Property and casualty claims intake (Canada)
Early access use case for reading auto and property claim documents into structured records with human review.
Documents in
- Claim notices
- Auto policy declarations
- Repair estimates
- Police or collision reports
- Ontario accident benefit forms
- Medical reports
- Adjuster notes
- Workers' compensation reports and decisions
How it runs
-
Intake
Claim documents are uploaded or sent via API and tracked as processing jobs.
-
Text extraction and OCR
Text is extracted from digital files and scanned pages, including faxed copies, are read with OCR.
-
Classification and schema matching
Documents are classified and matched to a schema. The early-access property and casualty and workers' compensation packs supply the document types and starter schemas.
-
Field extraction
Policy, loss, party and amount fields defined in the schema are extracted with confidence values.
-
Human review
Uncertain fields and unmatched documents pause for an adjuster or claims analyst to correct and approve.
-
Summary and output
Summaries are generated and results delivered via API and webhooks.
What you get
- Structured claim record with per-field confidence
- Mixed claim files sorted by document type and filed into province and loss-type folders
- Reviewer-confirmed values before downstream use
- Searchable claim documents
Early access
Canada is opening gradually. The property and casualty pack and the workers’ compensation pack are built and deployed in early access. Each ships document types, starter schemas, cross-document indexes, sample questions and smart folders, with English and French keywords and CAD by default. Social Insurance Numbers are reduced to the last 3 digits, and personal and health fields are flagged sensitive. The packs are built from official form guidance and regulator documents and have not been validated on production customer documents. Forms and fields are being confirmed with early customers. AI processing location is stated in the Order Form.
Where review fits
Review gates work as in any Droqify deployment, so adjusters confirm uncertain fields before release. Reviewers compare documents using extracted data and search. The pack prepares and checks document data; it does not decide claims.