Inteligência artificial generativa como catalisadora da gestão do conhecimento na engenharia de software

Abstract

Background: Generative Artificial Intelligence (GenAI) has emerged as a transformative technology with strong potential to support organizational processes across different domains. In Knowledge Management (KM), GenAI may facilitate the creation, organization, sharing, and reuse of knowledge. In Software Engineering, its adoption has been associated with potential productivity gains, although important technical, organizational, and ethical challenges remain. Objective: This study investigates how GenAI has been supporting KM processes in the context of Software Engineering, with the aim of understanding its reported applications, perceived benefits, challenges, and implications for practice. Method: The research was conducted in multiple stages. First, a Systematic Literature Review (SLR) was carried out to synthesize the existing evidence on the role of GenAI in Software Engineering, with emphasis on KM-related processes. Then, a survey was conducted with professionals working in Software Engineering in order to capture perceptions, practices, and challenges related to the use of GenAI in real-world settings. Finally, the findings were integrated through methodological triangulation. Results: The results indicate that GenAI has been applied to support different knowledge-intensive activities in Software Engineering, including knowledge creation and acquisition, software artifact generation, software development, documentation, testing, maintenance, and knowledge sharing. Participants reported benefits such as productivity improvement, knowledge accessibility, learning support, faster information processing, and enhanced knowledge reuse, while also highlighting challenges related to reliability and accuracy issues, privacy and security concerns, ethical risks and biases, lack of contextual understanding, and the need for human oversight. The integrated analysis suggests that GenAI can act as an important enabler of KM in SE, although its effective adoption depends on organizational context, human oversight, and appropriate use practices. Conclusions: This study contributes to a broader understanding of the role of GenAI as a catalyst for KM in Software Engineering. The findings provide both theoretical and practical insights into how GenAI can support knowledge creation, retention, sharing, and reuse in SE environments, while also clarifying the limitations and conditions that shape its adoption . onments, while also clarifying the limitations and conditions that shape its adoption