A Mixed-Methods Study of Policymakers' Adoption of AI to Support Use of Research Evidence: Implications for...

Policymakers are increasingly adopting artificial intelligence (AI) tools to support legislative decision-making, yet there is limited empirical understanding of how these technologies are used and the implications for evidence-based policymaking. General-purpose AI tools, such as large language models (LLMs), present both opportunities for improved efficiency and risks related to misinformation and lack of transparency. This study examines state legislators' use of AI in policymaking and introduces the AIRE Protocol (AI for Informed and Responsible Evidence-use), a structured framework for developing specialized AI tools grounded in validated evidence. We demonstrate the application of the AIRE Protocol through the development of the Results First AI Assistant, designed to enhance policymakers' access to the Results First Clearinghouse. A mixed-methods approach was used. Forty-five US state legislators participated in live interviews to assess AI adoption patterns, perceived benefits, and concerns. The AIRE Protocol guided the rapid prototyping and iterative development of the AI assistant, with input from policymakers, national policy organizations, and technical experts, resulting in tailored evidence based recommendations. While policymakers expressed interest in AI tools for improving access to information under time constraints, they also raised concerns regarding transparency, reliability, and appropriate use. Our findings suggest that AI tools tailored to policymakers' needs-developed using frameworks like AIRE-will facilitate the integration of validated evidence into legislative decision-making while addressing ethical and practical concerns associated with generalized AI solutions.