TemplatesReview

Remove personal information

Find the personal details in a text, swap each one for a placeholder, change nothing else, and get a short list of what a person must still check before the text goes anywhere.

Sample results: runs and scores on this page are illustrations while testing is set up. How we test

  • Who it is for: Anyone who forwards notes, feedback or messages that name people, such as a coordinator, an office manager or a volunteer lead.
  • Time: 10 minutes

Download it, in the format you use

  • Prompt chain

    Copy each step into ChatGPT or Claude, one after another.

  • Checklist

    Follow the steps and check off the checks by hand.

  • Claude skill

    A folder Claude loads, so it follows the steps by itself.

  • n8n file

    Import into n8n and connect your own AI account.

Open in the Editor

Using a download:How to use this in n8nHow to install a Claude skill

How it runs

Select a part to see its prompt, input, output and check.

The same job, with and without the template

Sample

One plain prompt

Remove the personal information from this text. Keep job titles and the name of the town, Millbrook. (The same text is pasted below.)

Here is the text with the personal information removed:

Subject: Feedback on the October budgeting workshop

Hello team,

[Name], who attended on October 12, asked me to pass this on. She said the session ran well but the room was too warm, and she could not hear [Name] at the back. Dana lives at [Address], Millbrook and had to leave early to collect her son, so she would like the slides sent to [Email]. If anything is unclear, call her on [Phone] after 6 pm. She also mentioned that the only night-shift nurse at Hillside Clinic, a friend of hers, wants to join the next one. [Name]'s member number is [ID].

Thanks, Priya Workshop coordinator

All personal information has been removed, so this is safe to share.

Problem:It leaves "Dana" and "Priya" in the text, keeps "the only night-shift nurse at Hillside Clinic", and ends by saying all personal information has been removed.

With this template

The same input, run through the steps.

Result: 9 details replaced: 4 names, 1 street address, 1 email address, 1 phone number, 1 ID number, 1 indirect detail.

Cleaned text

Subject: Feedback on the October budgeting workshop

Hello team,

[Person A], who attended on October 12, asked me to pass this on. She said the session ran well but the room was too warm, and she could not hear [Person B] at the back. [Person A] lives at [Street address A], Millbrook and had to leave early to collect her son, so she would like the slides sent to [Email A]. If anything is unclear, call her on [Phone A] after 6 pm. She also mentioned that a night-shift nurse at [Workplace A], a friend of hers, wants to join the next one. [Person A]'s member number is [ID number A].

Thanks, [Person C] Workshop coordinator

Look at these yourself

  • "a night-shift nurse at [Workplace A]": in a small town, a night-shift nurse at one named place may still point to one person.
  • "collect her son" and "a friend of hers": family and personal details the table did not cover; cut them if the reader does not need them.
  • "[Person A], who attended on October 12" beside "Millbrook": a date and a town together can narrow down a small group.

Read the cleaned text yourself before you share it. An AI tool can miss a detail.

  • Check:Every detail is quoted word for word from the text: Nine details quoted word for word from the text; Millbrook and the job titles are left out because they may stay.
  • Check:Each kind is one of the seven allowed words: Nine rows, each kind one of the seven allowed words: 4 names, 1 street address, 1 email, 1 phone, 1 ID number and 1 indirect.
  • Check:No number appears that the original text does not have: Every number left in the cleaned text (12 and 6) is in the original.
  • Check:The reminder to read it yourself is in the final text: The closing line is there: Read the cleaned text yourself before you share it.
  • Check:No listed detail is left in the cleaned text: None of the nine details is left; the first name Dana on its own and the email address are both replaced.
  • Check:Only the listed details were swapped: Only the nine listed details were swapped; every other word, number and line break is as written.
  • Check:The counts add up to the table: The Result line says 9 details: 4 names, 1 street address, 1 email address, 1 phone number, 1 ID number and 1 indirect detail; the table has the same.
  • For your read:A person reads the cleaned text before it goes anywhere: Does a night-shift nurse at one named place still point to one person in a town as small as yours?

Runs and scores

Sample

Claude, Sonnet model

October 4, 2026, easy sample

  • Check:Every detail is quoted word for word from the text

    Two details quoted word for word from the text: Jordan Ellis and jordan.ellis@example.org.

  • Check:Each kind is one of the seven allowed words

    Two rows, each kind one of the seven allowed words: 1 name and 1 email.

  • Check:No number appears that the original text does not have

    Every number left in the cleaned text (18, 10 and 1) is in the original.

  • Check:The reminder to read it yourself is in the final text

    The closing line is there: Read the cleaned text yourself before you share it.

  • Check:No listed detail is left in the cleaned text

    Neither the name nor the email address is left in the cleaned text.

  • Check:Only the listed details were swapped

    Only the two listed details were swapped; every other word and number is as written.

  • Check:The counts add up to the table

    The Result line says 2 details: 1 name and 1 email address; the table has the same.

  • For your read:A person reads the cleaned text before it goes anywhere

    The date and the community hall are left in, so would they tell the reader anything you do not want to share?

