Huntington National Bank faced the challenge of redacting sensitive data from over 400 million documents accumulated since 2015 in its on-premises document management system. As part of a 2025 proactive compliance initiative, the bank set out to process these documents, which come in different formats. Original estimates indicated this effort would take years, but by designing a scalable redaction workflow using Amazon Textract, Amazon SageMaker, AWS Step Functions, and AWS Lambda, Huntington reduced this timeline to months. Core requirements included data encrypted at rest and in transit, strict access requirements, services in-scope for PCI DSS compliance, outputs replicated back to on-premises data stores, and redaction accuracy meeting or exceeding 95%. To move documents, Huntington used AWS DataSync, AWS Direct Connect, Amazon S3, and AWS KMS to transfer over 400 million documents, encrypted in transit and at rest. Amazon Textract extracts text, tables, and forms from scanned documents, and Huntington used it to identify sensitive data such as Social Security numbers, account numbers, and personal addresses.