Abstract
This study investigates how large language models (LLMs) enable new modes of collaboration in zero-waste fashion design, addressing the challenge that traditional practice relies heavily on tacit knowledge developed through iterative material experimentation. Using first-person autoethnography, the research examines how a designer collaborates with ChatGPT and Claude across concept ideation, digital pattern development, toile construction, and sample production, tracing how technical terminology, design reasoning, and material knowledge are negotiated, misinterpreted, and re-articulated in human–AI interaction. Findings demonstrate that ChatGPT excels at generative conceptual prompting, whereas Claude better handles complex pattern-cutting rules; nevertheless, both require iterative, dialogue-based correction. The research proposes the AI+Zero-Waste Fashion Design Process Model, which provides designers with practical strategies for integrating LLMs into zero-waste design practice.
Keywords
Large Language Models, Zero-Waste Fashion Design, Design Dialogue, Multimodal Workflows, Human-AI Collaboration
DOI
https://doi.org/10.21606/drs.2026.1978
Citation
Li, P., Kettley, S., James, M., and Taylor, N. (2026) Dialoguing with Design: How LLMs Mediate Multimodal Workflows in Zero-Waste Fashion, 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.2026.1978
Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License
Included in
Dialoguing with Design: How LLMs Mediate Multimodal Workflows in Zero-Waste Fashion
This study investigates how large language models (LLMs) enable new modes of collaboration in zero-waste fashion design, addressing the challenge that traditional practice relies heavily on tacit knowledge developed through iterative material experimentation. Using first-person autoethnography, the research examines how a designer collaborates with ChatGPT and Claude across concept ideation, digital pattern development, toile construction, and sample production, tracing how technical terminology, design reasoning, and material knowledge are negotiated, misinterpreted, and re-articulated in human–AI interaction. Findings demonstrate that ChatGPT excels at generative conceptual prompting, whereas Claude better handles complex pattern-cutting rules; nevertheless, both require iterative, dialogue-based correction. The research proposes the AI+Zero-Waste Fashion Design Process Model, which provides designers with practical strategies for integrating LLMs into zero-waste design practice.