Date
Publisher
arXiv
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.
Study at a glance
- Question: How do undergraduate software engineering students autonomously use generative AI during multi-month capstone projects, and what do clients expect?
- Setting and data: Leibniz University Hannover, 2025/26 cohort, 150 undergraduate computer science students across 18 teams and 11 client stakeholders across 15 projects.
- Method: Mixed methods survey combining descriptive statistics, Spearman rank correlations, and qualitative pattern coding of free-text responses.
Why it matters
The educational consequences of unguided generative AI use in complex, multi-month capstone projects remain unclear. The absence of baseline evidence limits the development of informed instructional strategies, governance mechanisms, and targeted support for student projects.
Key findings
- Most surveyed students (139 of 150) used generative AI, most frequently for code generation or debugging (97) and learning new technologies (96).
- Generative AI usage frequency correlated positively with perceived benefits (rs = .517) and weakly negatively with self-assessed programming skills (rs = -.169).
- Clients broadly supported student AI use, but seven of eleven expressed concern that students might lack sufficient understanding to explain decisions in meetings.
Summary drafted with AI from the full paper and may contain errors. See the full paper for details.
What is the application?
Who is the user?
Who age?
Why use AI?
Study design
