Purchase Order Change Extractor

Extract the original PO reference, change reason, revised quantities, prices, dates, and changed line items from a purchase order change PDF.

The full guide: Extract data from purchase order changes

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 Purchase Order Change Extractor.

What does the purchase order change extractor read?

The change or document number, the issue date, the original PO number and date it amends, the change reason (enum, such as quantity adjustment, price revision, delivery date change, cancellation, or suspension), the change details, and the buyer and supplier names, addresses, and contacts.

How is a PO change different from the original purchase order or a change order?

A purchase order change is an amendment to an existing PO: it references the original PO number and carries only the deltas, such as a revised quantity, price, or delivery date. The purchase order is the original order, and a change order amends a broader contract scope and value. For the original order use the purchase order extractor; for a contract amendment use the change order extractor.

Which revised totals and terms come out?

The currency, the total change amount, the tax amount, the line extension total, the payment terms, the delivery date, the delivery address, the delivery terms (incoterms), and the count of affected lines each come back as fields.

Are the changed line items returned as a table?

Yes. The line items table returns each line with its line number, the original line number it maps to, item code and description, the quantity change, the new total quantity, the unit price, the line amount, the line tax amount, and the line delivery date.

Which reference fields come out, and what are the file limits?

The accounting cost center, the customer reference, and any free-form note each come back as fields. PDF only, up to 10MB and 100 pages; processed via the Talonic API for extraction only and 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 freight and customs teams, or the extraction API if you are building it in.