Using Generative AI in Software Design Education: An Experience Report

2025-06-26

AI Summary

Prior research predominantly examines generative AI (GenAI) in programming instruction, with limited empirical investigation into its role in software design education—particularly in non-coding activities such as conceptual modeling and requirements analysis. Method: This study systematically integrates ChatGPT into team-based design practice within an undergraduate software design course. Using students’ conversational logs and structured reflection reports, we conduct qualitative thematic analysis. Contribution/Results: We propose the first GenAI integration framework tailored for design education, empirically demonstrating its effectiveness in supporting concept modeling, requirement clarification, and iterative solution refinement. Results show significant improvement in students’ critical evaluation of AI-generated outputs and the emergence of a novel “human-AI co-design” paradigm. The study advances theoretical understanding of how GenAI can foster design thinking and collaborative learning, offering empirically grounded, transferable pedagogical insights for software design education.

Technology Category

• Humans and AI: Game Design — Procedural Content Generation & Storytelling
• Cognitive Modeling & Cognitive Systems: Computational Creativity
• Natural Language Processing: Code Generation / Program Synthesis from Natural Language

Application Category

• Economics, Online Markets and Human Computation: Economic aspects and information design of Web, GenAI, and cloud computing
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Social Networks and Social Media: Generative AI / large language models and their impact on social systems

Abstract

With the rapid adoption of Generative AI (GenAI) tools, software engineering educators have grappled with how best to incorporate them into the classroom. While some research discusses the use of GenAI in the context of learning to code, there is little research that explores the use of GenAI in the classroom for other areas of software development. This paper provides an experience report on introducing GenAI into an undergraduate software design class. Students were required to use GenAI (in the form of ChatGPT) to help complete a team-based assignment. The data collected consisted of the ChatGPT conversation logs and students' reflections on using ChatGPT for the assignment. Subsequently, qualitative analysis was undertaken on the data. Students identified numerous ways ChatGPT helped them in their design process while recognizing the need to critique the response before incorporating it into their design. At the same time, we identified several key lessons for educators in how to deploy GenAI in a software design class effectively. Based on our experience, we believe students can benefit from using GenAI in software design education as it helps them design and learn about the strengths and weaknesses of GenAI.

Problem

• Exploring GenAI integration in software design education beyond coding.
• Assessing student use of ChatGPT for team-based design assignments.
• Identifying educator strategies for effective GenAI deployment in classrooms.

Innovation

• Used ChatGPT for team-based software design assignments
• Analyzed ChatGPT logs and student reflections qualitatively
• Highlighted need to critique AI responses before use