Workers Compensation Extractor

Extract the employee, employer, injury, wages, disability benefit rates, insurance carrier, and claim status from a workers compensation filing PDF.

The full guide: Average weekly wage on a workers compensation claim

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 Workers Compensation Extractor.

What does the workers compensation extractor read?

The claim or case number (document number) and filing date, the injury date, the employee name, ID, and date of birth, the employer name and address, the injury type (enum) and the body part affected, and the description of the incident.

Which wage, benefit, and medical fields come out?

The average weekly wage and currency, the temporary and permanent disability benefit rates, the insurance carrier, the medical provider name and address, the date of maximum medical improvement, the return-to-work date, the total amount, and the payment status (enum).

Are the medical and wage records returned as tables?

Yes. The medical treatment records table returns each treatment date, type, provider, and cost; the wage history table returns each period gross wages and hours worked; the benefit payments table returns each payment date, amount, benefit type, and reference; and an injury details table returns body part, classification, severity, and occupational-disease flag.

Does it capture the claim status and appeal?

The claim status (enum), the appeal status (enum), the attorney name, the governing law, and the effective and expiration dates each come back, so the stage the claim has reached is captured.

The filing has medical and personal details. What happens to it?

The filing is processed via the Talonic API for extraction only, is not retained for training, and is not shared. Redact the employee ID, date of birth, and medical details 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 PDF to Markdown if you run this for data and platform teams, or the extraction API if you are building it in.