Skip to content
unformation

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
Anonymize your document here

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. 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. 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. 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. 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.

  1. 1Upload
  2. 2Choose rule
  3. 3Review
  4. 4Download

Upload

Drop files here or choose

Up to 10 files · 50 MB each · files stay on your device

or
  • docx
  • pptx
  • xlsx
  • pdf
  • txt
  • md
  • csv
  • json
  • html

Old .doc, .ppt and .xls files: save them as .docx, .pptx or .xlsx first.

0 network requests during processing

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

More situations