During the COVID-19 pandemic, we saw soaring demand for GetCalFresh, our digital application assister for California's version of the Supplemental Nutrition Assistance Program (SNAP). With more applications came more client requests for help, and with a small client success team at the time, Code for America needed a solution that could ensure all clients received responses in a timely manner. We built a chatbot that could handle common, simple client questions and direct them to relevant resources. Considering the sensitive nature of our clients' needs, we developed an empathetic, human-centered chatbot. Join us as we share lessons learned as we iterated on the chatbot with careful large language model implementation.

Emerging Technology + Innovation