Extract the insured, policy, loss date and cause, claimed amount, sworn-statement flag, and itemized items lost from an insurance proof of loss PDF.
The full guide: Proof of loss statements and the amount sworn to
Need to scale? Create an API key, then run this from your own code or an agent.
Create an API keyFree account required
Upload a file or pick a sample, and see the fields come back.
No signup · nothing stored
A proof of loss is the sworn statement an insured files stating the amount of a claim. The extractor reads the document number and submission date, the insured name and address, the policy number with its effective and expiration dates, the insurer name and NAIC number, the loss date, description, and location, the loss cause (enum), and the claimed amount with its currency.
Yes. The sworn-statement boolean (whether the claim was made under oath), the claimant signature date, the supporting documents array, the witness information, the deductible, the each-occurrence limit, the coverage type, and the adjuster name and contact each come back as fields.
Yes. The items lost table returns each item with its description, category, quantity, unit value, total value, depreciation percentage, and salvage value; a loss circumstances table returns each circumstance type, description, and contributing factor; and a witnesses table returns each witness name, address, phone, email, and relationship to the loss.
A proof of loss is the insured’s sworn statement of the amount they claim. An adjuster report is the insurer’s independent assessment of the loss, and an FNOL is the first notice that opens the claim. For those stages, use the adjuster report extractor or the FNOL extractor.
PDF only, up to 10MB and 100 pages. The proof of loss is processed via the Talonic API for extraction, is not retained for training, and is not shared.
The tool reads a single document. The platform reads the whole estate once and keeps it queryable — the same engine, with a memory.
See document data extraction if you run this for underwriting and claims teams, or the extraction API if you are building it in.