Slate Labs/Claims OS
Each Claims OS workflow deploys a team of purpose-built AI agents — the right tools, coordinated reasoning, and a clean handoff to your reviewer.
The agent workflows
Each workflow runs a team of purpose-built AI agents across one stage of the claims pipeline. Start with the one that hurts most: pre-auth, discharge, or FWA. Expand from there as your reviewers see what each workflow actually delivers.
Reads pre-auth forms, ICPs, bills, prescriptions, investigation reports, discharge summaries, and policy documents. Handles scanned PDFs, images, and email attachments. Classifies, extracts, and links clinical, billing, and policy entities into a structured claim record.
Tools: OCR · document classifier · entity linker
Checks claim completeness, summarizes diagnosis and treatment, validates eligibility against policy terms and exclusions, and prepares a one-screen reviewer packet with citations to the source pages and clauses.
Agents read the insurance policy, check treatment guidelines, and cross-reference the clinical packet — then surface a structured recommendation.
Tools: policy retriever · clinical summarizer · eligibility checker
Reconciles final bills, discharge summaries, package rules, tariffs, and policy sub-limits to support faster discharge decisions and final settlement. Highlights non-payable items and ineligible charges with the supporting clause.
Tools: tariff matcher · clause linker · bill reconciler
Drafts structured queries to hospitals, members, or internal teams with evidence and missing-document context attached. Tracks responses and follows up. Reviewer reviews and sends, never starts from a blank screen.
Agents pull the relevant sections from the admission packet and policy documents to draft precise, traceable queries.
Tools: template library · evidence assembler · channel router
Flags duplicate claims, suspicious billing patterns, unusual provider behaviour, and policy inconsistencies for your investigation team. Investigators get a packet with the supporting evidence already pulled together, not a raw alert.
Agents cross-reference billing codes, provider history, and policy rules to flag anomalies before they reach adjudication.
Tools: similarity index · provider profiler · pattern miner
Prepares structured, interoperable claim data from messy documents to support NHCX-aligned exchange with insurer and hospital partners. FHIR-shaped where it matters, with insurer-specific adapters where needed.
Tools: FHIR mapper · schema validator · insurer adapters
Under the hood
Each Claims OS workflow doesn't run a single AI model — it runs a coordinated team of purpose-built agents. One reads the policy. One extracts from the clinical packet. One reasons across both. One flags. One formats for your reviewer. Coordinated automatically. You see one clean, traceable output.
How a workflow runs
Pull pre-auth forms, bills, discharge summaries, investigation reports, and policy documents from email, hospital portals, your claims system, or APIs.
Classify documents, extract structured data, and link clinical context with billing line items and policy clauses.
Produce a concise summary with citations to the original document pages and the relevant policy text, ready for a medical or claims reviewer.
Assign to the right reviewer with completeness checks, suggested queries, and FWA flags ready for action.
Push approvals, queries, enhancements, and discharge decisions back into your claims management system and to NHCX-aligned exchanges.
System integration
The Claims OS runs as an intelligence and workflow layer between your claims management system and your exchange partners. It reads from your CMS, routes through the AI agent workflows, and writes structured decisions back.