Gradual Generation of User Interfaces as a Design Method for Malleable Software

TL;DR

This paper introduces a new design method for AI-generated user interfaces that structures customizations into intermediate layers, enhancing discoverability and user control during interface generation.

Contribution

It proposes a novel gradual generation approach that organizes customizations into layers, improving user experience and interface flexibility in GenUI applications.

Findings

Prototype websites demonstrate improved customization discoverability.

Designers can support expanded customization while maintaining simplicity.

Method enhances user control over AI-generated interfaces.

Abstract

AI is growing increasingly capable of automatically generating user interfaces (GenUI) from user prompts. However, designing GenUI applications that enable users to discover diverse customizations while preserving GenUI's expressiveness remains challenging. Current design methods -- presenting prompt boxes and leveraging context -- lack affordances for customization discovery, while traditional menu-based approaches become overly complex given GenUI's vast customization space. We propose Gradually Generating User Interfaces -- a design method that structures customizations into intermediate UI layers that AI gradually loads during interface generation. These intermediate stages expose different customization features along specific dimensions, making them discoverable to users. Users can wind back the generation process to access customizations. We demonstrate this approach through three prototype websites, showing how designers can support GenUI's expanded customization capabilities while maintaining visual simplicity and discoverability. Our work offers a practical method for integrating customization features into GenUI applications, contributing an approach to designing malleable software.