Fixed: Nothing needed fixing: every check passed on the first pass.

Met 8 of 8

1 of these is for your read: the tool hands it to you.

ChatGPT, GPT model

October 5, 2026, tricky sample

  • Check:Every detail is quoted word for word from the text

    Eleven details quoted word for word from the text; Harbor Print, the support lead and Ticket 55120 are left out (the company name and a job title may stay, and a ticket number is not personal).

  • First pass failed:Each kind is one of the seven allowed words

    The first version said "phone number" for rows 4 and 7, and the Kind column must say exactly name, email, phone, street address, ID number, birth date or indirect.

  • Check:No number appears that the original text does not have

    Every number left in the cleaned text (12, 9 and 55120) is in the original.

  • Check:The reminder to read it yourself is in the final text

    The closing line is there: Read the cleaned text yourself before you share it.

  • Check:No listed detail is left in the cleaned text

    None of the eleven details is left; Amara on its own in the refund sentence is replaced too.

  • Check:Only the listed details were swapped

    Only the eleven listed details were swapped; the verb in "the price rose last year" and Ticket 55120 are as written.

  • Failed:The counts add up to the table

    The Result line says 5 names, but the table has 6 (Ms. Okafor, Amara Okafor, Rose Tran, Rose, Amara and Sam).

  • For your read:A person reads the cleaned text before it goes anywhere

    The order of 12 posters, the date May 9 and the ticket number are left in and together may still point to one customer, so will you check them before you share it?

Fixed: The label step ran again once with the seven allowed kind words restated, and every row then used one of them. The note step ran again once and the Result line still said 5 names, so the check failed again and the run stopped there and flagged it for you.

Met 7 of 8

  • Not met:The counts add up to the table: The Result line still says 5 names, but the table has 6.

1 of these is for your read: the tool hands it to you.

n8n, import format 2.20

October 6, 2026, typical sample

  • Check:Every detail is quoted word for word from the text

    Nine details quoted word for word from the text; Millbrook and the job titles are left out because they may stay.

  • Check:Each kind is one of the seven allowed words

    Nine rows, each kind one of the seven allowed words: 4 names, 1 street address, 1 email, 1 phone, 1 ID number and 1 indirect.

  • First pass failed:No number appears that the original text does not have

    The first version wrote [Person 1], [Person 2] and [Person 3], and the numbers 1, 2 and 3 are not in the original text.

  • Check:The reminder to read it yourself is in the final text

    The closing line is there: Read the cleaned text yourself before you share it.

  • Check:No listed detail is left in the cleaned text

    None of the nine details is left in the cleaned text.

  • Check:Only the listed details were swapped

    Only the nine listed details were swapped; every other word, number and line break is as written.

  • Check:The counts add up to the table

    The Result line says 9 details: 4 names, 1 street address, 1 email address, 1 phone number, 1 ID number and 1 indirect detail; the table has the same.

  • For your read:A person reads the cleaned text before it goes anywhere

    Will you decide whether to cut "collect her son" and "a friend of hers" before you share it?

Fixed: The rewrite step ran again once with the rule to use letters and never digits restated, and the placeholders then read [Person A], [Person B] and [Person C].

Met 8 of 8

1 of these is for your read: the tool hands it to you.

The steps, and the check on each

  1. Step 1: List every personal detail

    Pick out each detail that names or points to one person, quoted word for word, before anything is changed.

    Hands back: A numbered table of the personal details, each quoted from the text.

    Check:Every detail is quoted word for word from the text

    A plain rule. If it fails, run the step again (the n8n file does this for you).

  2. Step 2: Choose a placeholder for each detail

    Give each detail a kind and a placeholder, with the same placeholder for the same person.

    Hands back: A table that gives each detail a kind and a placeholder.

    Check:Each kind is one of the seven allowed words

    A plain rule. If it fails, run the step again (the n8n file does this for you).

  3. Step 3: Write the cleaned text

    Replace each detail with its placeholder everywhere it appears and change nothing else.

    Hands back: The text with each personal detail replaced by its placeholder.

    Check:No number appears that the original text does not have

    A plain rule. If it fails, run the step again (the n8n file does this for you).

  4. Step 4: Add the count and the reminder

    Put the count, the cleaned text and a short list of what a person must still check into one package.

    Hands back: A count line, the cleaned text, a list of what to check yourself, and the reminder line.

    Check:The reminder to read it yourself is in the final text

    A plain rule. If it fails, run the step again (the n8n file does this for you).

After the last step

  • Check:No listed detail is left in the cleaned text

    A second look by the AI. If it fails, run the step again (the n8n file does this for you).

  • Check:Only the listed details were swapped

    A second look by the AI. If it fails, run the step again (the n8n file does this for you).

  • Check:The counts add up to the table

    A second look by the AI. If it fails, run the step again (the n8n file does this for you).

  • Check:A person reads the cleaned text before it goes anywhere

    You check this one. If it fails, it is flagged for you.

What you need first

  • The text to clean(needed)

    Paste the text as it stands. Paste only what your rules let you put into an AI tool; if they say no, take the names and numbers out by hand instead.

