Learning PowerUps as AI-Supported Motivational Design in Action
This theory-aligned AI prompt supports instructors in diagnosing motivational barriers and generating small, context-aware Learning PowerUps grounded in ARCS-V and learning science.
Presented by:
Travis N. Thurston, Utah State University
Hear it from the author:
Transcript:
I’m Travis Thurston, Executive Director for that Center for Empowering Teaching Excellence at Utah State University.
This project is really about helping instructors think differently about motivation, not as a student trait, but as something we can intentionally design for.
That is where Learning PowerUps come in. Learning PowerUps are small, practical teaching moves that respond to a specific motivational barrier in a specific teaching moment. They are not giant redesigns, they are more like well-timed instructional boosts that help students get unstuck, get started, or stay consistent with the work.
The ARCS Reactor uses AI to scaffold that process. It asks for context first, diagnoses the motivational challenge, and then generates a few targeted PowerUps the instructor can choose from and adapt.
So instead of using AI to generate content, I’m using it to help instructors reason more intentionally about attention, relevance, confidence, satisfaction, and volition.
The big takeaway is that AI can be most useful when it helps us make better teaching decisions, grounded in theory, grounded in context, and still grounded in human judgment and connection.
Key Words:
Motivational Design, Generative AI, Universal Design
Abstract:
Motivation is often treated as a learner trait rather than a designable feature of instruction. This poster introduces Learning PowerUps, small, context-sensitive instructional moves generated through a structured AI prompt grounded in the ARCS-V model (Attention, Relevance, Confidence, Satisfaction, Volition). Developed through design-based research, the ARCS Reactor scaffolds diagnostic reasoning before strategy selection, ensuring alignment between motivational barriers and instructional responses. Cross-platform evaluation across multiple AI systems demonstrated moderate-to-high fidelity to ARCS-V principles. Findings suggest that prompt structure—not platform optimization—plays a critical role in supporting evidence-based motivational design in higher education.
Outcomes:
1. Diagnose a motivational barrier in their own course using ARCS-V dimensions.
2. Design a small-scale Learning PowerUp aligned with a specific instructional moment.
3. Evaluate how AI can support motivational reasoning without replacing instructor judgment.
References:
Astleitner, H., & Keller, J. M. (1995). A model for motivationally adaptive computer-assisted instruction. Journal of Educational Computing Research, 13(2), 179–194. https://doi.org/10.2190/UMX2-7Q8P-YHRK-7L2U
Keller, J. M. (2010). Motivational design for learning and performance: The ARCS model approach. Springer.
McKenney, S., & Reeves, T. C. (2012). Conducting educational design research. Routledge.
Song, S. H., & Keller, J. M. (2001). Effectiveness of motivationally adaptive computer-assisted instruction. Educational Technology Research and Development, 49(2), 5–22. https://doi.org/10.1007/BF02504925
Wei, J., et al. (2022). Chain-of-thought prompting elicits reasoning in large language models. Advances in Neural Information Processing Systems, 35, 24824–24837.