Abstract
This study presents an AI-assisted Design Improvisation Pedagogy integrating artificial intelligence with bodystorming in space design education. Built on a three-dimensional framework—Embodiment, Enactment, and Improvisation—an AI system was developed using Coze to generate emergent scenarios and guide improvisational performance. Validated over three semesters with 16 undergraduate students tackling extreme environment challenges, the system employed Retrieval-Augmented Generation (RAG) to deliver context-rich, adaptive prompts. Results showed strong correlation between AI support and enhanced improvisational creativity (r = 0.48), especially in spontaneous adaptability. Students often underrated their own performances, with significant gaps in Improvisation (p < 0.01). Material types influenced outcomes, with sound-based tasks producing the largest evaluation discrepancies. Findings highlight AI’s evolving role from tool to creative collaborator, offering a novel pedagogical model that merges embodied cognition, reflective practice, and AI to foster design thinking under constraints.
Keywords
AI-assisted design pedagogy; bodystorming; design improvisation; design education
DOI
https://doi.org/10.21606/drs.2026.1362
Citation
Li, J., Wang, J., Zhu, L., Xu, J., Zhao, C., and Fu, Z. (2026) Bodystorming through Disruption: AI-assisted Design Improvisation Pedagogy, in Simeone, L., Gray, C. M., Verhoeven, A., de Götzen, A., Bakırlıoğlu, Y., Zohar, H., Stead, M., and Buwert, P. (eds.), DRS2026: Edinburgh, 8–12 June, Edinburgh, United Kingdom. https://doi.org/10.21606/drs.2026.1362
Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License
Included in
Bodystorming through Disruption: AI-assisted Design Improvisation Pedagogy
This study presents an AI-assisted Design Improvisation Pedagogy integrating artificial intelligence with bodystorming in space design education. Built on a three-dimensional framework—Embodiment, Enactment, and Improvisation—an AI system was developed using Coze to generate emergent scenarios and guide improvisational performance. Validated over three semesters with 16 undergraduate students tackling extreme environment challenges, the system employed Retrieval-Augmented Generation (RAG) to deliver context-rich, adaptive prompts. Results showed strong correlation between AI support and enhanced improvisational creativity (r = 0.48), especially in spontaneous adaptability. Students often underrated their own performances, with significant gaps in Improvisation (p < 0.01). Material types influenced outcomes, with sound-based tasks producing the largest evaluation discrepancies. Findings highlight AI’s evolving role from tool to creative collaborator, offering a novel pedagogical model that merges embodied cognition, reflective practice, and AI to foster design thinking under constraints.