Enhancing LGBTQ+ Inclusivity in an AI-Powered Sexual Health Chatbot: A User-Centered Design Approach Through a Nonprofit-Academic Partnership (Preprint)

BACKGROUND Despite the growing use of digital platforms for sexual health education, many tools fail to meet the needs of LGBTQ+ adolescents, who often lack access to inclusive, affirming resources. Artificial intelligence (AI)–enabled chatbots have emerged as promising tools to address these gaps, but concerns remain around bias, usability, and trustworthiness–particularly for queer and trans youth. OBJECTIVE This paper describes the development and implementation of an academic-nonprofit partnership between Northwestern University and Planned Parenthood Federation of America (PPFA) to adapt Roo, PPFA’s AI-powered sexual health chatbot, for LGBTQ+ teens. METHODS As part of a larger hybrid effectiveness-implementation trial, the research team collaborated with PPFA to create a customized instance of Roo and gathered feedback from a Youth Advisory Council (YAC) of LBGTQ+ teens via a private Discord server. Using a participatory, research-through-design approach, we analyzed structured qualitative feedback with rapid qualitative analysis to identify content gaps, usability concerns, and trust-related issues. RESULTS Participants expressed both skepticism and curiosity about AI’s role in delivering sexual health information, offering critical insights on the chatbot’s language, trustworthiness, and relevance. Teens identified key limitations in Roo’s inclusivity, tone, and interface, particularly around trans-specific content, conversational depth, and stigma reduction. These findings informed targeted content updates, interface refinements, and transparency improvements, implemented by PPFA to enhance Roo for broader use. CONCLUSIONS Academic-nonprofit collaborations can leverage participatory methods to enhance digital health tools in real-world contexts. LGBTQ+ teens served not only as testers but as co-designers, shaping the chatbot’s evolution and surfacing broader lessons about trust, AI literacy, and health equity. This partnership offers a scalable model for integrating community voice into the development, evaluation, and implementation of inclusive, AI-enabled health technologies.