Design Ideation with AI - Sketching, Thinking and Talking with Generative Machine Learning Models
Open accessThe DOI matches its Crossref record; 35 of the 35 references it cites were found in a registry or an index.
Abstract
Generative machine learning models provide opportunities to support design work in various parts of the design process. This study investigates how generative machine learning and large language models may play a part in creative design processes of ideation, early prototyping and sketching. A workshop was conducted in which design practitioners and design researchers developed design concepts for a provided design case, with the help of GPT-3. The findings point to three main themes, including i) the practical usefulness and limitations of the system in design ideation processes, ii) how the form of user interaction shapes users’ expectations of the system’s capabilities and potentials, and iii), how the broader discourse around AI both limits and enables how co-creative processes involving human and AI unfolds. The discussion outlines design implications and alternative framings of this kind of co-creative design practices based on post-human perspectives on design and technology use.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Figures




Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Control is frequently exerted through guided input (e.g., prompt engineering [102, 171]) and iterative refinement cycles [124].”
From Exploring Collaboration Patterns and Strategies in Human-AI Co-creation through the Lens of Agency: A Scoping Review of the Top-tier HCI Literature (2025) · cites this paper as [171]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Our review focused on papers published between 2018-2024, corresponding to the emergence and widespread adoption of transformer-based language models [129].”
From Co-Writing with AI, on Human Terms: Aligning Research with User Demands Across the Writing Process (2025) · cites this paper as [129]
Experimental — accuracy not yet measuredThe check wasn’t confident either way, so it gives no verdict — never disputed.
In the citing paper
“Tool-mediated passive and semi-proactive agency dominate here.”
From Exploring Collaboration Patterns and Strategies in Human-AI Co-creation through the Lens of Agency: A Scoping Review of the Top-tier HCI Literature (2025) · cites this paper as [171]
Experimental — accuracy not yet measured
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Language Models are Few-Shot Learners
Brown, T. B., Mann, B., Ryder, N., Subbiah, M., Kaplan, J., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., et al. (2020) · arXiv · doi:10.48550/arxiv.2005.14165 · Cited by 23,372
Meeting the Universe Halfway: Quantum Physics and the Entanglement of Matter and Meaning
Barad, K. (2006) · doi:10.2307/j.ctv12101zq · Cited by 10,472
Plans and Situated Actions: The Problem of Human-Machine Communication
Kantowitz, B., & Suchman, L. A. (1990) · The American Journal of Psychology · doi:10.2307/1423221 · Cited by 5,299
Generative Adversarial Networks: An Overview
Creswell, A., White, T., Dumoulin, V., Arulkumaran, K., Sengupta, B., & Bharath, A. A. (2018) · IEEE Signal Processing Magazine · doi:10.1109/msp.2017.2765202 · Cited by 4,540 · cited 1×
“The rapid development of AI and generative machine learning technologies [7], such as GPT-3 [5] and most recently ChatGPT, has made it critical to investigate what new forms of co-creativity such tools may enable and how it can be shaped to align with human values, especially as several of these technologies are expli…”
BackgroundLuger, E., & Sellen, A. (2016) · Proceedings of the 2016 CHI Conference on Human Factors in Computing Systems · doi:10.1145/2858036.2858288 · Cited by 1,176
Prompt Programming for Large Language Models: Beyond the Few-Shot Paradigm
Reynolds, L., & McDonell, K. (2021) · Extended Abstracts of the 2021 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3411763.3451760 · Cited by 952 · cited 4×
“As has been discussed earlier, the users’ work of fguring out a working syntax is a non-trivial task in the context of the open natural language interaction with large language models, and has been described in terms of prompt engineering or prompt programming [25].”
BackgroundInfluentialDesign-oriented human-computer interaction
Fallman, D. (2003) · Proceedings of the SIGCHI Conference on Human Factors in Computing Systems · doi:10.1145/642611.642652 · Cited by 485
Mapping the Landscape of Creativity Support Tools in HCI
Frich, J., MacDonald Vermeulen, L., Remy, C., Biskjaer, M. M., & Dalsgaard, P. (2019) · Proceedings of the 2019 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3290605.3300619 · Cited by 410 · cited 2×
“There is substantial interaction design research into ways of supporting the early stages of design processes, such as ideation and sketching [10, 12, 14, 36].”
