Use cases · Finance
Anonymize financial spreadsheets before using an AI
Anonymize any document before it reaches an AI. Nothing leaves your device. Ledgers, statements and client lists keep their numbers and formulas; the accounts and people become labels.
- 0 network requests
- Works with Wi‑Fi off
- Free, no account
- Restore names afterwards
Why it matters
Why finance teams anonymize first
Account numbers are credentials
IBANs and card numbers can be misused on their own. They should not sit in a prompt history, even one you trust.
Client lists are the business
Who your customers are and what they pay is often the most confidential thing you have. Analysis works just as well with Client 1, Client 2.
The math does not change
Only text cells and comments are touched. Formulas, totals and pivots still compute on the anonymized workbook.
Checksum validation, not guessing
IBANs and card numbers are validated with their check digits before being replaced, so ordinary numbers are left alone.
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.
- Client and counterparty names
- IBANs and account numbers
- Card numbers
- Tax IDs and registration numbers
- Invoice, contract and transaction references
- Contact emails and phone numbers
- Addresses
- Employee names in payroll
- Sheet names and comments that mention clients
Before and after
What the AI sees
Original
Invoice INV-2026-0142, Yurt Yazılım A.Ş., 18 500 EUR, pay to TR33 0006 1005 1978 6457 8413 26, contact finance@example.com
Anonymized
Invoice Ref 1, Company A, 18 500 EUR, pay to IBAN 1, contact email1@example.com
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
Will formulas and totals still work?
Yes. Formulas and numeric cells are never rewritten; only text cells, comments and sheet names are scanned.
Are card numbers detected reliably?
Card numbers are validated with the Luhn check digit and IBANs with their mod-97 checksum, so false positives are rare.
Can I use realistic fake IBANs instead of labels?
Yes. Choose the fake-value strategy; the replacements look real but are generated and consistent per original value.
Is the workbook uploaded?
No. Everything runs in your browser; 0 network requests during processing.
Other use cases