Prompt Quality Analysis in AI-Assisted Learning of Database Programming: Pedagogical Insights from a University-Level Intervention

Abstract

Integration of Artificial Intelligence (AI) tools in higher education has transformed the teaching and learning strategy, especially in technical domains such as database programming. This study investigates the relationship between the quality of student-generated AI prompts and traditional database programming proficiency in higher education. Through quantitative analysis of 20 student submissions, we evaluate prompt quality across three dimensions—Specificity, Clarity, and Context—and examine their correlation with conventional assessment performance. Our findings reveal that Specificity in prompt writing shows the strongest association with traditional database skills (r = 0.51, p < 0.05), suggesting that students who craft more precise AI instructions also demonstrate stronger technical competencies. Clarity emerges as the most challenging aspect for learners (M = 1.85/4), highlighting gaps in technical communication. The study provides actionable insights for integrating prompt engineering into database education while maintaining focus on foundational knowledge. We discuss implications for curriculum design, including the need for explicit writing instruction and ethical considerations in AI-augmented learning. Limitations and future research directions are outlined, particularly regarding longitudinal effects of prompt-writing training and ethical dimensions of educational AI use. This work contributes to emerging scholarship on AI's role in computing education by demonstrating how prompt quality reflects and potentially enhances traditional learning outcomes.