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 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 first half of Rules as Code Demo Day was wrapped up with Thomas Guillet who has contributed to Open Fisca France and beta.gouv. He demoed the code for Mes Aides—or My Benefits—which is France’s social benefit simulator that leverages open source rule models for over 600 benefits while keeping the displayed complexity to its minimum.
The team conducted experiments to determine whether clients would be responsive to proactive support offered by a chatbot, and identify the ideal timing of the intervention.
The team introduced "Policy Pulse," a tool to help policy analysts understand laws and regulations better by comparing current policies with their original goals to identify implementation issues.
We continued Rules as Code Demo Day with Daniel Singer and Preston Cabe from Benefits Data Trust. Benefits Data Trust provides benefit outreach and application assistance services in seven states. Using Benefits Launch, their in-house interview and rules engine, they support two hundred contact center employees as they screen and apply thousands of clients each year. They also offer a self-service screener, Benefits Launch Express. Additionally, they offer an eligibility API to integrate with other services.
Building on our February 2022 report Benefit Eligibility Rules as Code: Reducing the Gap Between Policy and Service Delivery for the Safety Net, the Beeck Center’s Digital Benefits Network (DBN) hosted Rules as Code Demo Day on June 28, 2022 where there were eight demonstrations of projects and code followed by a collaborative problem solving session on how to continue advancing rules as code for the U.S. social safety net.
The team aimed to automate applying rules efficiently by creating computable policies, recognizing the need for AI tools to convert legacy policy content into automated business rules using Decision Model Notation (DMN) for effective processing and monitoring.
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.
We wrapped up Rules as Code Demo Day with Max Ghenis and Nikhil Woodruff, the founders of PolicyEngine. The PolicyEngine web app computes the impact of tax and benefit policy in the US and the UK. With PolicyEngine, anyone can freely calculate their taxes and benefits under current law and customizable policy reforms, and also estimate the society-wide impacts of those reforms. Policymakers and think tanks from across the political spectrum can analyze actual policy. PolicyEngine is built atop the open source OpenFisca US and UK microsimulation models and they are building an open unified data set utilizing data from the Policy Rules Database, Current Population Survey, Survey of Consumer Finances, Consumer Expenditures, tax records, and IRS Public Use File.
MITRE’s Joe Ditre and Frank Ruscil demoed the code for the Comprehensive Careers and Supports for Households (C-CASH) at Rules as Code Demo Day. The MITRE team expanded the accessibility of the Policy Rules Database and the Cost-of-Living Database (the prior demo) by creating a web service API and a front-end Window’s application called C-CASH Analytic Tool (CAT). CAT provides a more scalable, flexible, and portable functionality which allows end-users to generate various households to run eligibility scenarios across different U.S. counties and states. They are currently working to create a national data hub and analytics tool, starting with utilizing U.S. Census data and populating the data warehouse by pushing large amounts of data through the PRD.
