An AI phone assistant acts on a chain of uncertain evidence — a noisy audio stream, an ASR transcript, an inferred intent, extracted slots, an EHR lookup, a synthesized reply. Any link can be silently wrong while every downstream step still looks reasonable. This is the same Discovery-as-data-quality result as the fleet benchmark, in a second, agentic domain: before acting, a Discovery stage establishes whether the evidence can be trusted — cheap checks first, expensive verification only where the decision is in doubt.
Evidence · synthetic · internally reproduced 27 Oct 2026: 1,235 unsafe-if-ungated actions, 2 executed; out of sample 1,827 and 2; fairness disparity 0.034; regression suite 24/24; out of sample, 25 of 1,573 clean turns were gated unnecessarily.
The call is a composition of Discovery stages; each returns a trust verdict into one DecisionGate. Reuses the fleet benchmark's modality-neutral Capability contract unchanged. Ground truth is a synthetic healthcare corpus — never real PHI — where every turn carries the correct gate and whether trusting it ungated would take an unsafe action.
Detecting bad data is table stakes; the result that matters is the decision. We run the failure-prone corpus with no data-quality control (trust everything) versus gated by adaptive Discovery, and count the unsafe actions that execute — wrong-patient lookups, unauthorized PHI disclosure, double bookings.
Cheap device-local validators (null / range / DTMF / slot / EHR freshness / PHI policy) resolve most turns; only consequential turns whose evidence isn't pristine escalate to the expensive specialist (2nd-pass alignment, patient reconciliation, groundedness).
| strategy · catch turns that need gating | precision | recall | specialist calls |
|---|---|---|---|
| Cheap validators onlymisses the hidden defects (confident hallucination, wrong patient, injection) | 1.000 | 0.787 | 0.00× |
| Always specialistexpensive verification on every turn | 1.000 | 1.000 | 1.00× |
| Discovery — adaptiveescalate only the consequential-uncertain minority | 1.000 | 0.999 | 0.13× |
// 4,000 synthetic turns · gate oracle = expected_gate · 24-scenario regression suite 24/24 safe-side · reproduce: redevops-edge/voice · python -m voice
A quality gate that "works" by silently re-prompting every non-native speaker has failed — more so in healthcare. Fairness is a blocking result, not a footnote: false-recovery (gating a genuinely clean turn) is measured for parity across accent groups.
// synthetic healthcare transactions, never real PHI · in-sample seed 7 + out-of-sample seed 23 (shifted distribution) · reproduce: redevops-edge/voice · python -m voice
// No real patient data is used or shipped — the corpus is generated synthetically for the benchmark. The runtime reuses the same Capability contract as the fleet benchmark, demonstrating one modality-neutral Discovery primitive across telemetry and agentic voice.