Abstract
Recent advances in Generative AI (GenAI) present promising opportunities to enhance user interview tasks, such as transcription and sentiment analysis. However, existing GenAI-powered interview tools tend to operate in isolation, supporting only discrete stages of the interview process. This fragmentation constrains designers' abilities to conduct fluid and responsive interviews. To explore how GenAI might be effectively integrated throughout the interview workflow, we conducted focus groups with eight UX design practitioners. Participants identified key limitations of current GenAI tools and articulated desired GenAI functions across all phases of the interview process. Grounded in a four-stage interview process, this study introduced a GenAI-powered workflow that embeds GenAI functions into each stage while maintaining human control and interpretive authority. We proposed Noma, a high- fidelity conceptual prototype that serves as a design probe to demonstrate the implementation of the workflow. Our study offered practical insights for designing cohesive GenAI-powered tools that support all stages of user interviews.
Keywords
AI-Augmented Interviews; Generative AI; UX Research; Human-AI Collaboration
DOI
https://doi.org/10.21606/iasdr.2025.1079
Citation
Chen, K., Li, S., Mei, Y.,and Zhou, Z.(2025) An Exploratory Research on Empowering the User Interview Process with Generative AI, in Chang, C.-Y., and Hsu, Y. (eds.), IASDR 2025: Design Next, 02-05 December, Taiwan. https://doi.org/10.21606/iasdr.2025.1079
Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License
Conference Track
Track 4 - Human-Centered AI
An Exploratory Research on Empowering the User Interview Process with Generative AI
Recent advances in Generative AI (GenAI) present promising opportunities to enhance user interview tasks, such as transcription and sentiment analysis. However, existing GenAI-powered interview tools tend to operate in isolation, supporting only discrete stages of the interview process. This fragmentation constrains designers' abilities to conduct fluid and responsive interviews. To explore how GenAI might be effectively integrated throughout the interview workflow, we conducted focus groups with eight UX design practitioners. Participants identified key limitations of current GenAI tools and articulated desired GenAI functions across all phases of the interview process. Grounded in a four-stage interview process, this study introduced a GenAI-powered workflow that embeds GenAI functions into each stage while maintaining human control and interpretive authority. We proposed Noma, a high- fidelity conceptual prototype that serves as a design probe to demonstrate the implementation of the workflow. Our study offered practical insights for designing cohesive GenAI-powered tools that support all stages of user interviews.