Team: PDF Form Modernization Assistant

Team Participants:

  • Matthew Phan (California Polytechnic State University, San Luis Obispo)

  • Anh Nguyen (California State University, Chico)

  • Isaac Lares (California State University, Channel Islands)

  • Harishita Gupta (San José State University)

  • Anoushka Sawant (San José State University)

“Sacramento State has roughly 14,000 PDFs on their website that needs to be reviewed, remediated, retired, or recommended—it’s not just a broken form, it’s a campus scale workflow problem.”

Problem

Sacramento State maintains hundreds of PDF forms that supported student services, HR, academic, and administrative processes. Many require accessibility review, modernization, conversion to fillable formats, or replacement with digital workflows. The campus lacks the resources to inventory, assess, and prioritize these forms at scale. It needs an AI-assisted solution that could identify PDF forms, extract form fields and business process information, assess accessibility and complexity, and recommend the most appropriate path forward. Recommendations might include remediation, recreation as an accessible PDF, migration to a web form, implementation in platforms such as Microsoft Forms, Power Apps, ServiceNow, Adobe Acrobat Sign, or OnBase, or retirement of the form. The ideal solution would also generate structured metadata and migration recommendations to support campus modernization efforts.

Technical Solution

The AI-Powered PDF Form Modernization Assistant team built an automated assessment platform using AWS Lambda (serverless compute) to process form uploads, Amazon Textract (document text extraction) to extract form fields and structure, and Amazon Bedrock (managed generative AI) to analyze fillable elements for accessibility compliance. Textract parses PDF forms to identify labels, input fields, and ARIA descriptions that traditional tools miss, while Bedrock evaluates each element against WCAG standards and generates remediation recommendations. The system stores assessment results in Amazon DynamoDB (NoSQL database) for tracking and provides actionable guidance on alternative delivery options including web forms and accessible document formats. By automating the assessment workflow, the platform reduces manual evaluation time from hours to minutes per form and creates a foundation for semantic matching to detect duplicate forms across the campus website.

Showcase

Presentation RecordingA recording of AI Summer Camp students presenting their project.
SlideshowThe accompanying slides shown in the video.
Source CodeAll of the code and assets developed during the course of the AI Summer Camp.

About the DxHub

The Cal Poly Digital Transformation Hub (DxHub) is a strategic relationship with Amazon Web Services (AWS) and is the world’s first cloud innovation center supported by AWS on a University campus. The primary goal of the DxHub is to provide students with real-world problem-solving experiences by immersing them in the application of proven innovation methods in combination with the latest technologies to solve important challenges in the public sector. The challenges being addressed cover a wide variety of topics including homelessness, evidence-based policing, digital literacy, virtual cybersecurity laboratories and many others. The DxHub leverages the deep subject matter expertise of government, education, and non-profit organizations to clearly understand the customers affected by public sector challenges and develop solutions that meet the customer needs.