Integrating AI into Requirements Quality Learning in Software Engineering Education: A TPACK-Guided Empirical Study

2026-07-30

AI Summary

This study addresses the effective and responsible integration of generative artificial intelligence (GenAI) into concept-intensive software engineering courses, particularly requirements engineering. Grounded in the TPACK framework, the authors designed a scaffolded pedagogical approach that embedded multi-agent AI tools into a master’s-level requirements quality analysis task, guiding students to selectively use AI as a complement—rather than a replacement—for human judgment. Mixed-methods evaluation revealed significant improvements in students’ understanding of structured dimensions of user stories, such as value articulation and testability, alongside the emergence of conditional trust in AI, proactive prompt refinement, and heightened awareness of quality standards. This work represents the first application of TPACK theory to AI-enhanced requirements engineering education and proposes a reusable integration paradigm that aligns instructional goals, disciplinary content, and AI capabilities.

Abstract

The rapid adoption of generative Artificial Intelligence (AI) in software engineering (SE) practice creates a need for pedagogically grounded approaches to AI integration in SE education, especially in conceptually intensive subjects such as requirements engineering (RE). This study examines a TPACK-guided integration of a multi-agent AI tool into a master-level RE assignment on requirements quality analysis. Using a mixed-methods design (N=100; 72 submissions analysed), we examine how structured assignment design shaped students' AI use, affected their understanding of user story quality criteria, and influenced their perceptions of AI's benefits and limitations. Results show that students used the AI tool selectively, mainly as support for analysis and evaluation rather than automation. Alignment improvements were most evident for structurally concrete requirements quality dimensions, such as value articulation and testability, while negotiability showed mixed effects. Students reported conditional trust, active refinement, and increased awareness of quality criteria, alongside moderate usability challenges. The findings show that TPACK-guided scaffolding can align AI affordances with pedagogical goals and RE content, offering design guidance for responsible AI integration in RE education.

Problem

• AI integration
• requirements engineering education
• requirements quality
• software engineering education
• generative AI

Innovation

• TPACK
• generative AI
• requirements engineering education
• multi-agent AI tool
• scaffolded integration