Anonymise student data before you use an AI tool

Teachers use chatbots to draft feedback, rewrite IEP language and summarise incident notes — and school records are education records the moment they identify a student. This preset removes student and guardian names, student IDs, emails, phone numbers, dates of birth and addresses, and leaves the substance of the note intact.

FERPA’s de-identification test is a judgement, not a checklist: under 34 CFR 99.31(b)(1), information stops being covered when there is no reasonable basis to believe the remaining record can be used to identify a student. In a class of twenty-eight, that bar is higher than it sounds.

Replace with
network while you type: 0 requests

Your text

0 characters

Safe to paste

waiting for text
The cleaned version appears here as you type — highlighted so you can see exactly what changed.
CtrlEnter
no personal data yet Everything below happens in this browser tab. Nothing is uploaded, and nothing you type is saved.

    Preset: student and guardian identifiers, IDs and contact details.

    What to look for — 30 detectors, custom terms, exceptions

    People & organisations

    Government & health IDs

    Financial

    Technical & secrets

    Location

    For the things no word list can know: internal codenames, unusual surnames, a product that isn’t public yet. Custom terms are never saved.
    Values on this list stay in the text and out of the mapping — useful when the model needs your own company name to answer usefully.
    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

    1. Open this page — the detectors are already set for “Student data”.
    2. Paste your text, or drop a .txt, .md, .csv, .json or .log file onto the panel.
    3. Check the highlights: every match is coloured by type, and one click keeps a type as-is.
    4. Copy the safe version and paste it into the AI tool of your choice.
    5. Paste the model’s reply back into step 3 to restore the real values.

    Small cohorts break pattern-based de-identification

    The identifiers are the easy part. The hard part is that a school note describes a person inside a very small group. “The Grade 7 student with a peanut allergy who left mid-lesson three times this term” names nobody and identifies one child to anyone in the building. That is the mosaic effect the FERPA standard is written to catch, and no detector can see it.

    The workable habit is to scrub the identifiers here and then rewrite the specifics: replace exact dates with “earlier this term”, drop the class period, and generalise anything unique. If you cannot generalise it without losing the point, that is a signal the note should not be leaving your systems at all.

    Guardians count too

    Parent and guardian names, emails and phone numbers are personal data in their own right, and they identify the student directly. They are included in the preset for that reason — a note addressed to “Ms Haddad” about “your son” is not de-identified in any useful sense.

    Staff names are a separate decision. They are detected as names by default; if you want them kept — because the model is drafting an email that has to be signed — add them to the “never redact” list rather than switching name detection off.

    Tips

    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 removing names make a record FERPA-de-identified?

    Not by itself. The regulation asks whether there is no reasonable basis to believe a student can still be identified, taking other available information into account. Names are the first step; class size, dates and unique circumstances are what usually decide the answer.

    Is it safe to paste an IEP into a chatbot after scrubbing?

    Special-education records are among the most sensitive documents a school holds, and many districts prohibit putting them into external tools regardless of redaction. Check the policy first; where AI is allowed, use the sanctioned tool rather than a consumer account.

    Does this site see anything I paste?

    No. There is no server-side processing and no upload endpoint. You can verify it by turning off your network connection — the tool keeps working, because everything happens in the browser tab.