Technological Ceiling
Frontier models with the right support systems can clinically reason across various modalities and specialties.
Automate workflows like prior authorization end to end
Implement accurate and autonomous work at scale, built with your team, integrated into your systems and auditable at every step
See how Geisinger tripled reviewless approvals, halved escalated cases needing manual review and strengthened payer-provider-patient relationships.
Most back office work at health plans is highly scrutinized and time sensitive, performed by clinicians and operators who are already stretched thin. AI can change this, but only if your operating model changes with it.
Operational Ceiling
The structural and human constraints that exist within your health plan: tightly interlinked tech stacks, flawed administrative workflows and high-stake work that impacts the life of every member.
The Opportunity Gap
During Relay, we work with your clinicians to map and augment the nuance of existing workflows, integrate our system into your existing systems, and equip your teams with the tools to evaluate and run AI reasoning reliably at scale.
We automate work while improving the operating model it is based on
Implement real-life workflows that run in the background, are integrated with your systems of record and continuously evaluated against real and synthetic data.
Whether in your interfaces or ours, any work done on our system can be called up and audited, with full provenance and proof of work available
We work with your clinical, UM, and technical stakeholders to configure and validate workflows that reflect real-world clinical interpretation and case processing.
Your clinicians learn how to architect, deploy, and monitor AI systems that standardize work and improve member care and experience at scale.
Across a range of plan functions
Utilization Management
Automated approvals and faster reviews
Automate more approvals without sacrificing accuracy, and accelerate reviews that still need a clinician.
HEDIS
Scale gap closure, not headcount
Close more care gaps to lift Star Ratings and revenue, improve member outcomes, and scale quality without scaling the team.
Payment Integrity
Catch more before you pay
Review every claim against the chart, and catch improper payments before they go out.
Powered by Florence
Florence is our AI system designed specifically for performing highly regulated and complex work in health plan environments.
Capable
Proven across the breadth of plan workflows
Built on frontier models that can reason and work across modalities — charts, faxes, structured feeds, and policy text — so Florence handles clinical and administrative work across utilization management, case management, HEDIS, risk adjustment, and payment integrity.
Captures organizational knowledge
Florence encodes how your plan actually decides: tacit knowledge, accepted evidence, and organizational interpretations of policy and thresholds. Those standards stay version-controlled and reusable, so every workflow reflects the way your organization works.
Evaluation and feedback built in
Synthetic data and large-scale evaluation catch issues before deploy. In production, feedback from LLM checks and human review flows back into the system so Florence keeps improving with every case.
trustworthy
Complete traceability of reasoning
Each outcome includes the reasoning and supporting evidence behind it — relevant record findings and the specific policy criteria applied — so any result can be reviewed and substantiated on demand.
Immutable decision ledger
Every action, from record access through final outcome, is written to an immutable ledger of events. That record keeps all activity auditable for appeals, regulatory review, and internal quality assurance.
Compliant by construction
Built to HIPAA, SOC 2, NCQA/URAC, and applicable federal and state AI and interoperability requirements. Work completes automatically only where criteria are clearly met; otherwise Florence escalates to a qualified human with a sourced evidence packet.
integrated
Ingests data in its existing form
Florence uses FHIR internally and normalises inbound data on ingestion, so plans keep current formats and channels. Supported inputs include X12 EDI, HL7 v2, C-CDA, NCPDP, SFTP extracts, proprietary feeds, and unstructured PDFs, faxes, and scans.
Standard and bespoke integration paths
Documented SDKs and APIs expose Anterior's production capabilities directly for common plan systems, with clear contracts for production traffic. Bespoke integration remains available wherever a plan's architecture requires a custom path.
Flexible deployment
Interface components can run standalone or embedded in existing plan systems. Florence operates as autonomous background agents or under human-in-the-loop review, fitting the plan's operating model rather than reshaping it.