Insurance Application Extractor

Extract the applicant, coverage type and limits, effective dates, premium, and property details from an ACORD insurance application PDF. No signup.

The full guide: ACORD 140 property and ACORD 126 liability sections

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 Insurance Application Extractor.

What does the insurance application extractor read?

The application or policy number and date, the named insured name and address, the applicant date of birth, phone, and email, the business description, the coverage type being applied for (such as Commercial General Liability or Auto), the requested coverage amount, and the proposed effective and expiration dates.

Which coverage limits and carrier fields come out?

The each-occurrence limit, general aggregate limit, products and completed-operations aggregate, and personal and advertising injury limit, plus the insurer name and its NAIC number and the producer (agency or broker) name and contact.

Are coverage lines and property details returned as tables?

Yes. The coverage lines table returns each line with its insurer letter, coverage type, policy number, effective and expiration dates, and occurrence and aggregate limits; an insurer list, a property locations table (address, construction type, year built, building value, occupancy type, protection class), and a beneficiaries table also come back.

Which forms does it follow?

The field labels follow the publicly distributed ACORD forms used across the US market (ACORD 25, 125, 126, and 140), so the certificate holder, the additional-insured and waiver-of-subrogation flags, and the description of operations all map to the same fields across commercial applications.

The form has personal details. What happens to it?

The application is processed via the Talonic API for extraction only, is not retained for training, and is not shared. Redact personal details such as the date of birth where you can. PDF only, up to 10MB and 100 pages.

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.