Greg Wadley

Samangi Wadinambiarachchi, Jenny Waycott, Greg Wadley

Current AI-powered creativity support tools (AI-CSTs) primarily use text prompting to generate solution-oriented outputs. However, the potential value of multimodal prompting in designer-AI interaction, specifically the introduction of productive friction to encourage iteration and reflection, has not been fully explored. To address this, we developed SketchifAI, a prototype AI-CST, and evaluated it with design students. In a mixed-methods, within-participants study, we examined how different input modalities (text, sketch, and sketch-plus-tags) affected design students' perceived ability to express their intent, their perception of creativity support, and their divergent thinking performance. Our preliminary findings suggest that the sketch modality tended to enhance fluency, with inconclusive evidence for differences in variety, originality, or quality compared to text modality. Yet, paradoxically, participants showed a strong preference for text prompting. We discuss how AI tools might be designed to reintroduce reflection-through-sketching, ensuring that designer-AI interaction supports, rather than erodes, essential design skills in students.

Samangi Wadinambiarachchi, Jenny Waycott, Yvonne Rogers et al.

As designers become familiar with Generative AI, a new concept is emerging: Agentic AI. While generative AI produces output in response to prompts, agentic AI systems promise to perform mundane tasks autonomously, potentially freeing designers to focus on what they love: being creative. But how do designers feel about integrating agentic AI systems into their workflows? Through design fiction, we investigated how designers want to interact with a collaborative agentic AI platform. Ten professional designers imagined and discussed collaborating with an AI agent to organise inspiration sources and ideate. Our findings highlight the roles AI agents can play in supporting designers, the division of authority between humans and AI, and how designers' intent can be explained to AI agents beyond prompts. We synthesise our findings into a conceptual framework that identifies authority distribution among humans and AI agents and discuss directions for utilising AI agents in future design workflows.