📎 Add a claim PDF
Drag a PDF here or click to browse — handwritten & scanned packets welcome
Drag a PDF here or click to browse — handwritten & scanned packets welcome
or try a sample packet:
A synthetic auto bodily-injury claim, ready to process
11-page packet plus prior policy, driving, and medical records. Click Process this claim to run the extraction, history-assembly, and validation pipeline.
📄 Source packetPage 1 / 11
🖼 Extracted image Layout Parser
Diagram detected in the police report and attached to the narrative, tied to its source page.
Crash diagram · rear-end impact, both vehicles northbound p.2
Key fields Custom Document Extractor
Predefined fields pulled from the packet. Each carries a source-page citation and a confidence score — click a citation to jump to the page.
📈 Chronological history & insights medical + driving
A single timeline merging the claimant's prior policy, driving, and medical history with this claim's treatment — the combined view surfaces pre-existing conditions, causation continuity, and liability signals an adjuster can act on.
Derived insights by persona
🔍 Source reliability & hard pages where Document AI struggles
Handwriting, figures at page edges, and rough scans are where Document AI drops confidence. The pipeline detects those regions and recovers the value with a targeted deterministic script or routes it to a human — it never silently guesses.
Medical chronology (this claim) date-ordered
Treatment for this loss, ordered by the date parsed from the record text, each with provider, source page, and confidence.
Business values & reconciliation
Monetary values extracted, then reconciled — the itemized charges are summed and checked against the stated total.
🛡 Validation agent human-in-the-loop
A separate agent scores the output and triages what a human must review before settlement — it does not decide.
Generated narrative high-fidelity grounded
Composed against business rules, grounded strictly in the packet. Every claim carries an inline citation.
On GCP this pipeline is Cloud Storage → Document AI (OCR + Custom Extractor + Layout Parser) → Vertex embeddings + Vector Search → Gemini (high-fidelity grounding) → Gen AI Evaluation Service, orchestrated with a durable workflow, wrapped in VPC-SC + CMEK + audit logging. This prototype runs the same logic on a synthetic packet.