Role of GenAI in Automated Code Generation within DevOps Practices: Explore how Generative AI

Abstract

Artificial Intelligence (AI) is a pivotal domain within computer science, profoundly influencing the software development lifecycle, particularly during the implementation phase. Here, developers grapple with the task of translating software requirements and designs into executable code. Automated Code Generation (ACG) leveraging AI emerges as a promising solution in this context. The automation of code generation processes is gaining traction as a means to tackle diverse software development challenges while boosting productivity. This paper presents a thorough review and discourse on both traditional and AI-driven techniques employed in ACG, highlighting their respective challenges and constraints. Through an examination of pertinent literature, we identify various AI methodologies and algorithms utilized in ACG, extracting evaluation metrics such as Accuracy, Efficiency, Scalability, Correctness, Generalization, among others. These metrics serve as the basis for a comparative analysis of AI-driven ACG methods, delving into their applications, strengths, weaknesses, performance metrics, and future prospects.