ResearchResearch paper

Interviews with 17 UI designers find prompt-to-design tools accelerate ideation but are not end-to-end designers

A paper submitted on November 9 interviewed 17 U.S.-based UI designers with prior hands-on experience. Participants mainly used prompt-to-design generators such as Uizard, v0, and Figma Make for ideation, rapid prototyping, and variations rather than complete deliverables. They valued speed and inspiration while raising concerns about output quality, creativity, and erosion of design craft.

Why it matters

The study provides practice-based counterevidence to claims that generated interfaces replace the design process. The current value is closer to shortening exploration and helping people compare options. Brand fit, user needs, domain constraints, security, and final judgment still depend on designers and organizational policy.

A closer look

The study used semi-structured remote interviews lasting about 60 minutes. Participants were adults in the United States with prior prompt-to-design experience; 16 were recruited through social media and one through referral, with recruitment ending at thematic saturation. Designers reported repeated and multimodal prompting as well as prompt co-creation with project managers, engineers, and AI. Some organizations encouraged experimentation, while others restricted use because of intellectual property, data security, brand consistency, and accountability. Several participants at large organizations reported that only internally approved enterprise AI systems could receive company data.

Who this is for

Design leaders, product teams, design-system owners, researchers, security teams, and governance teams evaluating prompt-to-design tools such as v0, Figma Make, or Uizard.

Original sources

Revisions & corrections (1)

— A primary research paper with a confirmed submission date, explicit methodology, supported findings, and stated limitations directly examines real-world use of generative UI design tools.

Related events

Research

A 17-million-element study links missing GUI accessibility labels to both agent-training debt and benchmark selection bias

A paper submitted on November 11 and accepted at AISSA 2026 analyzes 17,373,614 interface elements in Rico and AndroidControl. Under the authors' coding rule, content-description coverage among elements that need it is 17.74% and 57.27%, respectively. Input controls are the least labelled role in both corpora.

Research

reComposer replaces one-shot prompting with an editable plan that exposes intermediate image-making decisions

The reComposer paper, submitted on November 9, introduces an image-generation interface centered on an editable plan. It decomposes intent into elements such as subject, composition, and palette, lets a user revise each through conversation or direct manipulation, then synthesizes the plan into a final prompt and image. In a first-use study, eight professionals who create images in their day-to-day work reported greater control and ownership than with ordinary prompting.