Redact discovery documents in bulk — and keep the receipts.
Before a production goes to opposing counsel or a filing hits PACER, the sensitive data has to come out — Social Security and financial-account numbers, names, dates of birth, home addresses. Doing it by hand in Acrobat, one rectangle at a time across thousands of pages, is exactly where a missed name or an un-redactable black box slips through. Lacuna auto-detects sensitive spans across the whole production, lets you review every one, removes them from the PDF's text layer, and records every decision in a hash-chained tamper-evident audit log.
A black box in a filing is a problem waiting to surface.
A filled rectangle over text is just an object painted on top — the characters are still in the content stream underneath, recoverable by anyone who copy-pastes or runs pdftotext. It's how redactions in high-profile court filings have been undone after they were filed.
FRCP Rule 5.2 requires those identifiers be redacted from filings — a black box that's still recoverable doesn't accomplish that, and “concealed but recoverable” is the gap behind inadvertent-disclosure motions and embarrassing corrections. The visible page is only half of it: PDFs also carry metadata, embedded files, and prior revisions that leak the same information.
Redact the production, not one page at a time.
A 5,000-page production is the same three steps as a single exhibit.
Upload a single exhibit or a full production. Lacuna finds SSNs, financial-account numbers, names, addresses, phone numbers, and dates of birth across every page automatically.
You see every detected span in context and decide what goes and what stays. Lacuna surfaces the patterns; it doesn't decide what's privileged — every call is yours. Mark a passage for removal, keep what's discoverable, or flag a span for a second read. Nothing is touched until you commit.
Lacuna removes the approved text from the PDF's text layer and runs a sanitization pass that strips embedded files, scripts, attachments, and document metadata. What you download is a clean PDF, ready to produce.
The output is the same bytes you can re-verify yourself with pdftotext — not a “trust us” black box.
If a redaction is ever questioned, show your work.
Every job is written to a hash-chained tamper-evident audit log: which spans were detected, what you kept, what you removed, and when you committed it. Each entry is linked to the one before it by a SHA-256 hash, so an altered or dropped record breaks the chain.
The log records that a redaction happened, never what was underneath it — so it's safe to put in front of a court or opposing counsel without re-exposing the very data you removed. If an inadvertent-disclosure or clawback question ever comes up, you can account for exactly what was done.
Client files don't get shipped to someone else's AI.
Detection runs on Lacuna's own infrastructure — a deterministic pattern engine plus a compact AI model that labels sensitive spans on our workers. Neither pass transmits your page text to any third-party AI service. There's no “we'll just run it through a chatbot” step happening out of sight.
Privileged and client material isn't copied into an outside vendor's logs to be processed. Source files are deleted from primary storage when the job completes; encrypted backups are purged on a fixed schedule. The full retention and deletion model is spelled out here.
Produce with confidence.
Bulk PDF redaction with a tamper-evident audit log — priced for the firm that bills hourly, not the AmLaw 200.