FOI Redaction Walkthrough
Step-by-step guide to experiencing AI-powered PII detection and redaction for FOI requests
Great! You've deployed the demo
Now let's walk through what you just deployed and see it in action.
Start WalkthroughChoose your next step
Generate Evidence Pack
Create your business case documentation with what you've learned.
Generate Evidence PackTry AI-Powered FOI Redaction
10 minutes to see AI automatically detect and redact personal information
This walkthrough guides you step-by-step through uploading an FOI response document and reviewing AI-detected personal information. Perfect for FOI officers, information governance teams, and anyone evaluating AI for reducing manual redaction work.
What you'll do
In this 10-minute walkthrough, you'll:
- Access the redaction interface - Find your deployed AI redaction service (2 minutes)
- Download a sample FOI document - Get a realistic FOI response to test with (1 minute)
- Upload and process the document - Watch AI detect PII in real-time (2 minutes)
- Review detected PII with confidence scores - See what the AI found and how confident it is (3 minutes)
- View redacted output - See the document with PII replaced by redaction markers (2 minutes)
Before you start
Deploy the FOI Redaction scenario if you haven't already. Deployment takes 4-6 minutes.
Sample documents check
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
For FOI officers
- How AI reads FOI response documents
- Which types of PII can be automatically detected
- Time saved vs manual line-by-line review
- Accuracy and confidence scores for each detection
- When human review is still needed
For information governance managers
- Potential processing time reduction (80% time savings)
- Volume of FOI requests that could benefit
- Compliance risk reduction (fewer missed PII)
- Return on investment calculation
- Integration with existing FOI workflows
Sample documents you'll use
We've prepared 3 realistic FOI response documents representing common request types:
Personal information we detect
The AI automatically identifies these types of personal information (PII):
- Person names - Full names, first names, surnames
- Addresses - UK postal addresses including postcodes
- Phone numbers - Mobile, landline, including area codes
- Email addresses - Personal and work email addresses
In addition, the system can detect UK-specific identifiers like National Insurance numbers.
The wow moment
After you upload an FOI response, you'll see AI automatically:
- Find all PII locations - Even across multiple pages and sections
- Show confidence scores - 95-99% accuracy on typed documents
- Generate redacted output - PII replaced with markers like [REDACTED: NAME]
- Preserve document structure - Everything else remains readable
All in under 30 seconds. No manual highlighting. No missed personal details. No transcription errors.
Think about your council
How many FOI requests does your council process annually?
Consider the time savings. Our example calculation:
- Current state
- 500 FOI requests/year × 30 minutes manual redaction = 250 hours/year
- With AI redaction
- 80% auto-redaction, 20% manual review = 50 hours/year
- Time freed
- 200 hours saved for complex exemptions and policy work
- Annual cost benefit
- 200 hours × £25/hour = £5,000 saved per year
Committee language: "Implementing AI redaction reduces FOI processing time by 80%, freeing 200 hours annually while improving compliance by ensuring consistent PII detection."
Takes approximately 10 minutes