PII Scrubber for Plan Uploads

Overview

When you upload plan PDFs to the marketplace, BlueClerk automatically scans each page for personally identifiable information (PII) like owner names, addresses, and phone numbers, then removes them before storing the file. This protects homeowner privacy and ensures your plans can be sold without exposing sensitive customer data.

How It Works

Automatic Scanning

Every uploaded plan PDF is processed through Claude Vision AI:

1. Each page is scanned for owner names, addresses, and phone numbers
2. PII locations are identified with precise coordinates
3. White rectangles are drawn over detected PII using pdf-lib
4. The cleaned PDF is stored in place of the original
5. Upload response shows how many PII items were removed

What Gets Removed

• Owner names - Homeowner or property owner names on title blocks
• Street addresses - Physical addresses of properties
• Phone numbers - Contact numbers on plans

Graceful Fallback

If PII scrubbing fails for any reason:

• The original PDF is stored instead of blocking your upload
• Upload continues normally - you're never prevented from adding plans
• The system logs the error for admin review

Upload Feedback

Single Plan Upload

After uploading a single plan, you'll see:

• Success message confirming the upload
• PII count showing how many items were removed (if any)

Example: "Plan uploaded successfully. 3 PII items removed."

Bulk ZIP Upload

After uploading a ZIP of plans:

• Summary stats showing total plans processed
• Combined PII count across all plans in the batch

Tips

• Review your plans before uploading to understand what personal info might be present
• Title blocks are the most common location for owner names and addresses
• The scrubber works automatically - no configuration needed
• Plans remain fully usable after scrubbing - only PII is removed

Questions

Q: Will scrubbing affect plan quality or legibility? A: No. Only detected PII is covered with white rectangles. Dimensions, room labels, notes, and all other plan information remain intact.

Q: What if the AI misses some PII? A: The AI is highly accurate but not perfect. Review your plans before uploading and contact support if you notice any PII that wasn't removed.

Q: Can I see what was removed? A: The upload response tells you how many PII items were found and removed, but doesn't list specific text for privacy reasons.

Q: Does this work for both single and bulk uploads? A: Yes. PII scrubbing runs automatically on every plan PDF whether you upload one file or a ZIP with 100 plans.

Q: What happens if scrubbing fails? A: Your upload continues with the original PDF. The system logs the failure for review but never blocks your upload.