Skip to main content

Registration Service — AI Integration

Status: populated Owner: TBD Last updated: 2026-04-17 Companion: Service Template

1. AI Usage in This Service

Registration has limited, advisory-only AI integration. AI is used exclusively as a Tier A workflow (human-in-the-loop; no automated clinical decisions).

AI PurposePrompt Template NameInvocation PathHITL RequiredModeration
Name normalization hintregistration.name-normalize.v1POST /v1/ai/registration/normalize-name via Kong → ai-gateway-serviceYes — staff accepts/rejects hintInput/output screened by ai-gateway
Duplicate review narrativeregistration.mpi-review-summary.v1Staff-triggered in UI during duplicate reviewYes — human merge decision requiredInput/output screened by ai-gateway

2. Hard Constraints

ConstraintRule
No auto-mergeAI must not automatically execute merge or unmerge operations. AI provides a summary/hint only.
No AI-generated identity recordsPatient demographics are staff-entered or imported from authoritative sources. AI may suggest corrections as hints.
No direct LLM SDK callsAll AI calls route exclusively through ai-gateway-service via Kong /v1/ai/*
tenantId from JWT onlyAI calls include tenantId extracted from JWT; never from request body
Draft ≠ authoritativeAI hints and summaries are never persisted as patient identity until staff explicitly confirms

3. AIProvenance Touch Points

When an AI hint is accepted by staff, the mutation payload includes aiProvenanceRef: { templateName, requestId, acceptedBy } stored in patient_names.patronymic field (or a dedicated ai_provenance JSONB column in future iterations). This enables audit traceability.

4. Roadmap

Duplicate detection remains deterministic (probabilistic MPI rules + staff review). Future consideration: AI-assisted de-duplication confidence scoring as an additional signal — requires ethics and clinical safety review before enabling.