Explore how generative AI can support case-based learning across educational contexts. This session offers strategies for using AI as a case generator, dialogue partner, and evaluator to foster ethical, reflective, and stakeholder-aware case-based problem solving. A practical toolkit with adaptable prompts and templates will be shared.

Session Overview

What happens when students use generative AI to solve complex, real-world problems—and how can educators guide them to do so ethically and reflectively? This session focuses on how to use generative AI to support case-based learning in educational settings. Participants will explore how AI can serve as a case generator, dialogue partner, and evaluator, helping students engage in critical thinking and collaborative problem-solving. The goal is for students to not just use AI to find answers, but to ask better questions, consider multiple viewpoints, and reflect on the implications of different decision. Across the curriculum, AI can help students and teachers look at problems from the positions of different stakeholders and explore a range of solutions. The session includes examples of prompts that can be used to help design cases, lesson plan templates that can be adapted for different educational levels and subject matter areas, and reflective questions to encourage students to explore problem solving and AI use from multiple perspectives. Attendees will leave with a toolkit for integrating AI cases into their teaching practice in ways that are thoughtful, responsible, and aligned with real-world learning goals.

Background

Case-based learning is an approach that helps learners become effective problem solvers. It supports important skills, including critical thinking, decision-making, and transfer of learning. Additionally, case-based learning offers opportunities to situate learning in real-world contexts and can foster robust discussions when done collaboratively. Case-based learning has been applied widely in the medical education fields (Donkin et al., 2023), and in one study both faculty and students indicated preferring case-based learning to problem-based learning (Srinivasan et al., 2007).

While there are many variants of cases and case-based learning, all share a common focus on stories, whether real or contrived, that present a problematic scenario. Jonassen (2006) proposed a typology of learning cases, articulating the different forms and functions of learning cases. The scenario may include an actual or proposed solution. Alternatively, the solution may not be specified, learning space for learners or the solution may be unexplored, left for learners to propose. Finally, in some instances learners may become the authors of cases, demonstrating their understanding of a specific context in their telling of a case narrative.

While case-based learning can be done by learners working independently, the approach appears to work best when learners work in groups and discursively collaborate to address cases (Flynn & Klein, 2001; Sartania et al., 2022). In online classes, this means that small groups might work through cases together in discussion forums or breakout rooms.

Generative AI and Case-based Learning

Generative AI introduces new possibilities for case-based learning. It can rapidly generate diverse scenarios, simulate stakeholder perspectives, and provide iterative feedback. Generative AI can serve multiple functions in a case-based learning content, including:

Case generator, producing rich, nuanced scenarios tailored to curricular goals. Advantages of using Generative AI are numerous. It can save instructors class preparation time by filling in case details, generating variants of cases, and customizing cases to specific class contexts and learning objectives. For class activities where students are asked to generate examples, AI can save time as well. The large language model can help identify appropriate case details, promoting greater authenticity. Additionally, Generative AI can take existing cases and use them as a model for subsequent ones, and adjust cases to different student levels and different target learning outcomes.

Dialogue partner, helping students explore ideas, test hypotheses, and consider alternative viewpoints while addressing cases. As a partner, AI is tireless and draws upon a broad knowledge base. The AI dialogue partner can be set up with focused prompts, ensuring that it engages the student socratically or only answers focused questions from the student, and does not do the work for students.

Evaluator, offering feedback and prompting reflection on decisions and reasoning processes. In this role, student case solutions may be fed into Generative AI, after which students may receive formative comments on their solution or even dialogue with AI about the suitability of their solutions. For an instructor who wants to quickly understand how well a student or class is performing, AI can quickly make comparisons and identify trends across case solutions.

Regardless of how Generative AI is being used, the emphasis of case-based learning should be on the students and how they interact with and learn from the case (Anderson & Schiano, 2014). While it can generate cases and case solutions, the goal is never to have it doing the work that relates to the learning objectives, but rather to swiftly get instructors and students focused on the learning objectives, lesson preparatory work, provide learning supports as needed, and streamline assessment.

Ethical and Reflective Use of AI

Whenever AI is used, ethical concerns should be addressed. It is important to critically evaluate AI outputs, recognize bias, and reflect on the social and cultural implications of AI use. In this session, we will examine the potential for inaccurate and biased AI-generated cases and case solutions as well as concerns related to student digital literacy skills. To address these issues, we will share strategies to:
• Teach students to interrogate AI responses rather than accept them at face value
• Encourage meta-cognition about how and why AI is used in learning
• Embed digital literacy and AI ethics into case-based lessons
Additionally we will touch on issues related to intellectual property and academic honesty.

Topic Relevance to the OLC Community

This session aligns closely with the OLC Innovate community’s commitment to advancing online, blended, and digital learning through innovation, collaboration, and ethical practice. As generative AI becomes increasingly embedded in educational technologies, educators across K–12 and higher education must grapple with how to integrate these tools in ways that support meaningful learning rather than automation or shortcutting.

This session supports the “Teaching & Learning Innovation” track by offering faculty and instructional designers practical strategies for integrating generative AI into online and blended learning environments.

Session Format and Interactivity

This session will be highly interactive. Participants will:
• Experience AI-generated case-based learning from multiple perspectives
• Practice writing AI prompts for generating learning cases, producing multiple case solutions, and for analyzing case solutions
The session will also include opportunities for peer sharing, allowing attendees to learn from each other’s experiences and insights.

Outcomes and Takeaways

By the end of the session, participants will:
• Understand how generative AI can support case-based learning across educational contexts.
• Be equipped with practical tools for designing AI-enhanced learning experiences.
• Be prepared to guide students in ethical, reflective use of AI.
• Be inspired to explore new possibilities for AI integration in their own teaching and curriculum design.

The session will provide attendees with a toolkit for integrating generative AI into case-based learning. This includes:
• Prompt libraries for generating cases across disciplines and grade levels.
• Lesson plan templates that can be adapted for different online learning contexts.
• Reflective questions to guide students in ethical reasoning and stakeholder analysis.
• Rubrics for evaluating different types of AI-generated case-based learning.
These resources are designed to be flexible and scalable. Educators can use them in hybrid and fully online environments. They hold Creative Commons licenses, allowing others to freely adapt them to suit.

References
Anderson, E., & Schiano, B. (2014). Teaching with cases: A practical guide. Harvard Business Review Press.
Donkin, R., Yule, H., & Fyfe, T. (2023). Online case-based learning in medical education: a scoping review. Bmc Medical Education, 23(1), 564. https://doi.org/10.1186/s12909-023-04520-w
Flynn, A. E., & Klein, J. D. (2001). The Influence of Discussion Groups in a Case-Based Learning Environment. Educational Technology Research & Development, 49(3), 71-86.
Jonassen, D. (2006). Typology of case-based learning: The content, form and function of cases. Educational Technology, 46(4), 11-15.
Sartania, N., Sneddon, S., Boyle, J. G., McQuarrie, E., & de Koning, H. P. (2022). Increasing Collaborative Discussion in Case-Based Learning Improves Student Engagement and Knowledge Acquisition. Med Sci Educ, 32(5), 1055-1064. https://doi.org/10.1007/s40670-022-01614-w
Srinivasan, M., Wilkes, M., Stevenson, F., Nguyen, T., & Slavin, S. (2007). Comparing Problem-Based Learning with Case-Based Learning: Effects of a Major Curricular Shift at Two Institutions. Academic Medicine, 82(1), 74-82.

Vanessa P. Dennen

Professor at Florida State University