BackgroundDesign ideation: the conceptual sketch in the digital age
Jonson, B. (2005) · Design Studies · doi:10.1016/j.destud.2005.03.001 · Cited by 298
Technology and More-Than-Human Design
Giaccardi, E., & Redström, J. (2020) · Design Issues · doi:10.1162/desi_a_00612 · Cited by 286
Research works printed but not linked: 4
- 20. Jon McCormack, Alan Dorin, and Troy Innocent. 2004. Generative Design: A Paradigm for Design Research.. In DRS Biennial Conference Series. https://dl. designresearchsociety.org/drs-conference-papers/drs2004/researchpapers/171
- 27. Donald A. Schön. 1987. Educating the refective practitioner: Toward a new design for teaching and learning in the professions. Jossey-Bass, San Francisco, CA, US. Pages: xvii, 355.
- 32. Ron Wakkary. 2020. Nomadic Practices: A Posthuman Theory for Knowing
- 36. Danielle Wilde, Anna Vallgårda, and Oscar Tomico. 2017. Embodied Design 2208417 Ideation Methods: Analysing the Power of Estrangement. In Proceedings of the
Cited by
Items 201–212 of 212
Stewart, R., Anise, O., Hogan, A., & Griffin, A. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2609.26725
The Double Bind of Content Moderation in Visual GenAI Tools for Social Care
Grönvall, E., & van der Maden, W. (2026) · Nordic Conference on Human-Computer Interaction · doi:10.1145/3829807.3829908
The Second Workshop on Designing with AI
Okopnyi, P., van der Maden, W., Paananen, V., Kalving, M., Bachinski, M., Grassini, S., Väänänen, K., Klokmose, C. N., Grønbæk, J. E. S., Ivarsson, J., et al. (2026) · Nordic Conference on Human-Computer Interaction · doi:10.1145/3821402.3830214
The Dissonance Workshop: Live Performance and Generative Friction with AI
Snow, D., Cohen, A. E., Encinas, E., Schütt, J., Lindley, J., & Barry, M. (2026) · Nordic Conference on Human-Computer Interaction · doi:10.1145/3821402.3830199
Drawing the Line: Where AI Guidance and Human Creativity Meet in Emotion-Driven Comic StoryboardingPreprint
Shen, J. J., Pu, I., Briseño, A., Kim, H., Lu, F., Alghowinem, S., Breazeal, C., & Park, H. W. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2610.09155
Hosseinian, F., & Sheikhansari, I. (2026) · AI and Ethics · doi:10.1007/s43681-026-01437-0
Fuzzy Kano Validation of Generative AI-Curated Features for Simponia Redesign
Praadita, F. N., Zulaikha, E., & Sabar, S. (2026) · Journal of Business Social and Technology · doi:10.59261/bustechno.v7i4.799
Mei, Y., Zhao, W., Duh, H., & Zhou, Z. (2026) · Design and Artificial Intelligence · doi:10.1016/j.daai.2026.100119
Šklebar, J., Martinec, T., Škec, S., & Štorga, M. (2026) · Design Science · doi:10.1017/dsj.2026.10073
Karahanoğlu, A., Ortega, A. G., & Tholander, J. (2026) · Proceedings of the Second Annual Conference on Sports and Human-Computer Interaction · doi:10.1145/3838843.3838844
Self-citationGrigoriu, A., & Buraga, S. C. (2026) · Procedia Computer Science · doi:10.1016/j.procs.2026.09.185
Lin, L., Gao, M., Cheng, Y., 艾, D. 达. A., Shen, S., & Shadiev, R. (2026) · Thinking Skills and Creativity · doi:10.1016/j.tsc.2026.102419
Metadata
- Authors
- Tholander, J., & Jonsson, M.
- Affiliations
- Stockholm University (SE)
- Södertörn University, Sweden
- Venue
- Proceedings of the 2023 ACM Designing Interactive Systems Conference
- Publisher
- ACM
- Published
- 2023-07-10
- Pages
- 1930-1940
- OpenAlex
- W4383679937
- Semantic Scholar
- 04bf0f8249b21a3ffb92a158247f784566530e3d
- Cited by
- 148
- References
- 33
- Citations by year
- 2026: 41 · 2025: 58 · 2024: 48 · 2023: 1
- FWCI
- 130.76
- Type
- conference paper
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- Locations
- Designing Interactive Systems Conference (publishedVersion, cc-by)
- DiVA (Stockholm University) (submittedVersion, other-oa)
- Topics
- Physical Sciences › Engineering › Mechanical Engineering › Design Education and Practice
- Physical Sciences › Computer Science › Human-Computer Interaction › Innovative Human-Technology Interaction
- Physical Sciences › Computer Science › Computer Graphics and Computer-Aided Design › Digital Media and Visual Art
- Keywords
- design ideation, generative AI, large language models, GPT-3, sketching, early prototyping, human-AI co-creation, design process
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.