Refining Theory–Informed Interview Guides Through Human–AI Socio–Technical Prototyping

Authors

• Rania Kaja, University College Cork, Cork, Ireland; Taibah University, Yanbu, Saudi ArabiaFollow
• Karen Neville, University College Cork, Cork, IrelandFollow
• Stephen Treacy, University College Cork, Cork, IrelandFollow
• Simon Woodworth, University College Cork, Cork, IrelandFollow

Abstract

This paper introduces a practical and replicable socio–technical method for refining qualitative interview guides through structured human–AI collaboration. A generative AI system (ChatGPT) was used to role-play participants, allowing researchers to test and improve theory–informed questions through a two-layer workflow: (1) designing structured prompts that elicit realistic role-based responses, and (2) systematically evaluating those responses using criteria adapted from the Interview Protocol Refinement (IPR) framework. Applied in a healthcare study, this method supported the refinement of question clarity, relevance, and alignment with theoretical constructs, and the resulting guide was later used to elicit rich and reflective responses in real interviews. The main contribution is a replicable early–stage prototyping method showing how structured prompt engineering can refine qualitative instruments transparently and efficiently when traditional piloting is difficult. Although demonstrated in healthcare, the approach is conceptually and methodologically applicable to other IS contexts where expert access is limited.

Recommended Citation

Kaja, Rania; Neville, Karen; Treacy, Stephen; and Woodworth, Simon, "Refining Theory–Informed Interview Guides Through Human–AI Socio–Technical Prototyping" (2026). UK Academy for Information Systems Conference Proceedings 2026. 17.
https://aisel.aisnet.org/ukais2026/17