Civic Innovations

Last week, I took part in BenCon 2024 — an annual two-day conference hosted by the Beeck Center for Social Impact + Innovation at Georgetown University focused on charting the course to excellence in digital benefits delivery.

The cornerstone of this year’s conference was a series of live demonstrations highlighting the use of artificial intelligence (AI) tools and platforms to improve the delivery of public benefits. The Policy2Code Prototyping Challenge was a months-long effort by 14 different teams from across the country (and one international team) to identify innovative new ways to use generative AI to improve public benefit delivery.

While many of the teams that took part in the challenge focused their efforts on enhancing the experience of applicants and beneficiaries or assisting benefit “navigators,” my team took a bit of a different approach. In the work my company has dobe on public benefit systems, one common area of friction that we have observed is that there is a lack of understanding and context between the people who are experts in (often complex) public benefit program policies and those who are experts in software system implementation. This lack of shared understanding can make new system implementation difficult, costly, and sometimes error-prone.

My focus for the Policy2Code Prototyping Challenge was to develop ways to empower policy subject matter experts and place them as the ultimate arbiters of correctness in new system implementation. My team did this by developing ways to use Large Language Models (LLMs) to generate an intermediate format between policy language and software code that policy experts and software engineers could use to create a shared understanding about what is required when public benefit program rules are implemented in a software system. This intermediate format is a domain specific language (DSL) that contains specific details about public benefit rules that policy experts and software engineers can both understand, and that empowers policy experts to more easily verify the correctness of a system implementation.

Our team spent the summer working with various LLM models to develop the tools and approaches needed to generate programs describing public benefit policies in our experimental DSL. At last week’s BenCon conference, the team I was on was recognized for its work with an award for Outstanding Policy Impact. I believe that the approach we developed for the Policy2Code Prototyping Challenge holds enormous potential, and I’m excited to continue iterating on it.