Use cases · Claude
Anonymize documents before sharing them with Claude
Anonymize any document before it reaches an AI. Nothing leaves your device. Long contracts, reports and transcripts work just as well for analysis when the people and companies in them are labels.
- 0 network requests
- Works with Wi‑Fi off
- Free, no account
- Restore names afterwards
Why it matters
Why anonymize before you upload
Long context means more personal data per prompt
A 60-page contract or a year of meeting notes carries hundreds of names, emails and numbers. One anonymization pass replaces all of them consistently before the file leaves your machine.
Files in projects persist
Documents added to a project or a long conversation stay available for later prompts. Check the provider's data controls; sharing an anonymized copy keeps that footprint small.
The analysis does not depend on identities
Clause comparison, risk summaries and Q&A over a document work with Party A and Party B. Only you need to know who they are.
The mapping brings names back
Paste Claude's answer into the de-anonymizer with your mapping table and the labels turn back into the real names, in your browser.
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 and person names
- Company names and subsidiaries
- Email addresses and phone numbers
- Contract, case and reference numbers
- IBANs, tax IDs, registration numbers
- Addresses and site names
- Internal URLs and system names
- Signatures and witness names in scanned text
Before and after
What the AI sees
Original
This Agreement is made between Yurt Yazılım A.Ş. (tax ID 1234567890) and Mehmet Kaya, residing at Atatürk Cad. 12, Kadıköy.
Anonymized
This Agreement is made between Company A (tax ID Tax ID 1) and Person 1, residing at Address 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
Can I anonymize a whole PDF before uploading it?
Yes. Drop the PDF in; you get an anonymized DOCX and Markdown back. Scanned PDFs without a text layer are not supported; run OCR first.
Will Claude understand Person 1 and Company A?
Yes. Consistent labels are enough for summaries, comparisons and Q&A. Use fake names if you need the output to read naturally.
Does Claude train on my uploads?
That depends on the plan and settings you use. Check the provider's data controls. Anonymizing first removes the personal data from the equation.
Where does the anonymization run?
In your browser. There are 0 network requests during processing; you can verify it in the Network tab.
Other use cases