← All modules

Anonymization

Automatically detect and mask personal data. GDPR-compliant text analysis with automatic PII detection.

>95%
detection accuracy
15+
PII categories
100%
on German servers
The Challenge

One name in 10,000 texts

Finding personal data in free-text responses is like finding a needle in a haystack. One overlooked name, one forgotten email address – and you have a GDPR problem. Manual review is neither practical nor reliable.

  • GDPR fines up to €20M or 4% of annual revenue
  • Reputation damage from data breaches
  • Manual review misses an average of 15% of PII
Before → After

See Anonymization in Action

Original

Hi, I'm John Smith (john.smith@company.com). Please call me back at 555-123-4567. My address is 123 Main Street, New York, NY 10001.

Anonymized

Hi, I'm [NAME] ([EMAIL]). Please call me back at [PHONE]. My address is [ADDRESS].

1x Name1x Email1x Phone1x Address
Compliance

Meets the Highest Standards

GDPR Art. 25
Privacy by Design & Default
GDPR Art. 32
Technical Safeguards
GDPR Art. 89
Research Processing
CCPA
California Privacy Rights
Detected Data Types

Automatic PII Detection

Names

John Doe → [NAME]

Emails

john@company.com → [EMAIL]

Phone

+1 555 1234567 → [PHONE]

Addresses

123 Main St → [ADDRESS]

IBAN

DE89 3704... → [IBAN]

Custom

Define your own rules
Features

Privacy at the Highest Level

PII Detection

Automatic detection of names, emails, phone numbers, addresses and more.

Flexible Masking

Choose between replacement, pseudonymization or complete removal.

Configurable Rules

Define your own detection rules and exceptions for your use case.

Audit Trail

Complete documentation of all anonymization steps for compliance.

Three Methods

Choose the right approach

Depending on your requirements, you can fully anonymize, consistently pseudonymize, or generalize for maximum analyzability.

Redaction

Complete removal – the text is replaced by [REMOVED] or similar placeholders.

John Smith → [NAME]

Ideal für: Maximum security when the original value doesn't matter

Pseudonymization

Consistent replacement – the same person always gets the same placeholder.

John Smith → Person_A (everywhere in the text)

Ideal für: When you need to preserve relationships between people

Generalization

Replacement with general categories – context is maximally preserved.

john@company.com → [EMAIL]

Ideal für: When context matters, but not the exact data

GDPR Compliant by Design

Anonymize data before analysis – this way you can process sensitive text data in a GDPR-compliant manner.

  • Processing before storage
  • Documented processes
  • Audit trail
  • Configurable rules
Use Cases

Especially Important For

HR & Employee feedbackPatient dataCustomer feedbackSupport ticketsInternal surveysResearch data
FAQ

Frequently asked questions

Combine with other modules

See your open responses as structure – not as a wall of text

Start directly with your own data or validate your use case with guidance – including stakeholder assurance.

Free Beta
No credit card required
Personal support
GDPR-compliant
Made in Germany