Abstract
The increasing integration of Large Language Models (LLMs) into design workflows is reshaping how designers make decisions. This study examines the influence of LLMs on design decision-making during the early stages of service design, through a diary study with service design practitioners. By analysing usage logs and conducting post-intervention focus group interviews, we examine collaborative decision-making across three interaction dimensions: designer–designer, designer–LLM, and LLM–LLM. The findings reveal that LLMs reshape the internal decision logic and collaboration mode within service design teams. Across different stages of collaborative decision-making with human, LLMs take on varying roles as apprentice, collaborator, advisor, expert, co-creator, and evaluator. This study contributes to the understanding of AI-assisted design collaboration by mapping the evolving dynamics of decision-making in human–AI co-creation contexts.
Keywords
Large Language Model, service design, collaborative decision-making, Human-AI interaction
DOI
https://doi.org/10.21606/drs.2026.2569
Citation
Li, Y., and Park, H. (2026) Exploring How LLMs Shape Collaborative Decision-Making in Service Design, 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.2026.2569
Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License
Included in
Exploring How LLMs Shape Collaborative Decision-Making in Service Design
The increasing integration of Large Language Models (LLMs) into design workflows is reshaping how designers make decisions. This study examines the influence of LLMs on design decision-making during the early stages of service design, through a diary study with service design practitioners. By analysing usage logs and conducting post-intervention focus group interviews, we examine collaborative decision-making across three interaction dimensions: designer–designer, designer–LLM, and LLM–LLM. The findings reveal that LLMs reshape the internal decision logic and collaboration mode within service design teams. Across different stages of collaborative decision-making with human, LLMs take on varying roles as apprentice, collaborator, advisor, expert, co-creator, and evaluator. This study contributes to the understanding of AI-assisted design collaboration by mapping the evolving dynamics of decision-making in human–AI co-creation contexts.