Property Insurance Claim Extractor

Extract the claim and policy numbers, insured, loss date and type, claim amount, deductible, and adjuster from a property insurance claim PDF.

The full guide: Property insurance claims and ISO construction class

How should we start?

Build with Talonic

Need to scale? Create an API key, then run this from your own code or an agent.

Create an API key

Free account required

Start with a document

Upload a file or pick a sample, and see the fields come back.

No signup · nothing stored

Questions about Property Insurance Claim Extractor.

What does the property insurance claim extractor read?

The claim number and filing date, the loss date, the policy number with its effective and expiration dates, the named insured with address, phone, and email, the insurer name and NAIC number, and the producer (agency or broker) name and contact.

Which loss and coverage fields come out?

The loss type (fire, theft, water, wind, earthquake, or vandalism), the loss description, the coverage type, the claim amount, the deductible, the each-occurrence limit, the general aggregate limit, and the claim status (pending, approved, denied, paid, or under review).

Does it capture the building underwriting details?

Yes. The construction type, the year built, the insured building value, the occupancy type, the ISO protection class, and the property description come back as fields, following the ACORD 140 property section labels.

Are the damage items and repair estimates returned as tables?

A damage items table returns each item with its description, damage type, claimed amount, estimated replacement cost, and status; a repair estimates table returns each contractor, estimate date, cost, and scope; a property locations table also comes back for multi-location claims.

What are the file limits and privacy terms?

PDF only, up to 10MB and 100 pages. The claim is processed via the Talonic API for extraction, is not retained for training, and is not shared. Redact personal contact details where you can.

Doing this to one file, or to ten thousand?

The tool reads a single document. The platform reads the whole estate once and keeps it queryable — the same engine, with a memory.

See PDF to Markdown if you run this for data and platform teams, or the extraction API if you are building it in.