This paper explores the impact of generative ar-tificial intelligence on text production, focusing on the use of prompt-based AI tools. We propose to move beyond the current use of Large Language Models (LLMs) as “ghostwriters” and advocate for their relevance as tools to enhance the development of epistemic-heuristic strategies to facilitate knowledge construction. Our planned study aims to gain insight into the cognitive processes and behavior of university students when interacting with content generated by LLMs using eye tracking technology. Based on these insights, we explore the potential of providing cognition-aware assistance to enhance writing skills in educational contexts.