Proof of Coverage Extractor

Extract the insured, policy, coverage type, limits, certificate holder, and the in-force status from a proof of coverage letter or certificate PDF.

The full guide: Proof of coverage letter, limits and effective dates

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 Proof of Coverage Extractor.

What does the proof of coverage extractor read?

The certificate or document number and issue date, the named insured name and address, the policy number, the policy effective and expiration dates, the insurer name and NAIC number, the coverage type in force (enum), and whether the coverage is currently active (the is-active flag).

Which limits come out?

The each-occurrence limit, general aggregate limit, products and completed-operations aggregate, personal and advertising injury limit, deductible, and total amount or premium, alongside the certificate holder name and address, the additional-insured and subrogation-waived booleans, and the renewal date.

Are coverage lines returned as tables?

Yes. The coverage lines table returns each line with its insurer letter, coverage type, policy number, effective and expiration dates, and each-occurrence and aggregate limits, and an insurer list table returns each insurer letter, name, and NAIC number.

How is proof of coverage different from a binder?

A proof of coverage letter confirms an already-issued policy is currently in force as of the issue date. A binder provides TEMPORARY coverage before the full policy is issued. For temporary coverage use the binder extractor, and for a certificate of insurance use that dedicated tool.

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

The field labels follow the publicly distributed ACORD 25 certificate form. PDF only, up to 10MB and 100 pages. The letter 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.