DuoSketch: How Pairs Navigate Challenges in AI-Supported Collaborative Design Ideation

2026-10-07

AI Summary

This study addresses the challenge that generative AI struggles to accommodate shared design intent in dyadic collaboration, resulting in semantic loss and decision desynchronization during creative integration. To overcome this, we propose a collaborative system integrating a shared canvas with individual AI instances, featuring bidirectional bridging mechanisms—“AI-to-Shared” and “Shared-to-AI.” Employing a multi-agent coordination architecture alongside human-computer interaction prototypes, we conduct a qualitative investigation. This work identifies three core challenges and validates the critical role of manual bridging in mitigating misalignment between AI outputs and team objectives. Furthermore, it reveals latent communication costs inherent in such collaborative processes, thereby providing a theoretical foundation for the future design of collaborative AI systems.

Abstract

Generative AI offers new resources for collaborative design ideation, yet how designers work with it as a shared concept develops remains underexplored. We developed DuoSketch, integrating a shared canvas and live transcripts with a separate AI for each member of a pair. An exploratory qualitative study with 12 pairs identified three challenges: unresolved fit between AI proposals and shared design purposes, shared meanings not expressed in AI responses, and agreed changes missing from later outputs. We found that pairs navigated these challenges through bridging work in two directions: AI -> Shared Design (reworking features, developing uses, and assessing fit with shared requirements) and Shared Design -> AI (supplying materials, explaining meanings, and communicating decisions). We discuss how future AI systems can support the joint exploration and articulation of design ideas.

Problem

• collaborative design ideation
• generative AI
• human-AI collaboration
• shared concept

Innovation

• Collaborative Design Ideation
• Generative AI
• Shared Canvas
• Bridging Work
• Human-AI Interaction