The agents

Six AI agents. One claims operations layer.

Each agent runs on its own. Most TPAs start by deploying one or two on the workflow that hurts most, then expand the stack as their reviewers get comfortable working with agents in the loop.

Agent 01 / 06 Autonomous

Intake & Extraction Agent

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

Agent 02 / 06 Reasoning

Pre-Authorization Agent

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.

Tools: policy retriever · clinical summarizer · eligibility checker

Agent 03 / 06 Reasoning

Discharge Authorization Agent

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

Agent 04 / 06 Action-taking

Query Drafting Agent

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.

Tools: template library · evidence assembler · channel router

Agent 05 / 06 Investigative

FWA Signals Agent

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.

Tools: similarity index · provider profiler · pattern miner

Agent 06 / 06 Interop

NHCX Interop Agent

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

How an agent runs

From raw documents to a review-ready packet.

  1. STEP 01

    Ingest claim documents

    Pull pre-auth forms, bills, discharge summaries, investigation reports, and policy documents from email, hospital portals, your claims system, or APIs.

  2. STEP 02

    Extract medical, billing, and policy entities

    Classify documents, extract structured data, and link clinical context with billing line items and policy clauses.

  3. STEP 03

    Generate an evidence-backed claim summary

    Produce a concise summary with citations to the original document pages and the relevant policy text, ready for a medical or claims reviewer.

  4. STEP 04

    Route to your reviewer

    Assign to the right reviewer with completeness checks, suggested queries, and FWA flags ready for action.

  5. STEP 05

    Sync decisions back

    Push approvals, queries, enhancements, and discharge decisions back into your claims management system and to NHCX-aligned exchanges.

Fits your stack

Works alongside your claims system, not against it.

Slate Labs sits as a workflow and intelligence layer on top of your existing claims management system. We integrate where it helps and stay out of the way everywhere else.

Document intake

Email mailboxes, hospital portals, shared drives, SFTP drops, or direct API ingestion.

Claims management systems

Read and write through APIs or RPA bridges. Decisions and queries flow back into your system of record.

NHCX and insurer interfaces

Structured packets and FHIR-aligned data ready for NHCX exchange and insurer-specific formats.

Ready to see it on your own claim files?

Book a workflow review