18F, a consultancy within the U.S. General Services Administration, developed a prototype API and pre-screener to model federal SNAP eligibility rules, aiming to simplify benefits access through open-source technology.
This guide highlights best practices in benefits access, showcasing how Michigan, New York City, and San José improve accessibility through plain language, multilingual translation, resident co-creation, and technology tools.
This report summarizes insights from interviews with seven states on how they are adapting integrated eligibility and enrollment (IEE) systems in response to sweeping federal changes to SNAP and Medicaid under H.R. 1.
Design systems are a foundational component of good government digital service delivery. This publication explores why design systems matter and includes a tracker of centralized design systems across U.S. states.
The Digital Identity Community of Practice kick-off event featured key resources, a new research publication on account creation and identity proofing, and insights from multiple speakers.
This session from FormFest 2024 walked attendees through some of the major changes AI is bringing to form design. Learn about the National Head Start Association’s use of AI to reduce administrative burden and the Canadian Digital Service’s tips for protecting government applications systems from AI.
To kick off the Digital Service Network’s (DSN) summer event series, Let’s Get Digital, the DSN heard from the State of Arizona on their efforts to transform government services through a strong collaboration between information technology (IT) and digital service functions.
The second event in the Digital Service Network’s summer event series, Let’s Get Digital, focused on the City of Boston’s transformative journey to streamline its procurement processes.
The team explored using LLMs to interpret the Program Operations Manual System (POMS) into plain language logic models and flowcharts as educational resources for SSI and SSDI eligibility, benchmarking LLMs in RAG methods for reliability in answering queries and providing useful instructions to users.
The team developed an AI solution to assist benefit navigators with in-the-moment program information, finding that while LLMs are useful for summarizing and interpreting text, they are not ideal for implementing strict formulas like benefit calculations, but can accelerate the eligibility process by leveraging their strengths in general tasks.
