Prompt-to-Design Generators: Streamlining UI Design with GenAI

Paper: Designing UIs with GenAI: Understanding the Use, Benefits, and Limitations of Prompt-to-Design Generators

Authors: Jingzhou Ye, Yao Li, Xueqiang Wang

Executive Summary

Recent research has explored the use of generative AI (GenAI) in user interface (UI) design, particularly through tools known as prompt-to-design generators (P2dGens). These innovative tools allow designers to generate UI prototypes based on textual prompts, streamlining the design process. As the adoption of P2dGens becomes more widespread, understanding how designers incorporate these tools into their workflows is essential for organizations looking to enhance their design capabilities.

The study involved semi-structured interviews with 17 UI designers, shedding light on their experiences with P2dGens. The research highlights several key findings regarding how these tools are utilized, their advantages, limitations, and the broader organizational context in which they operate.

Designers primarily use P2dGens as accelerators for ideation rather than as comprehensive solutions for the entire design process. This indicates that while P2dGens can significantly enhance the early stages of design—helping to generate ideas quickly—they are not typically relied upon to finalize designs or replace traditional design methods. The research emphasizes that designers employ a range of prompting strategies, both individually and collaboratively, to maximize the benefits of these tools.

While many designers reported increased efficiency and a boost in creative inspiration from using P2dGens, they also expressed concerns. Some worry about a potential dilution of personal creativity and the overall quality of design outputs when relying too heavily on AI-generated suggestions. This tension between leveraging AI for efficiency and maintaining a unique design voice is a critical consideration for organizations integrating these tools.

The study also uncovered emerging governance practices around the use of P2dGens. Attitudes toward these tools vary widely across organizations, indicating that some companies may embrace P2dGens enthusiastically, while others could approach them with caution. This variability suggests that successful integration of P2dGens into design workflows may depend on the organizational culture and the support systems in place for designers.

The insights from this research are valuable for organizations looking to implement P2dGens in their design processes. By understanding how designers interact with these tools, companies can better support their teams, address concerns about creativity and quality, and foster an environment conducive to effective human-AI collaboration in design. The findings also contribute to the broader conversation about the role of AI in creative fields, highlighting the need for thoughtful integration strategies that balance technological benefits with human creativity.

Academic Abstract

The integration of generative AI (GenAI) into user interface (UI) design has led to prompt-to-design generators (P2dGens), tools that enable designers to create UI prototypes from textual prompts efficiently. Despite their growing adoption, little is known about how designers use these tools in everyday practice, their benefits, and limitations. We conducted semi-structured interviews with 17 UI designers to investigate P2dGens use, focusing on workflow integration, attitudes toward generator-assisted design, and the organizational climate. Findings show that designers primarily use P2dGens as ideation accelerators rather than end-to-end solutions, and they adopt a variety of individual and collaborative prompting strategies. Designers expressed complex attitudes, noting gains in efficiency and inspiration while also highlighting concerns about loss of personal creativity and design quality. We also observed emerging governance practices and varying attitudes within organizations toward P2dGens. These insights illuminate how P2dGens reshape UI design workflows and contribute to understanding human-AI collaboration in UI design.