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
Automated nature disclosed immediately. No data exchanged before identification.
Dental payer — claim status
Non-human status disclosed before any data is requested.
Prior authorization follow-up
Clear, early, unambiguous. The representative can make an informed decision about how to proceed.
Eligibility verification
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 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 comes after the purpose and claim details are established. A busy representative may have already started pulling up records.
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 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.