Virtual User Lab: An Interactive System for Simulating User Perspectives with AI Personas for Ideation and Evaluation
- Published in
- Proceedings of the 34th ACM Conference on User Modeling, Adaptation and Personalization (UMAP 2026)
- Publisher
- ACM
- Year
- 2026
- Pages
- 556–558
- AI persona
- Large language models
- User modeling
- Simulated users
- Innovation management
- Decision support
Abstract
Designers, researchers, and decision-makers often need to reason about diverse user and stakeholder perspectives at early stages, when empirical user research is costly or difficult to repeat. We present the Virtual User Lab (VUL), an interactive system that simulates how different target user groups may respond to product ideas and decision scenarios. VUL allows product teams to define end-user characteristics and personas, configure decision scenarios, and incorporate contextual information to ground responses using language models. This makes it possible to explore how different perspectives react to alternative ideas and to compare them in a structured way, making trade-offs visible. By enabling side-by-side comparison and interaction with these perspectives, the system supports more systematic reasoning about user assumptions.
Cite this paper
Kumar, C., Knecht, C., Lange, J., Saini, B. K., & Peissner, M. (2026). Virtual User Lab: An Interactive System for Simulating User Perspectives with AI Personas for Ideation and Evaluation. In Proceedings of the 34th ACM Conference on User Modeling, Adaptation and Personalization (UMAP 2026).