Letter of Intent Extractor

Extract the parties, transaction type, amount, binding status, exclusivity, conditions precedent, and milestones from a letter of intent (LOI) PDF.

The full guide: Binding status and exclusivity from a letter of intent

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 Letter of Intent Extractor.

What does the letter of intent extractor read?

The document number and date, the effective and expiration dates, the initiating party and counterparty names, addresses, and contact persons, the transaction type (enum) and description, the total amount and currency, and the execution date.

Does it capture whether the LOI is binding?

Yes. The binding status (boolean), the confidentiality clause and exclusivity clause flags, the exclusivity period, the governing law, and the dispute resolution method each come back as fields, so whether the letter creates obligations is captured.

How are the conditions and milestones returned as tables?

The transaction terms table returns each term with its description and value; the conditions precedent table returns each condition, its type, and responsible party; the timeline milestones table returns each milestone with its target date and owner; and a key deliverables table returns each deliverable, its type, owner, and due date.

Which deal-protection fields come out?

Whether a material adverse change clause applies, the break fee amount, whether financing and regulatory approval are conditions, the payment terms, and the indemnification, limitation of liability, and change of control flags each come back, alongside the signatories.

What are the file limits and privacy terms?

PDF only, up to 10MB and 100 pages. The letter 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.