Case Study

Impact stats

• More than 1 million documents reviewed in seven months since launch, averaging over 4,600 documents per day.

• Less than 3% of applicants abandoned their document upload during the proof of concept window.

Summary

In Pennsylvania, Nava is providing services to the Commonwealth Office of Digital Experience (CODE PA) and the Department of Human Services (PA DHS) to help meet new federal requirements under H.R. 1. The law requires the Supplemental Nutrition Assistance Program (SNAP) to maintain low payment error rates or funding for the program will become a state responsibility. The payment error rate is not a measurement of fraud or intentional misuse; it is used by the federal government to measure states’ SNAP processing accuracy, including slight overpayments or underpayments and other minor administrative processing errors, like missing signatures. 

CODE PA and PA DHS implemented Nava’s AI-powered document processing tool that analyzes images and documents uploaded by SNAP applicants and recipients to ensure quality and readability. If there are issues with the uploaded document, the user receives real-time feedback and guidance. Improving document upload quality helps minimize administrative burden for staff and users, and it reduces the risk of incorrect data entry due to blurry or unreadable images, ultimately helping to reduce Pennsylvania’s payment error rate. 

Approach

Intelligent document processing (IDP) uses open source software and AI for quick impact and transparency. Keeping the tool open source enables procuring entities to avoid vendor lock-in while maintaining a community-vetted codebase. PA DHS is leveraging Nava’s open source software solution to use the tool’s reusable and flexible software.

Outcomes

In two months, the Commonwealth was able to deploy intelligent document processing using AI-powered image technology to analyze image quality and readability with features such as:

• Checking image quality in real-time

• Preventing image degradation during upload

• Providing users with immediate feedback and corrective guidance if issues are detected

• Diverting limited staff time from rework to focusing on validation, accurate data entry, and determining eligibility

Since launch, the Commonwealth’s new document processing tool has evaluated over 1 million income documents for quality, averaging over 4,600 documents per day and resulting in fewer errors due to poor image quality. Fewer than 3% of applicants abandoned their document upload during the proof of concept window, indicating the experience is relatively seamless for applicants and in line with other upload experiences (e.g. mobile check deposits). About 24% of submitted documents needed user attention, meaning they were missing information or were unreadable. Those users received feedback in real-time to fix errors more quickly. 

This new tool modernizes the document submission process for SNAP users while improving document quality for state staff who determine SNAP eligibility. Since the initial implementation of the document processing tool, PA DHS has expanded the document upload categories to include personal information and expenses in addition to income documents. 

Conclusion

By supporting users’ self-service document upload through AI-powered analysis and enhancement, the Commonwealth can ensure submission integrity while significantly reducing administrative burden for users and staff. The intelligent document processing tool reduces rework, mitigates risk, and accelerates benefit delivery.