Adjuster Report Extractor

Extract the claim, policy, adjuster, loss type, estimated and approved amounts, damaged items, and repair estimates from an adjuster report PDF.

The full guide: Insurance adjuster report: cause of loss and estimate

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 Adjuster Report Extractor.

What does the adjuster report extractor read?

The document number and date, the claim number and policy number, the insured name and address, the adjuster name and license number, the insurer name and NAIC number, the coverage type (enum), and the policy effective and expiration dates.

Which loss and valuation fields come out?

The loss date, inspection date, and loss location address, the loss type (enum, such as fire, water, theft, collision, wind, or vandalism), the loss description, the estimated loss amount, the approved amount, the deductible, and the coverage status (enum, such as covered, denied, partial, pending, or suspended).

Are the damaged items and repair estimates returned as tables?

Yes. A damaged items table returns each item description, damage description, loss type, estimated value, repair estimate, and approved amount; a coverage summary table returns each coverage type, policy limit, deductible, status, claimed amount, and approved amount; and a repairs and estimates table returns each repair item, contractor, estimated cost, approved cost, and priority.

How is this different from a claim filing or loss run?

An adjuster report is the adjuster assessment of a single loss, with damage line items and an approved amount. A claim filing (FNOL) opens the claim, and a loss run summarizes many past claims on a policy. For those, use the claim filing extractor or the loss run extractor.

What are the file limits and privacy terms?

PDF only, up to 10MB and 100 pages. The report is processed via the Talonic API for extraction only, is not retained for training, and is not shared.

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 document data extraction if you run this for underwriting and claims teams, or the extraction API if you are building it in.