AI-Generated, Personality-Tailored Cases in Teacher Education: A Feasibility Study of Student Experiences

Higher education faces increasing demands to address student diversity in engagement, learning preferences, and professional readiness. This study examined the feasibility of integrating personality-tailored case-based learning in teacher education. Building on the Big Five personality model and principles of differentiated, case-based pedagogy, we developed a prototype that generated individualized case descriptions using a personality inventory and generative AI. The intervention was implemented in a teacher education course, with 37 students (≈79%) completing an anonymous evaluation survey. Quantitative measures included emotion-word selections and Likert-type ratings of case relevance and group discussions; qualitative data were collected through open-ended reflections. Findings indicated that students experienced the intervention as engaging, relevant, and appropriately challenging. Group discussions received the highest ratings, with students emphasizing the value of peer dialogue for gaining new perspectives and making sense of the cases. Qualitative themes highlighted the realism of personalized scenarios, opportunities for reflection, and the importance of scaffolding, while challenges included unclear instructions and limited diversity among cases. The study demonstrates the feasibility and perceived pedagogical value of personality-tailored cases as a scalable model of differentiation in higher education. Future research should adopt controlled designs to disentangle the effects of personality instruction, feedback, and personalization, and systematically evaluate the distinctiveness of generated cases. By integrating psychological self-insight with authentic practice scenarios, personality-informed case-based learning shows promise for enhancing student agency, reflective competence, and readiness for professional practice.