License Agreement Extractor

Extract the licensor, licensee, product, license type and scope, fee, term dates, and the key clauses from a software or IP license agreement PDF.

The full guide: Software license agreement: audit rights, escrow

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 License Agreement Extractor.

What does the license agreement extractor read?

The licensor and licensee names and addresses, the product name, the license type (perpetual, subscription, floating, concurrent, named-user, or site), the license scope, the license fee and currency, the payment terms, and the effective and expiration dates.

Are the licensed products returned as a table?

Yes. The licensed products table returns each product with its license type, scope, fee, and currency, and a usage terms table returns each restriction with its type, detail, and what it applies to, so a multi-product agreement comes back as rows.

Which CUAD clauses does it capture?

The license grant, IP ownership assignment, source code escrow, cap on liability and uncapped liability, audit rights, change of control, exclusivity, covenant not to sue, and the irrevocable-or-perpetual, non-transferable, and anti-assignment provisions are each read as their own field.

Does it read renewal and support terms?

The renewal terms, the maintenance-and-support-included flag, and the termination clause come back as fields, and the renewal schedule table returns each renewal date, term length, auto-renewal flag, and conditions. The field set follows the CUAD clause taxonomy.

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, 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.