When AI only asks: how question-driven dialogue shapes prewriting in the classroom

Generative artificial intelligence has altered the conditions under which pupils learn to write, raising concerns that the slow, effortful work of idea generation and elaboration may be bypassed when fluent text can be produced instantly. This study examines how generative AI can be employed to support students’ thinking during a prewriting session where they prepared to write a text about their hometown. Using reflexive content analysis, we examined 201 question–response pairs across entire prewriting dialogues to trace how seventeen lower-secondary students in Norway took up, reshaped, limited, or resisted questions from a restricted GPT-4–based chatbot programmed to ask one question at a time while refusing to generate text on pupils’ behalf. The analysis drew on both a cognitive and a sociocultural view of writing. Results revealed that students engaged with the question-driven format in markedly different ways: some sustained stable descriptive engagement; others negotiated relevance through redirection, and some constrained the dialogue through minimal uptake or repeated resistance. Sensory and memory questions often supported elaboration by anchoring attention in concrete experience, while reflective questions were productive mainly when grounded in such detail. The findings suggest that the value of a question-only chatbot lies mostly in how pupils engage with the dialogic space created. Implications for practice are that constrained generative AI can support students in the prewriting phase of classroom writing, and that some students need additional support and motivation from the teacher or peers in such sessions.