Redaxa · Privacy, before AI

Detection reference · Personal data · Updated 2026-11-03

Personal names

Detecting names reliably needs to know which words are names, and a pattern cannot. Redaxa flags a name only in the one place where it is almost certainly a person: right after a greeting. For everything else, use protected terms.

At a glance

Reported asPersonal name
CategoryPersonal data
Severitylow: a weak identifier that depends on context, such as a name or an IP address
Replaced with[NAME]
Where it runsThe same engine runs in the Chrome extension (free checks, on your device), in the web check and the Windows app (on Redaxa's server; the text is not stored) and in public repository checks.
Engine rulescanner.ts, line 196

What it looks like

Dear, Hi, Hello or Hey, then one or two capitalised words, then a comma or colon. Generic salutations (team, all, everyone, there, sir, madam and similar) are skipped.

Example

You paste

Hi Marco Bianchi, thanks for the draft.

Redaxa returns

Hi [NAME], thanks for the draft.
Reported asPersonal name
Severitylow: a weak identifier that depends on context, such as a name or an IP address
Replaced with[NAME]

All values on this page are synthetic or published specimens; none is a working credential or a real person's data.

In a repository check

The same example, committed to a public repository and run through the free repository check:

Values are always shown masked in repository reports. No key is ever tested against its provider.

What it does not flag

What to do

Swap names for consistent placeholders (Client A, Person B) before you paste. For the names you meet every day, add them as protected terms so every check flags them.

Check before you paste

The free Chrome extension runs this check inside ChatGPT, Claude, Gemini and Perplexity before a message is sent, on your device and with no daily limit. On the web you get 5 free prompt checks a day with no account.

Add the Chrome extensionTry a free web check

Related

Sources