From Prompts to Worlds: How Users Iterate, Explore, and Make Sense of AI-Generated 3D Environments

TL;DR

This study investigates how users interact with text-to-3D AI systems, revealing challenges in spatial specification, episodic presence, and iteration, and suggests improvements for more effective spatial and experiential alignment.

Contribution

It provides the first empirical analysis of user interaction with commercial text-to-3D AI, highlighting key usability barriers and proposing design principles for better spatial and experiential coherence.

Findings

Users can express themes but struggle with spatial details.

Immersion depends on expectation alignment, not sustained presence.

Refinement is hindered by interaction barriers, not user skill.

Abstract

Text-to-3D generative AI systems create navigable environments from natural language prompts, but unlike text-to-image generation, evaluation requires embodied exploration of spatial coherence, scale, and navigability. We present the first empirical study of a commercial text-to-3D platform, combining think-aloud protocols, behavioral observation, and validated measures of usability, presence, and engagement. We report three findings. First, asymmetric expressibility: users readily convey semantic intent (themes, atmosphere) but struggle to specify spatial structure (layout, scale), reflecting a language-to-space limitation rather than a skill deficit. Second, episodic presence: immersion arises when expectations align with outputs but does not accumulate into sustained place illusion. Third, structural iteration breakdowns: refinement fails due to interaction barriers - poor discoverability, opaque feedback, and high temporal costs - rather than user limitations. Together, these dynamics form a reinforcing cycle in which spatial mismatches persist, producing episodic presence and ongoing sensemaking. We reframe text-to-3D interaction as negotiated meaning-making rather than linear prompting, and argue that effective systems require hybrid input modalities, transparent feedback, and low-cost iteration.