  • What may stay(optional)

    For example job titles, or the name of a town. Leave empty if nothing may stay.

Ways to adapt it

  • This template does a careful first pass. It cannot promise that every personal detail is gone, and the last step says so. A person must read the cleaned text before it goes anywhere.
  • Paste only what your rules allow you to put into an AI tool. If they do not allow it, take the names and numbers out by hand and do not use this template on that text.
  • To let a kind of detail stay, such as dates or job titles, say so in the What may stay box. Details you name there are left out of the list.
  • To add a kind of detail, such as a license plate number, add it to the allowed kinds in the placeholder step and in its check, both.
  • For a long text, run one section at a time and keep the same letters for the same person in every section.

Change any step or check in the Editor, then download it again.

Try it with a sampleSample

A forwarded email with four names, a street address, an email, a phone number, a member number and a job that points to one person; the town and job titles may stay.

The text to clean
Subject: Feedback on the October budgeting workshop Hello team, Dana Whitfield, who attended on October 12, asked me to pass this on. She said the session ran well but the room was too warm, and she could not hear Marcus Lee at the back. Dana lives at 48 Alder Road, Millbrook and had to leave early to collect her son, so she would like the slides sent to dana.whitfield@example.org. If anything is unclear, call her on 555-0173 after 6 pm. She also mentioned that the only night-shift nurse at Hillside Clinic, a friend of hers, wants to join the next one. Dana's member number is MB-20418. Thanks, Priya Raman Workshop coordinator
What may stay
Keep job titles and the name of the town, Millbrook

The scoring guide

Sample

One criterion for each check, marked met or not met. (The guides in Quality rate a whole piece of work on three levels.) Under each one is how the three sample runs scored.

Download the scoring guide (Markdown)

  • Every detail is quoted word for word from the text

    A plain rule

    Meets:Every detail in the table is found word for word in the text.
    Does not meet:A detail has been reworded or corrected, or is not in the text word for word.
    Claude:Met
    ChatGPT:Met
    n8n:Met

  • Each kind is one of the seven allowed words

    A plain rule

    Meets:Every row has exactly one of name, email, phone, street address, ID number, birth date or indirect.
    Does not meet:A row has another word, such as phone number or address.
    Claude:Met
    ChatGPT:Met
    n8n:Met

  • No number appears that the original text does not have

    A plain rule

    Meets:Every number in the cleaned text is also in the original text.
    Does not meet:The cleaned text has a number the original does not, such as a placeholder written with a digit.
    Claude:Met
    ChatGPT:Met
    n8n:Met

  • The reminder to read it yourself is in the final text

    A plain rule

    Meets:The final text includes the line Read the cleaned text yourself before you share it.
    Does not meet:The line is missing, or it has been replaced by a claim that the text is safe to share.
    Claude:Met
    ChatGPT:Met
    n8n:Met

  • No listed detail is left in the cleaned text

    A second look by the AI

    Meets:No detail in the table is left in the cleaned text, whole or in part, including a first name on its own.
    Does not meet:A listed detail, or part of one, is still in the cleaned text.
    Claude:Met
    ChatGPT:Met
    n8n:Met

  • Only the listed details were swapped

    A second look by the AI

    Meets:Apart from the placeholders, every word, number and punctuation mark matches the original.
    Does not meet:A word was dropped, reworded or swapped by mistake, such as a verb that only looks like a name.
    Claude:Met
    ChatGPT:Met
    n8n:Met

  • The counts add up to the table

    A second look by the AI

    Meets:The Result line matches the table, in total and for each kind.
    Does not meet:A count on the Result line is different from the number of rows in the table.
    Claude:Met
    ChatGPT:Not met
    n8n:Met

  • A person reads the cleaned text before it goes anywhere

    You check this one

    Meets:You read the cleaned text from top to bottom, decided about each item under Look at these yourself, and looked for what the list missed.
    Does not meet:The cleaned text is shared without being read through by a person, or the items to check are skipped.
    Claude:For your read
    ChatGPT:For your read
    n8n:For your read

Claude: met 8 of 8 (including 1 for your read)

ChatGPT: met 7 of 8 (including 1 for your read)

n8n: met 8 of 8 (including 1 for your read)

Learn from this template

The AI swaps the details and a rule checks that nothing else changed. What it cannot judge is whether something still points to one person, such as a job title or a rare event. The last step ends with a reminder, and the final check is yours: you read the cleaned text first.

Where to see it: step 4 (Add the count and the reminder).

Read the guide: Where a person must look

More to read:Adapting a template

Practice:Check it yourselfWatch a check run

Which one fits?

Related templates

All Review templates

Review

Review

Review

Last run
October 6, 2026: n8n, import format 2.20 (sample run)
Tools and versions
Claude, Sonnet model; ChatGPT, GPT model; n8n, import format 2.20
What was checked
The files, against each tool’s import format, and 3 sample runs, each check’s finding recorded.
Version
1.0
What changed
First release.

Report a problem with this templateHow we test