How PII Detection Works

Choose your path: a visual tour with diagrams, or a hands-on console tour exploring the AWS infrastructure.

Architecture Tours

Visual Architecture Tour

How documents flow through PII detection and redaction

10 min

  1. Document Upload

    Your FOI document is uploaded securely to AWS

  2. Comprehend PII Detection

    Amazon Comprehend identifies personal information

  3. Confidence Scoring

    Each detected entity receives a confidence score

  4. Redaction Applied

    PII above threshold is redacted from the document

  5. Audit Report Generated

    A report documents what was redacted and why

Console Architecture Tour

Navigate AWS Console to understand PII detection infrastructure

15 min Requires deployed stack

  1. Comprehend PII Detection

    What to look for: PII entity types, confidence scores, detection results

  2. Lambda Redaction Function

    What to look for: Redaction logic, threshold configuration, audit logging

  3. S3 Document Storage

    What to look for: Original and redacted document buckets, encryption settings

  4. CloudWatch Audit Logs

    What to look for: PII detection events, redaction audit trail

What's Next?

Test the Limits

Push the boundaries to understand edge cases.

Try challenges

Production Guidance

Learn what changes for FOI compliance.

View guidance