Use cases · Legal
Anonymize contracts and case files for AI review
Anonymize any document before it reaches an AI. Nothing leaves your device. Parties become Party A and Party B consistently across the whole file, so clause analysis and drafting still work.
- 0 network requests
- Works with Wi‑Fi off
- Free, no account
- Restore names afterwards
Why it matters
Why lawyers anonymize first
Privilege and confidentiality
Client identity, case numbers and facts are confidential. Sending them to a third-party service is a disclosure you have to justify; sending an anonymized copy is a much smaller step.
The task is about the clauses, not the names
Summarize the indemnity, compare two NDAs, list the obligations: none of it needs the real parties. Consistent labels keep cross-references intact.
Court documents identify people beyond the parties
Witnesses, experts, judges and third parties appear in pleadings and judgments. Detection catches them; your dictionary catches the ones specific to the matter.
You keep the key
The mapping table stays on your machine. Restore names in the AI's output with the de-anonymizer when you need the final text.
How to do it
Four steps, all in your browser
- 1
Upload the file or paste the text
Word, PDF, PowerPoint, Excel, CSV, JSON, HTML, Markdown or plain text. Up to 10 files, 50 MB each. The file is opened in your browser tab and never sent anywhere.
- 2
Choose the rule
Decide how each category is rewritten: labels like Person 1 / Company A, realistic fake values, masking or redaction. Optionally enable smart detection and add words to your dictionary.
- 3
Review what will change
Names, companies, emails, phone numbers, IDs and IBANs are listed with their replacements. Turn items off, add missed ones, correct a category. Nothing changes until you confirm.
- 4
Download and paste into the AI
You get the same file back, a Markdown version to paste into the chat, and a mapping table. Paste the AI's answer into the de-anonymizer to put the original names back.
What to replace
Checklist for this domain
The tool detects most of these automatically. Add the rest to your dictionary so they are replaced consistently.
- Party names (persons and companies)
- Case, docket and file numbers
- Court and chamber names, if identifying
- Addresses of parties and properties
- IBANs and account numbers
- Tax IDs, registration and national ID numbers
- Dates of birth, hearing dates if identifying
- Lawyer, witness and expert names
- Signatures and notary references
Before and after
What the AI sees
Original
Case no. 2025/1432: Yurt Yazılım A.Ş. v. Mehmet Kaya. The defendant, residing at Atatürk Cad. 12, Kadıköy, shall pay 48 000 TRY to TR33 0006 1005 1978 6457 8413 26.
Anonymized
Case no. Case 1: Company A v. Person 1. The defendant, residing at Address 1, shall pay 48 000 TRY to IBAN 1.
Try it now
Anonymize your document here
Nothing is uploaded. Switch Wi‑Fi off if you want to check.
- 1Upload
- 2Choose rule
- 3Review
- 4Download
Upload
Drop files here or choose
Up to 10 files · 50 MB each · files stay on your device
- docx
- pptx
- xlsx
- txt
- md
- csv
- json
- html
Old .doc, .ppt and .xls files: save them as .docx, .pptx or .xlsx first.
Questions
Common questions
Are cross-references kept consistent?
Yes. Every occurrence of a party gets the same label throughout the document, including in headers, footnotes and tables.
Can I anonymize a scanned judgment?
Only if it has a text layer. Run OCR first, then anonymize the resulting DOCX or PDF.
How do I add matter-specific terms?
Add them to your dictionary in the options: project code names, property names, unusual spellings. They are replaced with the label you choose.
Does the file leave my computer?
No. Parsing, detection and rewriting run in your browser; 0 network requests during processing.
Other use cases