Note: NHID-Clinical is an early-stage open proposal by Brianna Baynard. It is not an accredited standard or regulatory requirement.
Home/Examples

Dialogue Examples

What transparent disclosure sounds like.

Side-by-side examples of AI voice agent openings — the kind of interaction this proposal is trying to encourage, and the kind it is trying to reduce.

The core idea is simple: an AI voice agent should say it is not human before asking for or sharing any operational information. The examples below show what that looks like — and what it looks like when it does not happen.

Good examples — disclosure upfront

What we'd like to see more of

These openings work because the AI identifies itself immediately — before asking for anything. The representative knows what they're dealing with from the first sentence.

General payer operations inquiry

"Hello, this is an automated AI voice agent from Acme Health Plan. I am not a human. I'm calling regarding a claim. Do I have permission to continue?"

Automated nature disclosed immediately. No data exchanged before identification.

Dental payer — claim status

"This is the AI claims assistant for Delta Dental. I am a non-human system. May I have your NPI to check a claim status?"

Non-human status disclosed before any data is requested.

Prior authorization follow-up

"Good morning. This is an automated system calling on behalf of Riverside Medical Group to follow up on a prior authorization request. I am not a person — I'm an AI agent. Are you available to continue?"

Clear, early, unambiguous. The representative can make an informed decision about how to proceed.

Eligibility verification

"Hi, this is an automated voice agent — not a human — calling from Valley Provider Services to verify eligibility for a patient visit. Before I give you any details, do I have your permission to proceed?"

Discloses first, then asks permission. Gives the representative control.

Problematic examples — what this proposal aims to reduce

Patterns that create impersonation latency

These examples illustrate the problem. Each one involves data being exchanged before the representative knows they are talking to an automated system. The scenarios are based on real patterns observed in healthcare payer–provider calls.

The full impersonation latency pattern
AI Agent "Hi, this is Sarah from Dr. Smith's office calling to check claim status for a patient. The provider's NPI is 1234567890."
Payer Rep "Sure, I can help with that. What's the patient's member ID?"
AI Agent "The member ID is 987654321 and the date of service was January 15th."
Payer Rep "Okay, I'm pulling that up. The claim is currently in review... wait, are you a real person?"
AI Agent "I am an automated system calling on behalf of Dr. Smith's office."

The representative shared claim status and engaged in a full workflow exchange before knowing they were talking to automation. NPI and member ID were already exchanged. There is no record of when — or whether — this would have been disclosed without a direct challenge.

Disclosure buried mid-call
"Good morning, this is the billing department at Valley Medical calling about claim 789012. The provider NPI is 5551234567 and we're following up on an authorization request from last week. By the way, I should mention I'm an automated calling system."

Disclosure comes after the purpose and claim details are established. A busy representative may have already started pulling up records.

Human sounds designed to deceive
"[audible breath] Hi, this is Mike from Advanced Medical Solutions. [pause] I'm calling to verify some patient eligibility information — just give me a moment to pull up the file. [typing sounds] Okay, so the provider NPI is..."

Breathing sounds, hesitation pauses, and typing are added to create the impression of a human caller. Even if disclosure eventually comes, the framing is designed to mislead.

Disclosure only when challenged
"Hello, I'm calling about a claim for member 445566. Can you confirm current claim status? [After representative challenges] Yes, this is an automated system."

Disclosure is contingent on being asked. This is the core pattern this proposal aims to change.

A note on scope

These examples cover B2B administrative voice workflows — AI systems calling payer offices on behalf of providers or vendors. They do not apply to patient-facing calls, secure messaging, or internal systems.

The examples above are illustrative, not exhaustive. If you encounter patterns in real calls that are not covered here, we want to hear about them.

Get involved

Seen something different in the real world?

Real call patterns from payer operations staff are the most valuable input to this proposal. Share what you've seen.

Join the Discussion →