Oldcastle APG accelerates proof-of-delivery document processing with Amazon Textract and Amazon Bedrock

Oldcastle APG, one of the largest global networks of manufacturers in the architectural products industry, was processing 100,000–300,000 ship tickets per month across more than 200 facilities.

Its existing OCR system was unreliable, only reading 30–40% of documents accurately and requiring constant maintenance and manual intervention.

AWS and Oldcastle APG built an event-driven document processing workflow to automate proof-of-delivery processing and improve visibility across deliveries.

1. 01Process a high volume of proof-of-delivery ship tickets with minimal human intervention.
2. 02Scale to 200,000–300,000 documents per month.
3. 03Handle rotated pages and variable formatting.
4. 04Improve extraction accuracy and add signature validation.
5. 05Provide real-time visibility into outstanding PODs and deliveries.

1. 01Amazon Simple Email Service receives ship tickets by email.
2. 02Amazon S3 Event Notifications trigger an event-based workflow and auto-scaling compute orchestration.
3. 03Amazon Textract StartDocumentAnalysis with Layout and Signature features extracts document text and signatures.
4. 04A microservice normalizes rotation issues and generates markdown from the extracted text.
5. 05Amazon Bedrock extracts key-value data from the markdown output.
6. 06Results are stored in Amazon RDS for PostgreSQL for downstream visibility and validation.

1. 01Manual processing was reduced and automation increased.
2. 02Extraction accuracy and reliability improved.
3. 03Signature validation and rejection of incomplete documents were added.
4. 04Real-time visibility into outstanding PODs and deliveries was provided.
5. 05The process scaled to 200,000–300,000 documents per month.
6. 06Processing cost was less than $0.04 per page.

• Automated proof-of-delivery processing workflow
• Added signature validation and rejection
• Real-time delivery visibility
• Scaled document processing volume