Drop in a set of discovery PDFs. Get dates, parties, dollar amounts, exhibits, and Bates references with the source file and page beside each one.
Every fact stays linked to its file, page, reading method, and confidence.
Upload PDFs to see dates, people, amounts, exhibits, and Bates numbers here.
What you get
Made for the first pass through a set of discovery PDFs.
Dates, people, amounts, exhibits, and Bates numbers land in one table.
It reads the PDF text first and uses OCR only on pages without usable text.
Each row keeps its file, page, nearby text, and confidence.
Upload up to 50 PDFs and watch each file move through the batch.
Take the full index with you as CSV or JSON.
Before you upload
Short answers about files, limits, storage, and review.
Upload PDFs from your discovery set. The tool reads selectable text and uses OCR on pages without a usable text layer.
A batch can contain up to 50 PDFs, but free processing covers 8 MB and 15 pages total. Larger or longer batches are accepted and placed in the heavy-work queue.
The app stores the PDF files and batch details so the worker can process them and you can check progress. It does not automatically delete them after processing.
It looks for dates, parties, dollar amounts, exhibits, and Bates references, then keeps nearby text for review. Check the results before relying on them.
High, medium, and low show how strong each match looks. The score and whether it came from OCR stay with the row, but neither guarantees the value is right.
The app has POST /api/upload and POST /api/extract routes. There is no public API key or developer signup in this version.
The upload is accepted, then checked on the server before extraction. If the batch is over 8 MB or 15 pages total, it is marked queued and the waitlist form appears; batches over 50 PDFs are still rejected.
It is free for now. There is no pricing, checkout, or payment flow on this page.