Leveraging AI to Enhance Human-Driven Software Development: A Comparative Study Across Diverse Applications
Keywords:
Generative AI, ChatGPT, Software Requirements, Software Development Life Cycle, AI-Powered ToolsSynopsis
This is a Chapter in:
Book:
Intelligent and Sustainable Solutions
https://www.okipublishing.com/book/index.php/okip/catalog/book/60
Print ISBN 978-1-6692-0012-3
Online ISBN 978-1-6692-0011-6
Series:
Chronicle of Computing
Chapter Abstract:
This study explores how Generative AI, including AI-Powered tools like ChatGPT, can enhance the Software Development Life Cycle (SDLC). In a software engineering course, students worked in teams on 12 use case studies spanning web development, mobile apps, and game development. These use case studies covered domains such as education, sports, healthcare, and entertainment. Teams adopted dual roles as stakeholders and developers. Each team first defined a use case study and outlined project requirements. Use case studies were then randomly assigned, and teams worked as developers, specifying requirements and architectural designs. Scrum-style meetings facilitated collaboration. The paper compared developer-created and AI-generated user stories, functional and non-functional requirements, and architectural designs, including UML diagrams. Results showed ChatGPT excelled in structured web and app development domains but struggled significantly in game development and faced considerable difficulty in generating UML diagrams across all applications. This research highlights the strengths and limitations of Generative AI in enhancing software development processes.
About this Paper
Cite this paper as:
Fellah A. (2025) Leveraging AI to Enhance Human-Driven Software Development: A Comparative Study Across Diverse Applications. In: Tiako P.F. (ed) Intelligent and Sustainable Solutions. Chronicle of Computing. OkIP. CAIF25#8. https://doi.org/10.55432/978-1-6692-0011-6_6
Presented at:
The 2025 OkIP International Conference on Artificial Intelligence Frontiers (CAIF) in Oklahoma City, Oklahoma, USA, and Online, on April 2, 2025
Contact:
Aziz Fellah
afellah@nwmissouri.edu
References
Ahmad, K., Bano, M., et al. (2021). What’s up with requirements engineering for artificial intelligence systems? Proceedings of the 2021 IEEE 29th International Requirements Engineering Conference (RE), 1–12. https://doi.org/10.1109/RE51729.2021.00011
Amershi, S., Begel, A., Bird, C., et al. (2019). Software engineering for machine learning: A case study. Proceedings of the 41st International Conference on Software Engineering (ICSE ’19), 291–300. https://doi.org/10.1109/ICSE.2019.00042
Barenkamp, M., Rebstadt, J., & Thomas, O. (2020). Applications of ai in classical software engineering. AI Perspectives, 2 (1), 1. https://doi.org/10.1186/s42467-020-00005-4
Bhandari, K., Kumar, K., & Sangal, A. (2023). Artificial intelligence in software engineering: Perspectives and challenges. 2023 Third International Conference on Secure Cyber Computing and Communication (ICSCCC), 133–137.
Briand, L. C., Bianculli, D., Nejati, S., et al. (2021). The case for context-driven software engineering for AI-based systems. IEEE Software, 38(6), 51–60. https://doi.org/10.1109/MS.2021.3106993 https : / / doi . org / 10 . 1109 /ICSCCC58608.2023.10176436 de Oliveira Santos, P., Figueiredo, A. C., et al. (2024). Impacts of the usage of generative artificial intelligence on software development process. Proceedings of the 20th Brazilian Symposium on Information Systems (SBSI ’24), 1–9. https://doi.org/10.1145/ 3658271.3658337
Habiba, U., Haug, M., et al. (2024). How mature is requirements engineering for ai-based systems? a systematic mapping study on practices, challenges, and future research directions. Requirements Engineering, 29, 567–600. https://doi.org/10.1007/s00766-024-00432-2
Heyn, H.-M., Knauss, E., et al. (2021). Requirement engineering challenges for AI-intense systems development. 2021 IEEE/ACM 1st Workshop on AI Engineering – Software Engineering for AI (WAIN), 89–96. https://doi.org/10.1109/WAIN52551.2021.00020
Horkoff, J., Hadar, I., et al. (2023). AI-assisted software engineering: Promises, pitfalls, and research opportunities. ACM Computing Surveys, 55(7), 1–38. https://doi.org/10.1145/3579777
Khlood, A., Mohamed, A., et al. (2023). Requirements engineering for artificial intelligence systems: A systematic mapping study. Information and Software Technology, 158, 107176. https://doi.org/10.1016/j.infsof.2023.107176
Lorenzoni, G., Alencar, P., Nascimento, N., & Cowan, D. (2021). Machine learning model development from a software engineering perspective: A systematic literature review. arXiv preprint, arXiv:2102.07574. https://arxiv.org/abs/2102.07574
Marar, H. (2024). Advancements in software engineering using AI. Computer Software and Media Applications, 6(3906). https://doi.org/10.24294/csma.v6i1.3906
Smith, J., Johnson, E., Davis, M., et al. (2024). Exploring the future of software engineering with ai. Journal of Software Engineering Research, 40 (5), 123–145. https://doi.org/10.1016/j.jsser.2024.01.001
Terragni, V., Roop, P., & Blincoe, K. (2024). The future of software engineering in an AI-driven world. Journal of Software Engineering. https://doi.org/10.48550/arXiv.2406.0773
Todorov, P. G. (2022). The application of artificial intelligence in software engineering. International Journal of Advanced Multidisciplinary Research Studies, 2(5), 835–842. https://doi.org/10.2139/ssrn.4943407
Yoshioka, N., Husen, J., et al. (2021). Landscape of requirements engineering for machine learning-based AI systems. Proceedings of the Asia-Pacific Software Engineering Conference Workshops (APSECW’21), 5–8. https://doi.org/10.1109/APSECW53869.2021.00011
