How Do Software Engineering Students Use Generative AI in Real-World Capstone Projects? An Empirical Baseline Study

2026-04-27

AI Summary

This study addresses the current lack of empirical research on how software engineering students autonomously use generative AI in authentic capstone projects, a gap that hinders effective pedagogical design and responsible integration. Employing a mixed-methods approach, we investigated AI usage among 178 undergraduate students across 15 client-sponsored projects, combining surveys, qualitative analysis, and stakeholder feedback to establish the first baseline of generative AI use in real-world educational settings. Our findings delineate typical use cases across requirements, design, and coding phases, revealing that students prioritize verification and independent understanding, while clients emphasize transparency and data security. Building on these insights, we propose student-driven guidelines for responsible AI use, introduce team governance roles, and offer curriculum recommendations to empirically inform the integration of generative AI into software engineering education.

Technology Category

• Humans and AI: User Experience and Usability
• Philosophy and Ethics of AI: Artificial General Intelligence
• Application Domains: Software Engineering

Application Category

• Social Networks and Social Media: Generative AI / large language models and their impact on social systems
• Economics, Online Markets and Human Computation: Trust and reliance of crowd workers and data experts on GenAI
• Search and Retrieval-Augmented AI: Search Tool Learning with LLM: Teaching LLMs to invoke search and make use of retrieved information

Abstract

Real-world Capstone Projects (RWCPs) are a key component of software engineering education, enabling students to develop software for external clients under authentic conditions. Their high ecological validity, combined with substantial variation in domains, technologies, and stakeholders, typically requires flexible and minimally prescriptive teaching approaches. The rapid integration of generative AI (GenAI) into professional software development adds new challenges: students are expected to use AI tools that are common in practice, yet unguided use may affect learning, collaboration, and consistency in ways that are not yet well understood. To establish an empirical baseline for responsible GenAI integration, we conducted a large-scale study of self-determined GenAI use in an undergraduate RWCP course. The module involved 178 students working in 18 teams across 15 client projects over four months, with GenAI use explicitly permitted. We collected mixed-method survey data from 150 students on attitudes, usage prevalence, workflows, use cases, and perceived benefits and risks, and surveyed client stakeholders regarding expectations and concerns. Our findings provide (1) a characterization of GenAI practices across the software engineering lifecycle, including a distinction between emerging workflows; (2) student-recommended use cases and responsible-use directives emphasizing verification and maintaining independent understanding; (3) client perspectives highlighting strong support for GenAI use but clear expectations regarding understanding, quality, and data protection; and (4) implications for future course iterations, including the need for explicit responsible-use guidelines, targeted AI literacy resources, and team-level governance roles. This study offers a status quo baseline for evidence-based pedagogical interventions in the era of GenAI.

Problem

• Generative AI
• Software Engineering Education
• Capstone Projects
• AI Integration
• Empirical Study

Innovation

• Generative AI
• Capstone Projects
• Software Engineering Education
• Responsible AI Use
• Empirical Study