AI Augmented Software Engineering - A Case of Competency-Based Education and its Institutional Effectiveness

Abstract

The transformative impact of Artificial Intelligence (AI) on software engineering (SE) necessitates a parallel evolution in educational paradigms. This paper presents a comprehensive case study on the institutional effectiveness of a competency-based educational (CBE) intervention designed to integrate AI-augmented tools into an undergraduate capstone project. A cohort of thirty students participated in a hands-on workshop focused on orchestrating a requirements-to-code workflow using a toolchain of n8n, JIRA, GitHub, and Large Language Models (LLMs). Grounded in the ARCS (Attention, Relevance, Confidence, Satisfaction) model of motivational design, this study employed a pre-test/post-test research design to quantitatively measure changes in student motivation. A detailed analysis of collected 5-point Likert scale survey data revealed statistically significant improvements ($\mathbf{p}\lt$ 0.001) across all four ARCS constructs, with large effect sizes (Cohen’s $\mathbf{d} \boldsymbol{\gt} \mathbf{0. 8}$). The most substantial gain was in Confidence, which increased by $\mathbf{1. 2 0}$ points, indicating a successful transition from apprehension to self-assurance. The findings robustly demonstrate that a structured, project-based workshop can significantly enhance student motivation and perceived competency in AI-augmented software engineering. This study provides a validated, replicable model and a robust assessment framework for institutions seeking to modernize their SE curricula, thereby enhancing institutional effectiveness in preparing a workforce for human-AI collaboration.

Ähnliche Arbeiten