Anonymise a résumé before an AI reads it
Two different people need this page. Recruiters who want a model to summarise or compare candidates without the identifying details that drive bias, and candidates who want feedback on their own CV without handing a chatbot their address and phone number.
The preset removes names, contact details, addresses, postcodes, social handles and personal URLs while leaving employers, job titles, dates and skills intact — the parts an assessment is actually supposed to be about.
Your text
Safe to paste
Preset: identity and contact details out, employers and history kept.
Mapping — 0 values (only visible in this tab)
| Placeholder | Real value | Uses |
|---|
Check a few rows before you paste — this is the fastest way to spot a detector that grabbed the wrong thing. Nothing here is stored or sent anywhere.
What to look for — 30 detectors, custom terms, exceptions
People & organisations
Government & health IDs
Financial
Technical & secrets
Location
Step 3 — paste the AI’s answer here to put the real values back
The model replies using the placeholders. Paste its answer below and every
[NAME_1] becomes the real name again — using the mapping held in this tab, which
is the only copy that exists.
How it works
- Open this page — the detectors are already set for “Résumés & CVs”.
- Paste your text, or drop a .txt, .md, .csv, .json or .log file onto the panel.
- Check the highlights: every match is coloured by type, and one click keeps a type as-is.
- Copy the safe version and paste it into the AI tool of your choice.
- Paste the model’s reply back into step 3 to restore the real values.
Blind screening only works if it is consistent
Removing a name is the easy half. The signals that leak identity through a CV are the address, the personal domain, the social handles, the volunteer work, the alumni association and sometimes the phrasing of a hobby. If you strip names but leave “linkedin.com/in/aoifebrennan” in the text, you have removed the appearance of bias without removing the input.
The preset therefore switches on URLs and @handles, which are off by default elsewhere on the site, and leaves employer names on — those belong in the evaluation. If your process also blinds employers or universities, switch company names on and add the institutions to custom terms.
If you are the candidate
Asking a model to critique your CV is one of the genuinely good uses of these tools, and it is also one of the easiest ways to hand over a complete identity profile: full name, home address, phone, email, employment history and dates, in one paste. Scrubbing costs you nothing here, because the feedback you want — structure, clarity, whether the achievements are quantified — does not depend on your address.
One asymmetry worth knowing: your CV is a document you control, but once pasted into a consumer chatbot it may be retained and, on the default settings of several consumer plans, used for training. Opting out of training changes the training question, not the retention one.
Tips
- Recruiters: keep the mapping open in the tab so you can restore the real name when you shortlist.
- Candidates: replace the company you are applying to with a custom term if you would rather not have it in the prompt.
- Ages, graduation years and “20+ years of experience” are all age proxies — decide deliberately whether they stay.
Detectors are pattern-based and imperfect: read the highlighted output before you paste it anywhere, and confirm your own confidentiality obligations against the current rules for your profession, employer or jurisdiction. Compiled 2026-07-29.
Frequently asked questions
Does anonymising a CV remove hiring bias?
It removes some inputs to it. Research on blind screening shows mixed results — bias can re-enter through career gaps, school names, phrasing and later interview stages. Removing identity from the text is a reasonable step, not a solution to bias in hiring.
Can I scrub several CVs at once?
Yes — paste them one after another into the same box, or drop a text export. Every candidate keeps a distinct, stable placeholder, so a model can compare “[NAME_1]” against “[NAME_2]” without knowing either.
Are the candidate’s details stored anywhere?
No. The text lives in the tab until you clear it or close it. There is no upload, no account, and no analytics attached to what you type — the only thing this site persists is which detectors you switched on.