Loss Run Extractor

Extract the insured, policy number, carrier, and every claim with its loss date, status, paid, and reserve amounts from an insurance loss run PDF.

The full guide: Loss run claim history with paid and reserve split

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 Loss Run Extractor.

What is a loss run and what does this tool extract from it?

A loss run is the claims history an insurer issues for a policyholder. The extractor reads the report number and date, the named insured and address, the policy number with effective and expiration dates, the insurer name and NAIC number, and the coverage type with its per-occurrence and general aggregate limits.

Are the individual claims returned as a table?

Yes. The claims table returns one row per loss with the claim number, loss date, description, status, claimed or incurred amount, amount paid to date, reserve amount, deductible, coverage type, and the date the claim was reported.

Can it total paid losses and reserves for a policy?

The paid amount, reserve amount, and deductible are extracted per claim, so the incurred (paid plus reserves) figure that underwriters use to price a renewal can be summed straight from the rows without re-keying.

Does it read loss runs across different carriers and lines?

The field labels follow ACORD form conventions used across the US market, so general liability, commercial auto, umbrella, and workers compensation loss runs from different carriers map to the same columns. The policy coverages table records the limits per policy.

What are the file limits and privacy terms?

PDF only, up to 10MB and 100 pages. The loss run is processed via the Talonic API for extraction, 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.