Question 1

What is a discovery document index?

Accepted Answer

It is a file-by-file list of facts pulled from a production—such as dates, parties, amounts, exhibits, and Bates references—with source details beside each row.

Question 2

What can this discovery PDF extractor find?

Accepted Answer

It looks for dates, people or parties, dollar amounts, exhibit references, and Bates numbers in the text of each uploaded PDF. It is a first-pass index, not a relevance or privilege decision.

Question 3

Can it read scanned discovery PDFs?

Accepted Answer

Yes, when OCR can read the page: the tool reads selectable text first and applies OCR only to pages without a usable text layer. Review OCR-derived rows before relying on them.

Question 4

Does it add Bates numbers or create a privilege log?

Accepted Answer

No. It reports Bates references already visible in the PDFs; it does not Bates-stamp pages, decide privilege, or create a legal production log.

Question 5

How many PDFs can I upload at once?

Accepted Answer

A batch can contain up to 50 PDFs. Free processing covers 8 MB and 15 pages total, and one PDF can be up to 80 pages; larger free batches queue, while those hard limits reject.

Question 6

How do I review a fact from the production?

Accepted Answer

Each row keeps its source file, page, nearby text, reading method, and confidence score. Use those details to open the original PDF and verify the fact.

Question 7

What happens when a batch exceeds free processing?

Accepted Answer

The upload is accepted and marked queued when it exceeds 8 MB or 15 total pages, so no fake progress runs. A batch over 50 PDFs or a PDF over 80 pages is rejected; the waitlist covers future heavy processing.

Question 8

Are discovery PDFs stored, and is there an API?

Accepted Answer

PDF bytes are temporary and deleted after processing; the active review keeps extracted fields and source metadata, not the original files. There is no public API or posted paid-processing price in this version.

Stop searching discovery PDFs. Get the key facts in one place.

See a messy production become a review index.

Your results

No facts yet

Turn a discovery production into a review list.

Build a discovery index

Read text, then OCR

Keep the source beside it

Process a production batch

Export the fact list

Discovery PDF questions, answered.