Policy Endorsement Extractor

Extract the policy number, endorsement type, coverage changes, premium adjustment, limits, and effective dates from an insurance endorsement or rider PDF.

The full guide: Policy endorsement or rider, the premium adjustment

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 Policy Endorsement Extractor.

What does the policy endorsement extractor read?

The endorsement or rider document number and date, the policy number being modified, the endorsement effective and expiration dates, the named insured name and address, the insurer name and NAIC number, the producer name and contact, and the endorsement type and coverage type (both enums).

Which coverage-change fields come out?

The coverage change description (added, removed, or amended), the coverage change amount, the premium adjustment, the each-occurrence and general aggregate limits, and the conditions and exclusions introduced, alongside the additional-insured and subrogation-waived booleans, the certificate holder, and the authorizing name and date.

Are the changes returned as tables?

Yes. The coverage changes table returns each change with its type, amount, and effective and expiration dates, and a coverage lines table returns each line with its coverage type, policy number, effective and expiration dates, and occurrence and aggregate limits.

How is an endorsement different from a binder or the base policy?

An endorsement or rider MODIFIES an already-issued, in-force policy — it references the base policy number and adjusts coverage or premium. A binder provides temporary coverage before the policy issues, and the base policy itself is a separate document. For those, use the binder extractor or the insurance policy extractor.

Which forms does it follow, and what are the limits?

The field labels follow the publicly distributed ACORD forms (ACORD 25, 125, 126, and 140). PDF only, up to 10MB and 100 pages. The endorsement 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.