Designing for Student Engagement with AI in Courseware: Lessons from Iterative Improvements to DOT in REAL CHEM

This design-based research study reports on a Learning Engineering (LE) cycle embedded within the broader REAL CHEM courseware initiative, examining how students use and perceive DOT, a generative AI tutor for general chemistry. In Fall 2024, student awareness and engagement with DOT were low, and interviews revealed reliance on external AI tools and limited generative use. Guided by LE principles—human-centered design, iterative refinement, and evidence-informed decision making—we redesigned DOT by refining its base prompt and introducing AI Activation Points to make the system more proactive and contextually aligned with student workflows. Summer 2025 findings showed increased awareness, higher engagement, and improved student satisfaction. Results illustrate how targeted, iterative LE cycles can improve the effectiveness of AI-enabled learning supports at scale.