Abstract
Generative Artificial Intelligence (GenAI) is increasingly integrated into creative design practices, but designers often struggle to effectively align its capabilities with their workflows. Current approaches to GenAI development frequently emphasise technological innovation over the practical needs and experiences of designers. This technology-centred focus overlooks the diversity of designers’ practices, including their workflows and habitual methods, thus limiting opportunities for meaningful collaboration and interaction between designers and GenAI systems. To address this gap, we introduce Mindmesh, a collaborative design canvas developed to support interdisciplinary teams in designing GenAI tools within creative contexts. Developed through literature review, co-occurrence analysis, and expert feedback, the canvas provides a structured approach to define design goals, outline interaction methods, specify AI system behaviours, and consider ethical and interpret ability issues during the GenAI design process. We demonstrate its practical application through a case study involving the design of Hand Sketch, a gesture-based multimodal poster generation system. This case illustrates how the canvas facilitates collaboration across disciplines, supports early-stage design thinking, and encourages critical reflection on GenAI development within the creative context. By connecting abstract design requirements with practical system planning, Mindmesh contributes to the collaborative development of GenAI tools that align better with creative practices and designers’ needs.
Keywords
Human-AI collaboration; Human-centred AI; Collaborative design; User-centred design
DOI
https://doi.org/10.21606/iasdr.2025.389
Citation
Fang, C., Zhu, Y., Fang, L., Lou, Z., Yenigun, E.O., Liu, W.,and Wang, S.J.(2025) Mindmesh: A Collaborative Canvas for Designing Generative AI in Creative Context, in Chang, C.-Y., and Hsu, Y. (eds.), IASDR 2025: Design Next, 02-05 December, Taiwan. https://doi.org/10.21606/iasdr.2025.389
Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License
Conference Track
Track 4 - Human-Centered AI
Mindmesh: A Collaborative Canvas for Designing Generative AI in Creative Context
Generative Artificial Intelligence (GenAI) is increasingly integrated into creative design practices, but designers often struggle to effectively align its capabilities with their workflows. Current approaches to GenAI development frequently emphasise technological innovation over the practical needs and experiences of designers. This technology-centred focus overlooks the diversity of designers’ practices, including their workflows and habitual methods, thus limiting opportunities for meaningful collaboration and interaction between designers and GenAI systems. To address this gap, we introduce Mindmesh, a collaborative design canvas developed to support interdisciplinary teams in designing GenAI tools within creative contexts. Developed through literature review, co-occurrence analysis, and expert feedback, the canvas provides a structured approach to define design goals, outline interaction methods, specify AI system behaviours, and consider ethical and interpret ability issues during the GenAI design process. We demonstrate its practical application through a case study involving the design of Hand Sketch, a gesture-based multimodal poster generation system. This case illustrates how the canvas facilitates collaboration across disciplines, supports early-stage design thinking, and encourages critical reflection on GenAI development within the creative context. By connecting abstract design requirements with practical system planning, Mindmesh contributes to the collaborative development of GenAI tools that align better with creative practices and designers’ needs.