Find and redact personal data in documents

Data protection teams find personal data in documents and redact it

Needs setupAI Act: no extra obligationsReading & capturing documentsAll industries

Fits: HR · Legal & compliance · Office, administration & casework

For subject access requests, file inspections or disclosure to third parties, the AI finds names, addresses, account numbers and health information in large volumes of documents. You check in a targeted way instead of page by page.

Is this for you?

  • You regularly have to release documents and redact third parties’ personal data, such as for subject access requests, file inspections or publications.
  • It involves many pages of emails, scans and minutes, not individual cases.
  • You have or are planning a redaction tool that really removes content instead of just covering it.
First step today

Write a short test text with made-up names, addresses, an IBAN and a piece of health information, and use the template below to have it searched. Check what was missed, especially information without names.

How to go about it

  1. Define document types and what is to be redacted
  2. Collect all documents to be released
  3. Have the locations marked
  4. Check suggestions and gaps
  5. Redact permanently and release
  6. Analyse what was missed and refine the categories

Templates to copy

Try it now
in the training
Analyse
in the training
Plan the rollout
in the training
Included in the training

The complete guide

  • 6 steps explaining exactly what to do
  • 3 proven templates to copy into your own AI
  • Safe use: data, checking, deciding, informing
  • Pitfalls, effort and how to recognise success

With the training you get all 430 guides for as long as your access runs.

See the trainingOne-off per person, no subscription

Same approach, other use cases

13 more use cases follow the pattern “Reading & capturing documents”.

A-089 · Legal status 08.10.2026