From Prompt Engineering to Epistemic Prompting: Prompt Trajectories as AI-Mediated Problem Framing in Science Education

Abstract

Prompt engineering is commonly presented as a technical competence for obtaining more accurate, relevant, or well-formatted outputs from large language models (LLMs). However, in STEM education, prompting should also be understood as a continuous epistemic practice. Students interpret contextual and disciplinary cues and adopt expectations about what kind of knowledge, representation, and action are appropriate. Drawing on epistemological framing, and AI-mediated concept-to-decision reasoning, the paper presents a new framework called epistemic prompting and proposes a multi-turn Framing-Prompting Loop. The educationally relevant outcome is a prompt framing trajectory: the sequence of prompts, model responses, learner uptake, disciplinary checks, and reframing moves through which a knowledge task develops. In this framework, an initial prompt establishes a provisional macro-frame by selecting the problem, representations, assumptions, criteria, and distribution of work between learner and model. Each subsequent learner turn can then maintain, specify, challenge, repair, or transform that organization. The implications for AI-mediated STEM instruction, and, specifically, on learner-LLM interaction are also discussed.