Theory-Operationalising Tool Co-Creation: Building Methodology-Specific Analysis Tools Through Human-AI Collaboration. A Position Statement for Qualitative Research Methodology

In this position statement, I articulate an emerging form of human-AI collaboration in qualitative research, i.e. the co-creation of methodology-specific analysis tools through iterative dialogue between domain experts and large language models (LLMs). Crucially, in this approach, I use AI in the coding stage of the development process, producing standalone tools that contain no AI in their operation, thereby addressing significant ethical concerns around data security while leveraging AI's computational translation capacity. Drawing on established critiques of methodologically agnostic computer-assisted qualitative data analysis software (CAQDAS) (COFFEY, HOLBROOK & ATKINSON, 1996; KELLE, 1997; LONKILA, 1995), contemporary work on AI as co-researcher (COSTA, BRYDA, CHRISTOU & KASPERIUNIENE, 2025), and human-AI co-creation frameworks (GIACCARDI & REDSTRÖM, 2020; VERGANTI, VENDRAMINELLI & IANSITI, 2020), in this statement, I position the development of critical incident semantic analysis (CISA) tools as a case study in what I term "theory-operationalising tool co-creation". With this approach, I expand access to methodological tool development, enabling non-programmers to learn to build sophisticated software in weeks rather than the months or years that would be required by traditional development teams while also maintaining robust data security through client-side processing.