Scanvas system helps designers find linked ideas that create more value
Scanvas: Discovering and Developing Synergistic Opportunities in Generative Design Spaces
Human-Computer Interaction
Summary
Good design can be more than just adding features—it can create extra value by combining goals in smart ways, but finding these combinations is hard. The authors developed Scanvas, a tool that breaks down ideas into parts and then looks for ways to link goals, fix weaknesses, or share components to make better designs. Their tests with professional designers showed Scanvas helps find more valuable and creative ideas than existing AI tools. This system aims to support designers in exploring design spaces more effectively and discover new opportunities.
What this means in practice
- •For product designers: Help designers systematically find and develop design ideas that combine goals for greater overall value in product development.
- •For industrial design teams: Provide teams an AI-driven interactive system to explore and improve design concepts by linking components and turning issues into resources.
- •For innovation consultants: Offer consultants a tool to generate synergistic design options that go beyond simple feature combinations for client solutions.$Commercial implications: Enables creation of AI-powered ideation software for consultants seeking novel and high-impact design opportunities.
Authors
Yaqing Yang, Aniket Kittur, Hongyu Howie Wang, Nikolas Martelaro, Matt Klenk, Yan-Ying Chen, Matthew K. Hong
Abstract
Good design is often synergistic, creating super-additive value by linking goals so that existing resources produce greater outcomes. However, finding these synergistic opportunities in sparse design spaces is difficult, and current LLM-supported ideation tools largely default to additive paradigms such as feature blending, variant generation, or local patching. We present Scanvas, an AI-supported system for systematically discovering and developing synergistic design opportunities. Scanvas operationalizes synergy through a two-step computational process: first, it decomposes seed ideas into explicit properties (components, behaviors, surpluses, and issues) to enrich the design space; second, it systematically searches across enriched ideas using three theory-grounded strategy operators: unlocking or strengthening goals, turning weaknesses into resources, and sharing components across functions. We instantiate Scanvas as an auto-generation pipeline and an interactive system. Pipeline ablations and a user study with 12 professional designers demonstrate that Scanvas enables users to surface and develop significantly higher-quality, synergistic concepts compared to LLM ideation baselines.