PII Detection Experiments
5 guided experiments to understand how PII detection
handles different types of personal information.
Pre-loaded for immediate exploration
✓ Free - no AWS charges
About this sample data
What is this data?
Simulated Freedom of Information request documents
What does it represent?
Typical UK council FOI submissions and responses
Important:
This is fictional data with no connection to any real council system
How was it generated?
Generated from anonymised FOI request patterns
What you'll learn: How different PII types are detected,
the role of confidence thresholds, and when human review is needed.
Experiments completed:
0 of 5
Available experiments
5 min
What you'll learn:
AI reliably detects standard PII: names, addresses, phone numbers
Expected response
All names, addresses, phone numbers and emails are redacted
Start experiment
Reset conversation
Mark as complete
5 min
What you'll learn:
AI can detect less obvious PII: staff IDs, case references
Expected response
Staff IDs and case references identified with lower confidence
Start experiment
Reset conversation
Mark as complete
10 min
What you'll learn:
Some place names may match person names - review is essential
Expected response
Some false positives flagged (e.g., 'Reading' detected as a name)
Start experiment
Reset conversation
Mark as complete
5 min
What you'll learn:
Lower threshold catches more PII but increases false positives
Expected response
Lower threshold redacts more items but includes false matches
Start experiment
Reset conversation
Mark as complete
5 min
What you'll learn:
Visual comparison helps understand what was redacted
Expected response
Clear visual comparison showing redacted sections
Start experiment
Reset conversation
Mark as complete
What's Next?
Architecture Tour
Understand how PII detection and redaction work together.
Take the tour
Test the Limits
Push the boundaries to understand edge cases.
Try challenges