Distribution Agreement Extractor

Extract the supplier, distributor, territory, products, exclusivity, minimum commitment, discount, and termination terms from a distribution agreement PDF.

The full guide: Exclusive territory and MFN in a distribution agreement

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 Distribution Agreement Extractor.

What does the distribution agreement extractor read?

The agreement number, the signing date, the effective and expiration dates, the supplier (manufacturer) name and address, the distributor (reseller) name and address, the territory where the distributor may sell, and the description of the products or product lines covered.

Which commercial terms come out as fields?

Whether the distributor has exclusive rights (a boolean), the minimum purchase commitment, the payment terms, the distributor discount rate off wholesale price, the warranty terms, and the renewal term of the agreement.

Does it capture the CUAD-style protective clauses?

Yes. The anti-assignment, change-of-control, most-favored-nation, non-compete, audit-rights, insurance, cap-on-liability, termination-for-convenience, and post-termination-services clauses each come back as their own fields, alongside the governing law and the termination clause.

Are the products, pricing, and territories returned as tables?

A products table returns each product id, name, category, and SKU; a pricing schedule table returns each tier with its minimum quantity, unit price, discount percent, and currency; a territories table returns each region and whether it is exclusive; and a payment schedule table returns the terms, days due, and early-payment discount.

What are the file limits and privacy terms?

PDF only, up to 10MB and 100 pages. The agreement is processed via the Talonic API for extraction only, 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 legal and commercial teams, or the extraction API if you are building it in.