Hybrid interpretation with generative AI: a pilot study using the A Duo with ChatGPT instrument

Abstract

Generative artificial intelligence is reshaping analytical practices and raises questions about how meaning is constructedwhen analysts work in dialogue with a generative system. This article presents <em>A Duo with ChatGPT</em>, a structured instrumentdesigned to make hybrid interpretation empirically traceable during a qualitative analysis task. Our contribution is methodological,focussing on instrument design and feasibility rather than evaluating ChatGPT’s performance. The frameworkprovides an operational definition of hybrid interpretation and specifies four epistemic dimensions (distributed agency,interpretive abduction, epistemic control, and analytic metacognition). The instrument organises the task into successivephases that alternate between human-only interpretation and guided interactions with ChatGPT and asks participants to recordprompts, system outputs, decisions, and brief annotations of significant moments. The instrument was piloted with threeparticipants with education-related backgrounds and different profiles, an undergraduate student in Pedagogy, an in-serviceprimary teacher, and a doctoral researcher. The pilot suggests that the instrument is feasible and generates analysable processrecords that can be read through the four epistemic dimensions in participants’ written accounts. The article discusses howthese traces support a process-based reading of hybrid interpretation and outlines directions for refinement and replication.