Discover how generative AI is shaping the future of education!
Dr. Luis E. Pérez-Cortés, Dr. Daniel Robinson, and Dr. Hugh Kellam contributed to Handbook of Generative AI in Education: Integrating Research into Practice. Below, Dr. Pérez-Cortés explores how research can guide thoughtful and effective AI use in teaching and learning.
What is the name of the book?
Handbook of Generative AI in Education: Integrating Research into Practice
Chapter: “From Prompt to Practice: Using the PROSE Model for Constructive Alignment in Course Design and Teaching with Generative AI”
Where can it be located?
The book is available electronically through the UTA Libraries, where members of the UTA community can access it at no cost.
Citation of the article, journal, or book?
Pérez Cortés, L. E., & Kellam, H. (2026). From prompt to practice: Using the PROSE model for constructive alignment in course design and teaching with generative AI. In M. C. Mayrath, J. T. Behrens, and D. H. Robinson (Eds.), Handbook of generative AI in education: Integrating research into practice (pp. 379-397). Springer. https://doi.org/10.1007/978-3-032-24819-0_13
Q: What core idea or moment sparked the creation of this book or article?
A: The handbook emerged from a growing need to move the educational conversation around generative AI beyond excitement, speculation, and concern toward evidence-informed and theoretically grounded practice. As generative AI rapidly entered classrooms and universities, the editors and contributors sought to bring together research, learning theory, practical examples, and implementation guidance that could help educators understand not simply what AI can do, but how it can be used responsibly and effectively to support teaching and learning.
Q: In your own words, what is the most important question your work attempts to answer?
A: At its core, our chapter asks: How can educators design generative AI prompts so that the technology supports the intended goals of teaching and learning? More specifically, we examine how prompt design can be approached as an instructional design process. Through the PROSE model, we explore how clearly defining the AI’s persona, assessment criteria, learning objective, expected steps, and examples can help align AI-supported activities with course goals, instructional practices, and assessment expectations. Ultimately, the chapter is less concerned with simply getting better outputs from AI and more concerned with helping educators design AI interactions that are pedagogically meaningful and connected to what students are actually expected to learn.
Q: How does your publication challenge, refine, or expand the existing conversation in your field?
A: In our chapter, we introduce the PROSE model—Persona, Rubric, Objective, Steps, and Example—as a framework for designing generative AI prompts that are aligned with learning objectives, instructional activities, and assessment. Rather than approaching prompting primarily as a technical skill or a matter of finding the right wording, we position prompt design as an instructional design activity.
We also provide practical examples, instructor reflections, and student feedback illustrating how the structure of a prompt can shape the quality and usefulness of AI-supported learning experiences. In this way, the chapter expands the conversation from simply asking what generative AI can produce to asking how educators can deliberately design AI interactions that support constructive alignment, meaningful learning, and sound pedagogical practice.
Q: What do you hope readers or future scholars take away as the essential message of your work?
A: I hope readers take away that effective educational uses of generative AI require thoughtful pedagogical design. AI does not automatically improve learning simply because it can generate sophisticated responses. Its educational value depends heavily on the goals, expectations, context, and instructional structures surrounding its use.
For educators, I hope the PROSE model provides a practical way to translate those principles into everyday teaching practice. For researchers, I hope the chapter encourages continued investigation into not only whether generative AI supports learning, but also how particular design choices influence the quality of AI-supported teaching and learning experiences.
Q: How does this publication connect to the broader themes or questions that shape your career as a scholar?
A: Much of my work examines how emerging technologies can be designed and used to support meaningful learning experiences. As generative AI has rapidly expanded its presence and adoption across educational contexts, my research has followed that growing reality by examining how educators and learners can use these systems in ways that remain grounded in instructional goals rather than being driven primarily by the novelty or capabilities of the technology.
This chapter connects closely with my broader interests in instructional design, learning technologies, and the ways interactive systems shape teaching and learning. The PROSE model reflects a recurring question across my scholarship: How can we take technologies that are already becoming part of learners’ and educators’ lives and design experiences around them that are purposeful, accessible, pedagogically sound, and responsive to how people actually learn?
Q: Were there any challenges or obstacles that significantly shaped the direction of this project?
A: There were no major obstacles that significantly changed the direction of the project. One ongoing challenge, however, was writing about a technology that was—and continues to be—developing extremely rapidly. This reinforced the importance of grounding the chapter in durable principles of instructional design and constructive alignment rather than focusing too heavily on the capabilities of any particular AI platform or model.
Q: In what ways do you see your findings influencing practice, policy, or future research?
A: For practice, I hope the PROSE model gives instructors and instructional designers a straightforward framework for creating more purposeful and pedagogically aligned uses of generative AI. It can support educators in thinking beyond simply asking AI to generate content and instead considering the role, criteria, objectives, processes, and examples that should guide an AI-supported activity.
For institutional practice and policy, the work also suggests that discussions about AI should extend beyond questions of whether students or instructors are permitted to use these tools. Institutions may also need to consider how educators are prepared to use AI effectively, including professional development around instructional design, assessment, transparency, responsible use, and AI literacy.
For future research, the chapter raises opportunities to examine how different approaches to prompt and activity design affect student learning, engagement, feedback, self-regulation, and the quality of AI-generated support. More broadly, I hope this work contributes to a research agenda focused on identifying the conditions under which generative AI supports learning, when it does not, and how educators can design experiences that preserve meaningful human judgment and pedagogical purpose.