Integrating GenAI Tools Into Software Engineering Education

This article addresses the challenge of integrating GenAI tools into formal higher education, specifically in software engineering, where structured approaches for their adoption into teaching and learning practices are currently lacking. The goal of this research is to explore how GenAI tools can be applied throughout various phases of the software development lifecycle and to propose a methodology for their effective incorporation into software engineering education. The methodology focuses on three key aspects: learning, phase‐specific GenAI tool guidance, and project‐based mentorship. The research was conducted with 21 final‐year undergraduate students who used GenAI tools such as ChatGPT, GitHub Copilot, Gemini, and Tabnine to develop a full‐stack application as part of their coursework. The research model was based on the integrated TTF‐TAM model, and data analysis was performed using structural equation modeling (SEM) to assess the alignment of these tools with course tasks, students' satisfaction, their readiness to adopt GenAI tools for learning, and the learning outcomes achieved. The findings demonstrate that, with effective mentoring and guided use of GenAI tools, students gained the necessary knowledge and practical experience while maintaining high levels of motivation. This research highlights the potential of GenAI tools to enhance learning outcomes and supports their adoption as part of the learning process in software engineering education.