Interaction Design with Generative AI: An Empirical Study of Emerging Strategies Across the Four Phases of Design

TL;DR

This empirical study explores how Generative AI can support each phase of human-centered interaction design, revealing effective prompting strategies and highlighting the need for manual quality assessment of AI-generated outcomes.

Contribution

It provides the first comprehensive empirical analysis of Generative AI's role across all four phases of interaction design, identifying successful prompting patterns and challenges.

Findings

Generative AI supports all key design phases but outcomes need manual quality checks.

Prompting strategies vary depending on design phase and activity.

Designers can leverage AI to enhance creativity and efficiency in interaction design.

Abstract

Generative Artificial Intelligence (Generative AI) holds significant promise in reshaping interactive systems design, yet its potential across the four key phases of human-centered design remains underexplored. This article addresses this gap by investigating how Generative AI contributes to requirements elicitation, conceptual design, physical design, and evaluation. Based on empirical findings from a comprehensive eight-week study, we provide detailed empirical accounts and comparisons of successful strategies for diverse design activities across all key phases, along with recurring prompting patterns and challenges faced. Our results demonstrate that Generative AI can successfully support the designer in all key phases, but the generated outcomes require manual quality assessments. Further, our analysis revealed that the successful prompting patterns used to create or evaluate outcomes of design activities require different structures depending on the phase of the design and the specific design activity. We derive implications for designers and future tools that support interaction design with Generative AI.