Tangible Prompting Lucy Li, Quincy Kuang, Paul-Peter Arslan, Yuhan Wang, Min Fan, Jean-Baptiste Labrune, Xiao Xiao, Hiroshi Ishii
Large language models are increasingly used for ideation, yet most interactions with them occur through linear GUI-based chat interfaces that favor incremental refinement over exploratory thinking. We introduce Tangible Prompting, a system that supports AI-assisted ideation by manipulating physical objects representing different ideation actions, allowing users to navigate and shape a space of emerging ideas. The tangible vocabulary externalizes diverse choices during the ideation process and enables users to
generate alternatives, redirect exploration, combine ideas, and eliminate unpromising directions. Our study with 32 participants examines how pairs collaboratively ideate using the system in tangible versus screen-only conditions. The findings suggest that tangible interactions alter users’ relationship to AI by triggering more verbal communication between participants, giving beat to a burstier
rhythm of ideation, and contributing to an increased agency of human ideas over AI contributions.
generate alternatives, redirect exploration, combine ideas, and eliminate unpromising directions. Our study with 32 participants examines how pairs collaboratively ideate using the system in tangible versus screen-only conditions. The findings suggest that tangible interactions alter users’ relationship to AI by triggering more verbal communication between participants, giving beat to a burstier
rhythm of ideation, and contributing to an increased agency of human ideas over AI contributions.
