Pay Application Extractor

Extract the application number, period, contract sum, work completed, retainage, and current payment due from an AIA G702 pay application PDF.

The full guide: AIA G702 pay application: work completed and retainage

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 Pay Application Extractor.

What does the pay application extractor read?

The application number and date, the billing period from and to dates, the project name and location, the contractor name and license number, the owner name, and the architect or engineer overseeing the project, following the AIA G702 layout.

Which payment figures come out?

The original contract sum, the net change by change orders, the contract sum to date, the total completed and stored to date, the work completed this period, the retainage and retainage percentage, the total earned less retainage, the previous certificates, and the current payment due.

Does it compute progress against the contract?

The percent complete and the balance to finish come back as fields, and because the continuation sheet is returned as rows, the completion of the whole application reconciles against the sum of the line items.

Is the schedule of values returned as a table?

Yes. The schedule of values table returns each line item with its number, description, scheduled value, work completed in previous and current periods, materials presently stored, total completed and stored, percent complete, balance to finish, and retainage, following the AIA G703 continuation sheet.

What are the file limits and privacy terms?

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