Leveraging Generative AI in Support of Self-Directed Learning: Insights from Student Prompting Practices.

Saved in:

Bibliographic Details
Title:	Leveraging Generative AI in Support of Self-Directed Learning: Insights from Student Prompting Practices.
Authors:	Posavec, Kristina¹ kristina.posavec@imin.hr
Source:	International Journal of Instruction. Apr2026, Vol. 19 Issue 2, p281-298. 18p.
Subject Terms:	Autodidacticism, Educational quality, Generative artificial intelligence, Higher education, *Digital literacy, Prompt engineering, Artificial intelligence & ethics
Abstract:	This study explores how undergraduate students engage with generative artificial intelligence (AI) tools in structured prompting tasks and how these interactions relate to self-directed learning (SDL) and AI literacy. A total of 57 students participated in a survey-based study that examined their prior experiences with AI, prompting practices, SDL-related behaviours, perceptions of AI usefulness and ethics, and the pedagogical quality of AI-supported outputs. Findings indicate that nearly all students had prior experience with AI tools and actively engaged in prompt formulation, with most demonstrating specificity and contextual awareness but fewer engaging in iterative refinement. Prompting tasks supported SDL skills such as goal setting, evaluation, and task ownership, though personalization and ethical reflection were less common. Students generally perceived AI as useful and time-saving, yet many expressed uncertainty about ethical boundaries and authorship. The pedagogical quality of outputs was often high, showing structured design, age-appropriate examples, and creative elements. These exploratory results suggest that prompting can serve as both a cognitive and pedagogical practice, supporting learner autonomy and creativity, while highlighting the need for explicit scaffolding in iterative prompting, ethical awareness, and responsible AI use in higher education. [ABSTRACT FROM AUTHOR]
	Copyright of International Journal of Instruction is the property of International Journal of Instruction and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database:	Education Research Complete

Description
Abstract:	This study explores how undergraduate students engage with generative artificial intelligence (AI) tools in structured prompting tasks and how these interactions relate to self-directed learning (SDL) and AI literacy. A total of 57 students participated in a survey-based study that examined their prior experiences with AI, prompting practices, SDL-related behaviours, perceptions of AI usefulness and ethics, and the pedagogical quality of AI-supported outputs. Findings indicate that nearly all students had prior experience with AI tools and actively engaged in prompt formulation, with most demonstrating specificity and contextual awareness but fewer engaging in iterative refinement. Prompting tasks supported SDL skills such as goal setting, evaluation, and task ownership, though personalization and ethical reflection were less common. Students generally perceived AI as useful and time-saving, yet many expressed uncertainty about ethical boundaries and authorship. The pedagogical quality of outputs was often high, showing structured design, age-appropriate examples, and creative elements. These exploratory results suggest that prompting can serve as both a cognitive and pedagogical practice, supporting learner autonomy and creativity, while highlighting the need for explicit scaffolding in iterative prompting, ethical awareness, and responsible AI use in higher education. [ABSTRACT FROM AUTHOR]
ISSN:	1694609X
DOI:	10.29333/iji.2026.19215a