The team examined how AI, specifically LLMs, could streamline the case review process for SNAP applications to alleviate the burden on case workers while potentially improving accuracy.
There are frameworks available that could inform the standardization of communicating rules as code for U.S. public benefits programs. The Airtable communicates the differences between the frameworks and tools. Each entry is tagged with different categories that identify the type of framework or tool it is.
The New South Wales government describes its efforts to connect with other Australian jurisdictions and international colleagues in its move towards making machine-consumable legislation and policy.
Better Rules utilizes multidisciplinary teams that include people skilled in policy, legal, business rules, programming, and service design working together in an iterative fashion to develop rules. Several outputs are produced using this approach, each offering an opportunity that can be fed back into that iterative process and re-used to solve other issues.
The team explored the performance of various AI chatbots and LLMs in supporting the adoption of Rules as Code for SNAP and Medicaid policies using policy data from Georgia and Oklahoma.
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 NYC Mayor’s Office for Economic Opportunity (NYC Opportunity) developed the NYC Benefits Platform, including ACCESS NYC, to help residents easily discover and check eligibility for over 80 social programs.
Alluma is a nonprofit that provides digital solutions to simplify eligibility screening and enrollment for social benefit programs, supporting cross-benefit access in 45 counties and two states. Their One-x-Connection product suite streamlines Medicaid and SNAP applications using a business rules engine, with a focus on human-centered design and anonymous, simplified eligibility checks, having helped screen over 10 million individuals and submitted over 67 million applications.
This publication explains the fundamentals of state IEE systems—including the technology, opportunities, risks, and stakeholders involved. It is a resource for state officials, advocates, funders, and tech partners working to implement these systems.
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.
