Decision record
HOLD · TerminalOutcome: terminal hold, not sent- Operation
- op_1e5947a3
- Request
- req_1e5947a3
- Tenant
- UniversalHealthCare.ai
- Subject
- UHC-PT-00908synthetic
Terminal hold · no dispatch. Future outreach requires a new customer-triggered request.
The judgment engine proposed a third contact in the same period. The frequency cap held it. Terminal — the next contact needs a new customer-triggered request in a new period.
Timing
Regent's freshness guarantee begins when Regent receives the push. The snapshot timestamp inside the request is tenant-asserted metadata and is never the basis of that guarantee; data age before the push is the tenant's pipeline responsibility.
Versions in effect
AI judgment
Context · pre-agent hard stops
- ContactabilityActive WhatsApp channel.evidence: computed by RegentPASS
- Crisis flag / global opt-outNo crisis flag. No global opt-out.evidence: tenant-assertedPASS
Judgment · AI proposal
- AI judgmentSEND — no response to the previous two contacts.evidence: computed by RegentINFO
Governance · rules run after the proposal
- Proposal-specific consentConsent scope covers re-engagement contact.evidence: tenant-assertedPASS
- Frequency cap (3 of 3)Cap reached for the current period. Terminal hold — no dispatch, nothing queued.evidence: computed by RegentHOLD
Action · dispatch
- Governed dispatchNo dispatch. Future outreach requires a new customer-triggered request.evidence: computed by RegentNOT RUN
Dispatch state
Evidence
Exact inputs, policy versions, model version, gates and recorded outcome are preserved and integrity-verifiable on demand. Inspect reconstructs the recorded decision context — the inputs, versions, gates and outcome exactly as they were. It does not re-run the model or promise an identical regenerated answer.