"She was useful, but a bit too optimistic": Augmenting Design with Interactive Virtual Personas

2025-08-26

AI Summary

Traditional user personas suffer from static representation, low designer engagement, and poor adaptability to iterative design processes. To address these limitations, this paper introduces Interactive Virtual Personas (IVPs)—the first LLM-driven, multimodal dialogue system integrated into human-centered design practice. IVPs enable designers to conduct real-time, voice-based user interviews, ideation sessions, and prototype evaluations. Leveraging prompt engineering, human-in-the-loop design principles, and speech interface technologies, IVPs dynamically simulate user needs through bidirectional, context-aware interaction. Empirical evaluation demonstrates that IVPs significantly improve information acquisition efficiency, enhance creative ideation, and accelerate feedback loops. However, IVPs exhibit optimistic bias and behavioral inconsistencies, underscoring their role as complementary—rather than substitutive—tools for authentic user participation. Critical challenges concerning representational fidelity, algorithmic bias, and ethical implications necessitate careful mitigation strategies.

Technology Category

• Humans and AI: Game Design — Virtual Humans, NPCs and Autonomous Characters
• Cognitive Modeling & Cognitive Systems: Simulating Human Behavior
• Intelligent Robots: Human-Robot Interaction

Application Category

• User Modeling, Personalization and Recommendation: User modeling and simulation for interactive and conversational systems
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Personas have been widely used to understand and communicate user needs in human-centred design. Despite their utility, they may fail to meet the demands of iterative workflows due to their static nature, limited engagement, and inability to adapt to evolving design needs. Recent advances in large language models (LLMs) pave the way for more engaging and adaptive approaches to user representation. This paper introduces Interactive Virtual Personas (IVPs): multimodal, LLM-driven, conversational user simulations that designers can interview, brainstorm with, and gather feedback from in real time via voice interface. We conducted a qualitative study with eight professional UX designers, employing an IVP named "Alice" across three design activities: user research, ideation, and prototype evaluation. Our findings demonstrate the potential of IVPs to expedite information gathering, inspire design solutions, and provide rapid user-like feedback. However, designers raised concerns about biases, over-optimism, the challenge of ensuring authenticity without real stakeholder input, and the inability of the IVP to fully replicate the nuances of human interaction. Our participants emphasised that IVPs should be viewed as a complement to, not a replacement for, real user engagement. We discuss strategies for prompt engineering, human-in-the-loop integration, and ethical considerations for effective and responsible IVP use in design. Finally, our work contributes to the growing body of research on generative AI in the design process by providing insights into UX designers' experiences of LLM-powered interactive personas.

Problem

• Addressing static personas' limitations in iterative design workflows
• Introducing interactive virtual personas for real-time designer engagement
• Exploring LLM-driven user simulations to complement human user input

Innovation

• LLM-driven conversational user simulations
• Real-time voice interface for designer interaction
• Multimodal personas for iterative design feedback