Demand Letter Extractor

Extract the claimant, defendant, demand amount, basis of claim, payment deadline, and damages breakdown from a demand letter PDF. No signup.

The full guide: Claimant, amount, and deadline from a demand letter

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 Demand Letter Extractor.

What does the demand letter extractor read?

The document number and date, the claimant name, address, and contact info, the defendant name and address, the demand description, the total amount and currency, the basis of claim, and the payment deadline. It reports these fields as written and gives no legal advice.

Which payment and interest fields come out?

The payment terms and instructions, the interest amount and interest rate, the consequences of non-compliance as stated on the letter, the prior correspondence date, and the negotiation status (enum) and notice type (enum) each come back as fields.

Are the claim items and damages returned as tables?

Yes. The claim items table returns each item description, amount, basis, and sequence, and the damages breakdown table returns each damage category, amount, explanation, and date incurred, so the total demanded reconciles against its line items.

Does it capture the attorney details?

The attorney name, contact, and bar number, the law firm name, the governing law, the effective and expiration dates, and the supporting and reference documents (as arrays) each come back as fields.

Does the tool advise on how to respond or draft one?

No. It only extracts the fields present on the letter into structured data. It does not draft demand or collection language, does not advise on how to respond, and gives no legal opinion. PDF only, up to 10MB and 100 pages; the letter 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.