This paper focuses on the review of the literature about the effects of generative AI for SE based on a comparison of research papers on methodologies, applications, and effects on SE processes. It plans to analyze and discuss existing classifications used for the purposes of MMA-based applications, including their potential and challenges, and analyze the productivity rate according to citation scores and other parameters. Generative AI models such as GPT-3, BERT, and Transformers are also involved in the paper, and this paper focuses on automatic coding, testing, and documentation. Primary research reveals that there is high interest in using generative AI for code generation with tools like OpenAI’s Codex and DeepMind’s AlphaCode, but at the same time, it reveals that there are issues like, quality of code, dealing with ambiguous requirements and integration problems. In the review, the author also covers generative AI in context to software testing and in relation to generating documentation, increased efficiency, and the identified limitations. The study reveals new opportunities of generative AI in SE but reveals basic issues such as explicability or ethic concerns at the same time. It seeks to improve the comprehension and chart future advancements in generative AI for SE; thus, focusing on the advancement and application of the strategies and ideas in the SE process for the researchers and practitioners.