Anonymize an HR or payroll spreadsheet before an AI analyses it
Drop an Excel or CSV export from your HR or payroll system. Employee names, staff IDs and national insurance numbers become codes; departments, salaries and day counts stay readable, so ChatGPT or Claude can still compare pay by team or spot outliers. Restore its table here.
Restoring uses the key of this tab: code your text here first, keep this tab open, then come back with the answer.
Adjust
See the key (it stays in this tab)
The key links each code to the real value. It exists only in this tab's memory: close or reload the tab and it is gone.
connect-src 'none' in its security policy) and loads no analytics. Turn Wi-Fi off once the page has loaded: the tool works just the same. The engine is the one inside the Hidden Tokens app.How it works
1 · Code
Paste a text or drop a file. Names, companies, addresses, emails, phone numbers, bank details, ID and case numbers become codes such as NAME-001 or COMPANY-001. Unknown proper nouns are coded too: when in doubt, the engine codes.
2 · Send the codes
Copy the coded text, or download the coded file, and give it to ChatGPT, Claude, Gemini or Copilot. The AI reasons on the codes: it still knows who did what, not who they are.
3 · Restore
Paste the AI's answer in the Restore tab, in the same browser tab. The codes become the real names again, on your screen only.
Example: six columns of a payroll export
Employee,Employee ID,NI number,Department,Annual salary,Sick days 2026
Fiona Gallacher,E1042,QQ 12 34 56 A,Finance,52000,3
Tomasz Wierzbicki,E1057,QQ 65 43 21 B,Warehouse,28500,11
Ama Mensah,E1063,QQ 11 22 33 C,Sales,41000,0Employee,Employee ID,NI number,Department,Annual salary,Sick days 2026
FIRSTNAME-001 NAME-001,REF-001,ID-001,Finance,52000,3
NAME-002 NAME-003,REF-002,ID-002,Warehouse,28500,11
NAME-004 NAME-005,REF-003,ID-003,Sales,41000,0Names, staff IDs and national insurance numbers are coded; department, salary and sick days stay readable for the analysis. Note the last column: sick days are health-related data. If the AI does not need them, delete the column before coding.
Payroll data is the most sensitive file in the building
A payroll file combines everything people care about: who earns what, who was off sick, who has a garnishment order. Even with names coded, a small team can be re-identified: if there is one person in Legal, “Legal, 74,000” is that person.
- Remove the columns the question does not need. Asking for average pay by department needs neither sick days nor dates of birth. A deleted column cannot leak.
- Group small teams. If a department has one or two people, merge it into a wider group before sending, or the AI can point to them.
- Check what stayed readable. Job titles are ordinary words and stay readable; “Head of Payroll” can be one named person in your company.
The free tool handles up to 1,000 rows and one file at a time, with a new key each time. For monthly payroll runs, the Hidden Tokens app keeps one key per folder, so an employee keeps the same code from January to December, and recognises HR columns from their headers.
The free tool or the Hidden Tokens app?
This free tool
- One text or one file at a time
- Up to 3,000 words or 1,000 spreadsheet rows
- The key lives in this tab and disappears when you close it
- Word, Excel, CSV and text
The Hidden Tokens app
- Whole folders: the same person keeps the same code in every document
- One key per case file, kept on your computer
- PDF and scanned documents, read on your computer
- Inside Claude Desktop, and in ChatGPT, Gemini and Copilot with the extension
- Industry packs, firm rules and a signed proof of what the AI saw
A word on the word “anonymize”
Strictly speaking, this tool pseudonymizes: each value is replaced by a code that can be reversed with the key. Under the GDPR, pseudonymised data is still personal data for whoever holds the key, which here is you, in this tab. What the AI receives no longer names anyone directly. Clues can remain, such as a job, a town and an age together: the tool warns you when it sees them. Read the result before sending it.
Questions
Will the AI still compute averages and totals?
Yes. Salaries stay numbers and each employee keeps one code across the file, so averages, medians and totals by department work. Restore the AI's table here afterwards.
Is health data such as sick leave protected?
Only identifiers are coded. A sick-day count or an absence reason stays readable. Remove such columns when the question does not need them.
What about a file larger than 1,000 rows?
The free tool stops at 1,000 rows. Split the file, or use the Hidden Tokens app, which has no limit and keeps the same codes across files.
Is this enough for the GDPR?
No tool makes processing compliant on its own. Coding removes direct identifiers from what the AI receives; deciding what to send and whether to send it stays with you.
Other ways to use the free tool
By file type
By AI tool
By task
For whole folders, use the app
Hidden Tokens codes whole case files on your computer with one key, works inside Claude Desktop and in your browser, reads PDFs and scans, and puts the real names back into Word and Excel files.