Settlement Agreement Extractor

Extract the plaintiff, defendant, case number, settlement amount, release flags, and payment schedule from a settlement agreement PDF.

The full guide: Settlement amount, mutual release, and installments

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 Settlement Agreement Extractor.

What does the settlement agreement extractor read?

The document number and date, the effective and expiration dates, the plaintiff name and representative, the defendant name and representative, the case number, the court jurisdiction, the settlement amount and currency, and the dispute description.

Which release and clause flags come out as booleans?

Whether the agreement includes a mutual release, a confidentiality clause, a non-admission of liability, a covenant not to sue, and a waiver of jury trial each come back as booleans, alongside the governing law, the indemnification, the enforcement mechanism, the cap on liability, and the insurance requirement.

How are the payments and conditions returned as tables?

A payment schedule table returns each payment date, amount, currency, and method; a conditions precedent table returns each condition id, description, responsible party, and satisfaction date; and a signatories table returns each party name, title, signature date, and role.

Does it capture both signature dates?

Yes. The plaintiff signature date and the defendant signature date each come back as their own fields, alongside the signatories table, so you can see when each side executed the agreement.

Does the tool interpret the settlement or give legal advice?

No. It extracts the fields present on the agreement into structured data and gives no legal opinion on the release, enforceability, or terms. PDF only, up to 10MB and 100 pages; the document is processed for extraction only and is not retained.

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 legal and commercial teams, or the extraction API if you are building it in.