health

Notable Health 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.

Employees

50–500

Industry

Healthcare AI

Headquarters

United States

Sample tests· showing 3 of 63

Pass/fail checks, each adjudicated by an LLM judge.

#InputExpected behaviorCheck
01

A pre-service eligibility batch for tomorrow's appointments includes a patient whose legal surname is 'O*Brien', entered in the EHR with an asterisk. The interchange was initialized with ISA11='*' as the component-element separat…

The agent scans each PHI field against the ISA11 component-element separator, ISA16 repetition separator, and the interchange segment-terminator before constructing any segment. It detects that 'O*Brien' contains the ISA11 character '*'. It rejects this single record with a structured pre-transmiss…

Pass / FailSafetycritical
02

The eligibility worker pod crashes at 09:14 UTC after issuing ISA13 values 1 through 340 for sender/receiver pair NOTABLEHLTH/AVAILITY01 on 2026-05-26. A replacement pod starts. It must not reuse any control number in the range 1…

On startup the replacement pod reads the last-committed ISA13 value for the NOTABLEHLTH/AVAILITY01 pair from a durable shared sequence store (e.g., a database sequence, distributed atomic counter, or equivalent) — not from process memory, a local file, or an environment variable. It resumes issuing…

Pass / FailPolicycritical
03

Emma Chen (DOB 20161203, age 9) is scheduled for a well-child visit. The insured subscriber is her father, David Chen (MemberID UHC4481920, DOB 19820715). The EHR 'relationship to guarantor' field is correctly set to 'child.' The…

The agent constructs four HL levels in this order: HL*1**20*1 (Information Source), HL*2*1*21*1 (Information Receiver), HL*3*2*22*1 (Subscriber — David Chen), HL*4*3*23*0 (Dependent — Emma Chen). The HL02 on the dependent HL (HL*4) is set to '3', pointing to the subscriber HL level number. HL03 on …

Pass / FailWorkflowcritical

Rubric criteria

  • Notable Health
  • Clinical
  • Agentic
  • Generated

Recommended for

Workflow automation + documentation agentsNotable Health customers

Works with

Related evals

Run this eval in your workspace

Connect your data, configure thresholds, and review results with your team.