Construction Change Order Extractor

Extract the change order number, description, reason, cost adjustment, time impact, approvals, and line items from a construction change order PDF.

The full guide: AIA G701 change order: contract sum adjustment

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 Construction Change Order Extractor.

What does the construction change order extractor read?

The change order document number, the issue date, the project name and number, the original contract number, the contractor name and address, the owner name and address, and the architect name, following the AIA G701 change order layout.

Which change and cost fields come out?

The change order number, the description of the work added, deleted, or revised, the reason for the change, the change order amount adjusting the contract sum, the total amount and any tax amount, and the currency of all figures.

Does it capture the schedule and approval status?

Yes. The contract time adjustment in days, the schedule impact narrative, the change order status, the requestor name, the approval date, and the approving signature all come back, alongside the effective date and payment terms.

Are the change order line items returned as a table?

The change order items table returns each line with its number, description of work, quantity, unit, unit price, line amount, and CSI MasterFormat code; an approvals table returns each approving party, name, approval date, and signature.

What are the file limits and privacy terms?

PDF only, up to 10MB and 100 pages. The change order 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 PDF to Markdown if you run this for data and platform teams, or the extraction API if you are building it in.