Generative AI for Enterprise Software Engineering: Current Applications, Challenges, and Future Research Directions

Generative Artificial Intelligence (GenAI) and Large Language Models (LLMs) are revolutionizing <br> enterprise software engineering, meaning there is intelligent automation throughout the software <br> development lifecycle (SDLC). While standard software engineering tools are mainly used to automate <br> repetitive tasks, GenAI tools employ sophisticated deep learning architectures to create human-like code, <br> automate software testing, aid debugging, generate technical documentation, optimize DevOps processes, <br> and manage software projects effectively. These abilities have greatly fueled the organization's interest in <br> the software development assistance provided by AI tools as they look to boost developer productivity, lower <br> operational expenses, speed up software delivery, increase software quality, and keep up in a progressively <br> digital economy. As organizations embrace the development environment that leverages AI, Generative AI <br> becomes integral to intelligent decision making, collaborative software engineering, predictive <br> maintenance, and ongoing software evolution in the modern Enterprise ecosystem (Fan et al., 2023; Lo, <br> 2023; Fui-Hoon Nah et al., 2023). <br> This study explores the transformative impact of Generative AI and Large Language Models in enterprise <br> software engineering through a systematic review of past academic and industry research into the <br> applications, benefits, challenges, and future implications of Generative AI and Large Language Models. <br> Research methodology used is Systematic Literature Review (SLR) and Comparative Analysis to assess the <br> previously conducted studies on the application of AI in software development, intelligent automation, <br> DevOps adoption, software quality assurance, software project management and enterprise software <br> governance. The comparative approach helps identify new technological trends, implementation strategies, <br> gaps in research, and organizational best practices in a variety of software engineering fields. <br> The results show that using Generative AI significantly increases the speed of software development, <br> enhances code generation and debugging efficiency, improves software testing quality, increases <br> documentation quality, and boosts developer productivity. Large Language Models have shown impressive <br> potential for software engineering automation, software maintenance, and collaborative software <br> engineering. Moreover, AI-driven DevOps enhances the automation of deployments, system monitoring <br> and management, predictive maintenance, and security compliance, while also promoting human-AI <br> interactions in enterprise development processes. There are still challenging issues to overcome such as <br> code reliability, AI hallucination, cybersecurity threats, intellectual property concerns, governance <br> frameworks, explain ability, ethical implementation of AI, and AI workforce adaptation (Keskar &amp; Keshar, <br> <div> 2023; Kar et al., 2023; Solanke, 2023). </div> <div> In conclusion, Generative AI is poised to revolutionize enterprise software development, providing a host <br> of innovation and operational advantages while also highlighting the importance of responsible governance, <br> trustworthy AI usage, and ongoing human oversight for sustainable and secure software creation. </div>