Abstract
Text-to-image Generative AI (T2I GenAI) tools have become commonplace in design practice and education, raising important questions about their role alongside exploratory sketching. This article explores T2I GenAI as an emerging visualisation modality that alters how designers create and explore ideas. Specifically, we examine the acute tensions between GenAI’s near-instantaneous, high-fidelity, text-driven outputs versus the ambiguous, iterative, and reflective act of traditional sketching. We report on a one-day ideation activity by 13 student designers, in which we analysed 1292 prompts, generated imagery, alongside reflective survey data to uncover patterns of productive and counterproductive T2I GenAI use. We outline prompting behaviours that characterise (counter)productive sketching behaviours, including broad exploration, reinterpretation, ambiguity and design fixation. Through our findings, we contribute practical prompting strategies to employ T2I GenAI to support and stimulate traditional sketching. As such, we provide insights on how AI can augment and challenge the cognitive and creative value of sketching.
Keywords
Generative AI, Text-to-image AI, Exploratory Sketching, Prompting Strategies, AI Ideation
DOI
https://doi.org/10.21606/drs.2026.1595
Citation
Ranscombe, C., Tan, L., Zhang, W., and Afif, N. (2026) Friend and foe: Characterising (counter)productive prompting of generative AI to supplement exploratory sketching, 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.2026.1595
Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License
Included in
Friend and foe: Characterising (counter)productive prompting of generative AI to supplement exploratory sketching
Text-to-image Generative AI (T2I GenAI) tools have become commonplace in design practice and education, raising important questions about their role alongside exploratory sketching. This article explores T2I GenAI as an emerging visualisation modality that alters how designers create and explore ideas. Specifically, we examine the acute tensions between GenAI’s near-instantaneous, high-fidelity, text-driven outputs versus the ambiguous, iterative, and reflective act of traditional sketching. We report on a one-day ideation activity by 13 student designers, in which we analysed 1292 prompts, generated imagery, alongside reflective survey data to uncover patterns of productive and counterproductive T2I GenAI use. We outline prompting behaviours that characterise (counter)productive sketching behaviours, including broad exploration, reinterpretation, ambiguity and design fixation. Through our findings, we contribute practical prompting strategies to employ T2I GenAI to support and stimulate traditional sketching. As such, we provide insights on how AI can augment and challenge the cognitive and creative value of sketching.