The Policy Rules Database (PRD), developed by the Federal Reserve Bank of Atlanta and the National Center for Children in Poverty, consolidates complex rules for major U.S. federal and state benefit programs and tax policies into a standardized, easy-to-use format. This database allows researchers to model public assistance impacts, simulate policy changes, and analyze benefits cliffs across various household scenarios using common rules and language across different programming platforms.
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.
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 application to simplify Medicaid and CHIP applications through LLM APIs while addressing limitations such as hallucinations and outdated information by implementing a selective input process for clean and current data.
The Digital Service Network (DSN) spoke with three staff members from the New York State Executive Chamber—Gabe Paley, Tonya Webster, and, Luke Charde to learn more about the state's efforts to improve residents’ experiences accessing government programs.
A profile on FormFest speakers Sarah Rodriguez, Emily Lippolis, and Verenice Ramirez, featuring stories about their motivations for working on public sector form innovation.
This mainstage session from FormFest 2024 included conversations about form design, accessibility, user experience, and data collection to show how good forms can build trust and confidence in government.
The State Chief Data Officer Tracker, created by the Beeck Center’s Digital Service Network and Data Labs teams, is a first-of-its-kind resource that tracks the evolving role of CDOs in state governments and their efforts to advance data-informed decision-making and collaboration across agencies.
A collaborative resource document detailing the civic tech support offerings, state and local government resources, and civic tech organizational support.
An event recap from one of FormFest 2024's closing main stage session featuring speakers from the City of Portland, Oregon and New York City, New York.
This is the summary version of a report that documents four experiments exploring if AI can be used to expedite the translation of SNAP and Medicaid policies into software code for implementation in public benefits eligibility and enrollment systems under a Rules as Code approach.
