On July 16, members of the Digital Identity Community of practice gathered to learn how peers are gathering beneficiary feedback on their experiences with accounts and proving their identity.
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.
NYC's My File NYC and New Jersey's unemployment insurance system improvements demonstrate how successful digital innovations can be scaled across various programs, leveraging trust-building, open-source technology, and strategic partnerships.
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.
MITRE developed the Comprehensive Careers and Supports for Households (CCASH™) tool to help individuals understand and manage federal benefits and employment services, transitioning from a consumer-focused tool to a policy analytics system. By integrating data from sources like the U.S. Census and the Policy Rules Database, MITRE created a model that allows users to analyze and compare benefits eligibility across states, supporting evidence-based policymaking.
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to simplify Medicaid and CHIP applications through LLM APIs while addressing limitations such as hallucinations and outdated information by implementing a selective input process for clean and current data.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 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.
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.
