Privacy Protection (PII)
The Privacy Protection tile lets AI-School automatically check chat messages for personally identifiable information (PII) before they are sent to the AI. Per category, you configure how the system handles detected data.
What is PII protection?
PII stands for Personally Identifiable Information personal data that can directly or indirectly identify a person, such as e-mail addresses, social security numbers, credit card details or phone numbers.
When PII protection is enabled, user chat messages are analysed before they reach the AI. Depending on the configured action per category, data is passed through, anonymised, masked or blocked.
Activating PII protection
The Privacy Protection tile is located in the Security & Privacy area of the management environment.
- Go to the management environment
- Select the Privacy Protection tile
- Enable the Activate PII protection toggle
- Set the desired action per category
- Click Save
Available actions per category
| Action | Description |
|---|---|
| Pass through | The information is forwarded unchanged. Use this for data that poses no risk. |
| Anonymise | The information is fully replaced by a placeholder (e.g. jan@school.nl [EMAIL]). The AI does not see the real data. |
| Mask | The information is partially hidden (e.g. ****-****-****-1234). The type is recognisable but the full value is not. |
| Block | The chat message is fully blocked and not sent to the AI. Use this for very sensitive information. |
Available categories
| Category | What is detected |
|---|---|
| E-mail addresses | Addresses such as jan@example.com |
| Credit card numbers | Visa, Mastercard and other cards |
| Social Security / BSN Numbers | 9-digit BSN numbers |
| Phone numbers | Dutch and international formats |
| IBAN / Bank account numbers | National and international IBAN numbers |
| IP addresses | IPv4 and IPv6 addresses |
| Passport / ID numbers | Passport and identity card numbers |
| Medical information | Medical terms and health information |
| URLs | Web links and page addresses |
| MAC addresses | Network device MAC addresses |
How does medical information detection work?
The Medical information category uses heuristic keyword matching rather than pattern recognition. The system scans chat messages for medical terms in both Dutch and English:
| Dutch | English |
|---|---|
| diagnose / diagnoses | diagnosis |
| medicijn / medicatie | medication |
| allergie / allergie�n | allergy / allergies |
| bloeddruk | blood pressure |
| hartslag | heart rate |
| cholesterol | cholesterol |
| diabetes | diabetes |
| insuline | insulin |
| pati�nt | patient |
| symptoom / symptomen | symptom |
| behandeling | |
| operatie |
Limitations
- False positives a sentence like "The company operation went smoothly" may be flagged as medical.
- False negatives a rare condition or brand name not in the list will not be detected.
Use Anonymise for medical information (the default setting). The exact medical term is replaced by a placeholder, so the AI retains context without seeing the specific data. Use Mask if you only want to partially hide the term.
Read-only access
Administrators with read-only rights can view the settings but not modify them. Contact AI-School if you need to make changes but lack sufficient permissions.
See also
- Restrictions configure usage limits
- System Prompts guide AI behaviour via system instructions