A voluntary behavioral baseline for transparent AI voice agents in B2B healthcare payer–provider calls.
Open reference implementation with a cryptographic authorization layer (NHID-Auth v2).

Built by a former payer operations associate who saw the impersonation latency problem firsthand on live calls.
Not a standard. Not a certification. Not a product. An open, testable reference for the ecosystem.

Website · Simulator · Specification · v2 Identity · Discussions

_{The NIST badge links to a public comment submitted to a NIST RFI docket — not a NIST endorsement, adoption, or certification.}

Impersonation latency is the core problem: the measurable trust delay when an AI voice agent operates and exchanges PHI without disclosing its non-human identity. NHID-Clinical makes that delay observable and testable with four deterministic controls, a supplemental audit-trail requirement, and a live conformance API.

_{Illustrative visualization of the trust verification pathway — conceptual render for clarity, not a product diagram.}

Plus ATR-01 (audit trail) — every call must produce a machine-readable trace.
18-case CTS suite · same inputs → identical output · 330 Python tests passing (+ 66 TypeScript middleware tests)

Try the Governance Simulator →

Full technical architecture →

_{Without a standard: disclosure after PHI moves, no audit trail. With v1.3: early disclosure, verification checkpoint, human escalation, sealed audit.}

How the controls play out on a real call — the same sequence the CTS suite and live adapters evaluate.

flowchart LR
    A["Call starts"]:::start --> B{"Identity disclosed<br/>before PHI?"}:::neutral
    B -->|No| C["DENY_DATA<br/>IDG-01 + PDX-01"]:::deny
    C --> D["Escalate to human<br/>EIT-01"]:::neutral
    B -->|Yes| E["PHI exchange<br/>PDX-01, DBC-01"]:::neutral
    E --> F{"Human requested?"}:::neutral
    F -->|Yes| D
    F -->|No| G["Call completes"]:::ok
    D --> H["Audit trace<br/>ATR-01"]:::ok
    G --> H

    classDef start fill:#0b6ebc,stroke:#063752,color:#ffffff
    classDef deny fill:#d64545,stroke:#7a1f1f,color:#ffffff
    classDef ok fill:#0e9f6e,stroke:#066a49,color:#ffffff
    classDef neutral fill:#4b5563,stroke:#262b33,color:#ffffff

No signup or API key required for demo and vendor adapter routes.

curl -s -X POST https://gfvq4swdtf.execute-api.us-east-1.amazonaws.com/prod/v1/adapters/vapi/check \
  -H "Content-Type: application/json" \
  -d @tests/demo_scenarios/vapi_noncompliant.json | python -m json.tool

New here? 5-minute quickstart · v2 integration guide (Tier 0 → Tier 2)

git clone https://github.com/NHID-Clinical/NHID-Clinical.git
cd NHID-Clinical
pip install -r requirements.txt
python -m pytest tests/ -v

Expected: 330 passing in ~1.4s (~18 skip without a running server). Live demos and full docs on nhid-clinical.org.

NHID-Clinical/
├── schema/          # Event schema (JSON Schema Draft 2020-12)
├── src/             # Policy engine + NHID-Auth v2 identity layer
├── tests/           # CTS (YAML) + pytest harness + demo scenarios
├── traces/          # 10 canonical failure traces
├── adapters/        # VAPI, Twilio, Vonage, Retell, Amazon Connect
├── functions/       # AWS Lambda handler
├── docs/            # Quickstart, integration guides, knowledge archive
└── specs/           # PDF artifacts (Overview, Core Spec, Blueprint)

v1.3 verifies disclosure behavior. v2 verifies authorization: Ed25519 agent passports, NPI binding, scoped delegation (max 3 hops), revocation, and call-SID nonce binding. Reference code in src/agent_identity.py.

python -m pytest tests/test_identity.py -v
python examples/issue_and_verify.py

Details →

We are seeking the first shadow evaluation partners — 90 days, observe-only, no vendor changes required.

For Payers → · Community · GitHub Discussions · contact@nhid-clinical.org