Anonymize an Excel file for AI — in your browser
Most working data lives in Excel. Data Alias reads the first sheet of an XLSX workbook entirely in your browser — no upload, no server-side conversion — then applies the same column classification and cell-level detection as CSV: suggested rules for name, email, and phone columns, plus scans for credentials, contact details, and identity numbers buried in text cells.
How it works, step by step
Upload your XLSX workbook
Drop the .xlsx file into the workspace (up to 10 MB). The first sheet is parsed in your browser; the file itself never leaves your machine. XLSX is a Pro format — free to use during the beta.
Review the suggested rules per column
Column headers get suggested data types (person, company, email, phone, identifier) with matching protection rules, and every cell value is scanned for emails, phone numbers, IPs, API keys, national ID numbers, and payment card numbers. Nothing is applied until you review and confirm the rules.
Download the safe copy for the AI tool
The safe copy exports as a .safe.csv of the first sheet — honestly named, because Data Alias does not rebuild a workbook. That flat, aliased copy is exactly what the AI tool can ingest for analysis.
Example: q3-accounts.xlsx → q3-accounts.safe.csv
Why anonymize before you upload?
Because the answer depends on which tool you use, which account you are signed into, and what its defaults happen to be this month. A copy that never contained real identities does not depend on any of that. Here is what each vendor documents about its own handling.
ChatGPT (OpenAI)
Opting out of training is not the same as no retention
Consumer ChatGPT lets you opt out of model training via Data Controls, but OpenAI's own documentation notes retention for abuse monitoring — up to 30 days even for content you delete. An opt-out changes what training sees, not whether your pasted data reaches and briefly lives on OpenAI's servers.
Source: OpenAI Data Controls FAQ ↗Business-tier defaults are not consumer defaults
OpenAI documents that business tiers default to not training on customer data — but much real-world pasting happens in personal accounts, where the defaults and retention rules differ. A copy that never contained real identities doesn't depend on which account type someone used.
Source: OpenAI enterprise privacy ↗Claude (Anthropic)
The consumer training default changed in 2025
In August 2025 Anthropic updated its consumer terms, presenting the data-for-training choice pre-checked in favor of sharing — consumer users had to actively opt out to keep chats out of training. Defaults like this can change again; a file that only ever contained aliases is indifferent to them.
Source: Anthropic consumer terms update ↗Settings are per-account, your data policy isn't
Whether a given Claude account opted out is invisible to you when a file gets shared onward or pasted by a colleague. Anonymizing before upload is the control that travels with the file rather than with the account settings.
Source: Anthropic consumer terms update ↗Gemini (Google)
Human reviewers can read consumer conversations
Google documents that conversations in the consumer Gemini apps may be read by human reviewers to improve the service. That is a documented process, not a leak — and it is exactly why pasting a customer list into a consumer chat deserves an anonymized copy instead of the original.
Source: Google Gemini Apps privacy notice ↗A reviewed conversation should contain aliases, not identities
If a conversation can be sampled for review, the safest version of your file is one where the reviewer would see PERSON_001 and EMAIL_002 rather than real people. The analysis quality is the same; the exposure is not.
Source: Google Gemini Apps privacy notice ↗These are each vendor's own documented behaviors as of our research (July 2026). Policies and defaults change — an anonymized copy is the control that doesn't depend on them.
What to know about excel files
First sheet only, by design
Data Alias reads the first sheet of the workbook. If the data you need lives on another sheet, move it first or export that sheet separately — the review table shows you exactly what was read, so nothing is silently skipped.
The output is a CSV, not a rebuilt workbook
Rebuilding an .xlsx with formulas and formatting would invite silent mistakes, so the safe copy is a clean .safe.csv of the sheet's values. For AI analysis that is the more useful shape anyway — flat rows with consistent aliases.
Common questions
- Which sheet does Data Alias read?
- The first sheet of the workbook. Other sheets are not read or exported. If your data is on a different sheet, move it to the front or save it as its own file before uploading.
- Why is the download a .safe.csv instead of an .xlsx?
- Because Data Alias does not rebuild workbooks, and we won't pretend otherwise. The safe copy is a flat CSV of the first sheet's values with aliases applied — which is the format AI chat tools handle best.
- Is Excel support free?
- XLSX is a Pro-plan format, and everything including Pro features is free during the beta. The Free plan covers CSV and TXT.
An honest note on detection
Data Alias reduces exposure risk but cannot catch every sensitive value, and no automated detector can. That is why nothing is applied without your review: check the safe copy before you share it with an AI tool or anyone else.
No account needed. Files stay in your browser — verify it yourself.
Related guides
Every format is covered in the full guide index.