Lessons Learned from the Use of Generative AI in Engineering and Quality Assurance of a WEB System for Healthcare
Guilherme H. Travassos, Sabrina Rocha, Rodrigo Feitosa, Felipe Assis, Patricia Goncalves, Andre Gheventer, Larissa Galeno, Arthur Sasse, Julio Cesar Guimaraes, Carlos Brito, Joao Pedro Wieland
TL;DR
This study investigates using Generative AI to support software engineering in a real health-care web system for smoking cessation. Through an iterative, artifact-driven process spanning elicitation, specification, design, implementation, and quality assurance, the authors map how multiple AI tools can assist each activity while highlighting the indispensable role of human oversight and well-structured prompts. Key findings show that prompts and Markdown-based artifacts are critical for traceability and quality, yet full automation remains elusive, especially in regulatory contexts like healthcare. The work provides practical lessons on integrating AI into SE workflows, ethical considerations, and directions for incremental adoption and future research. The practical impact lies in guiding software teams on when and how to leverage AI to accelerate development while preserving quality and compliance.
Abstract
The advances and availability of technologies involving Generative Artificial Intelligence (AI) are evolving clearly and explicitly, driving immediate changes in various work activities. Software Engineering (SE) is no exception and stands to benefit from these new technologies, enhancing productivity and quality in its software development processes. However, although the use of Generative AI in SE practices is still in its early stages, considering the lack of conclusive results from ongoing research and the limited technological maturity, we have chosen to incorporate these technologies in the development of a web-based software system to be used in clinical trials by a thoracic diseases research group at our university. For this reason, we decided to share this experience report documenting our development team's learning journey in using Generative AI during the software development process. Project management, requirements specification, design, development, and quality assurance activities form the scope of observation. Although we do not yet have definitive technological evidence to evolve our development process significantly, the results obtained and the suggestions shared here represent valuable insights for software organizations seeking to innovate their development practices to achieve software quality with generative AI.