The Policy2Code Prototyping Challenge explored utilizing generative AI technology to translate U.S. government policies for public benefits into plain language and code, culminating in a Demo Day where twelve teams showcased their projects for feedback and evaluation.
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-powered explanation feature that effectively translates complex, multi-program policy calculations into clear and accessible explanations, enabling users to explore "what-if" scenarios and understand key factors influencing benefit amounts and eligibility thresholds.
The federal government's investments in children are crucial in addressing poverty and have long-term benefits across multiple domains, such as health, education, and economic stability, illustrating how support in one area can lead to positive outcomes in others.
The goal of the brief is to encourage policy makers and employers to consider benefits cliffs as they look to create mandatory wage increases, with a look at a legislative action in NYC.
Research examining how much poverty would decrease—overall, by age, and by race and ethnicity—and how much benefits would increase if all people eligible for safety net programs received the full benefits they qualify for in each of the 50 states and DC.
A modernized public benefits system would better serve program participants, administrators, policy makers, and taxpayers. This paper proposes a set of principles both define the desired future state and outline the values that shape decision making along the way. Practices describe the processes needed to achieve modernization.
This Issue Spotlight explores the challenges that recipients of public benefits programs offering cash assistance encounter in accessing funds through financial products or services, with a specific focus on assistance provided on prepaid cards.
PolicyEngine is a nonprofit that provides a free, open-source web app enabling users in the US and UK to estimate taxes and benefits at the household level, while also simulating the effects of policy changes. By combining tax and benefits data, PolicyEngine helps individuals and policymakers better understand the impacts of existing policies and proposed reforms, using microsimulation models built from legislation and enhanced survey data.
Github repository for Policy Rules Database, which encodes up-to-date rules and provisions for all major federal and state public assistance programs, taxes, and tax credits.
PolicyEngine US is a Python-based microsimulation model of the US tax and benefit system. It models federal individual income taxes (including credits), major benefit programs, and state income taxes (currently in six states). The PolicyEngine US package can be used as a Python package, via the PolicyEngine API, or via the policyengine.org web app.
