Refills, approved at the speed of Stars.

PHI is processed inside our HIPAA-compliant cloud and is encrypted at rest with AES-256 and in transit with TLS 1.3. We sign a BAA with every covered entity. PHI is never used to train foundation models.

PrefillX is designed against the FHIR R4 specification — it reads Patient, MedicationRequest, and Observation resources from any FHIR R4-compliant EHR feed. Our criteria-check output is returned to the EHR as a structured update with the reasoning trace attached; the prescriber’s signature and any downstream pharmacy routing happen through the EHR’s existing workflow.

For a customer already exposing a FHIR R4 feed, the platform-side work — protocol configuration, audit-log integration, pharmacist review UI — is on the order of weeks. Total time-to-value is paced by the customer’s own EHR-access posture and clinical change-management.

No. PrefillX operates under FDA enforcement discretion for Clinical Decision Support — 21st Century Cures Act §3060. PrefillX does not approve refills; it marks each refill Met or Flagged against a pharmacist-authored protocol. The pharmacist remains the decision-maker of record on every refill — Met cases are reviewed and approved with the AI’s reasoning trace inline; Flagged cases get a full chart-context review.

Routine refills that meet every criterion of the universal 7-point refill check (patient / medication / prescriber / visit / allergy / interaction / supply-window) and the relevant drug-class protocol (one of forty-three) are marked Met with a complete reasoning trace logged — the pharmacist reviews and approves these on the routine path with the trace inline. Edge cases — drug-drug interactions, renal flags, controlled substances, PA-required medications, recent ED visits, off-protocol classes — are Flagged for the pharmacist with the full chart context attached. PrefillX never approves a refill; the pharmacist signs off on every refill, and the protocol — pharmacist-authored — governs which path each takes.

We instrument PDC against MAC, MAD, and MAH; Met rate; pharmacist override rate on the Met path; pharmacist review depth on the Flagged path; and reasoning-trace audit completeness. All metrics ship with confidence labels and a methodology link.