Incorporating AI Tools for Evaluations that Share Leadership and Support Communities

Generative AI tools can support inclusive, community-engaged evaluation by integrating community voices throughout the evaluation process; however, integrating new tools effectively and efficiently can be challenging. We will share our firm’s experience integrating and internally evaluating generative AI tools, including Fireflies.ai, Notebook LM, and Custom GPTs, to process large volumes of qualitative data and enhance analytic capacity while preserving community voice. These tools, new to many evaluators, help triangulate diverse inputs across the evaluation lifecycle for more robust synthesis than human analysis alone. We also address ethical considerations (e.g., data privacy, security, and environmental impact) and demonstrate how well-engineered prompts and triangulation across AI systems improve output quality and reliability. These tools empower communities by integrating more of their voice into the evaluation process, enabling informed decision-making, equitable participation, and shared governance of evaluation outcomes. Attendees will gain practical and ethical insights for thoughtfully integrating AI into their evaluation contexts.

Christopher Cox, Ph.D.; Emily Royse, Ph.D.