AI as intermediary in modern-day ritual: An immersive, interactive production of the roller disco musical Xanadu at UCLA

TL;DR

The paper addresses the gap in AI interfaces by proposing a ritual-based, multi-user framework for human–AI collaboration during a live immersive performance. It describes Xanadu, a UCLA-produced roller-disco musical, where audience contributions are transformed by AI into virtual XR elements and integrated in real time, guided by acolytes and performers. The work introduces a meta-instrument design pattern and a reciprocal interaction loop that enables group creativity and play beyond single-user paradigms. Its findings suggest that ritual dramaturgy can structure complex, interactive AI-enabled performances and motivate future group-oriented AI applications in live media and beyond.

Abstract

Interfaces for contemporary large language, generative media, and perception AI models are often engineered for single user interaction. We investigate ritual as a design scaffold for developing collaborative, multi-user human-AI engagement. We consider the specific case of an immersive staging of the musical Xanadu performed at UCLA in Spring 2025. During a two-week run, over five hundred audience members contributed sketches and jazzercise moves that vision language models translated to virtual scenery elements and from choreographic prompts. This paper discusses four facets of interaction-as-ritual within the show: audience input as offerings that AI transforms into components of the ritual; performers as ritual guides, demonstrating how to interact with technology and sorting audience members into cohorts; AI systems as instruments "played" by the humans, in which sensing, generative components, and stagecraft create systems that can be mastered over time; and reciprocity of interaction, in which the show's AI machinery guides human behavior as well as being guided by humans, completing a human-AI feedback loop that visibly reshapes the virtual world. Ritual served as a frame for integrating linear narrative, character identity, music and interaction. The production explored how AI systems can support group creativity and play, addressing a critical gap in prevailing single user AI design paradigms.

Figures (7)

• Figure 1: Xanadu was an immersive musical performed at UCLA in May 2025.
• Figure 2: Audiences were shown by performers how to create drawings as offerings to the muses, which were transformed into images and objects in the muses' "shrines" by generative AI.
• Figure 3: In Olympus, the audience's movement ultimately brings Kira and Sonny back together.
• Figure 4: The audience's dance moves help build the Xanadu auditorium.
• Figure 5: Generation Task 1, a scene for each muse