Using artificial intelligence in software development processes: achievements and challenges

Abstract

This study consolidates contemporary methodologies for applying artificial intelligence in software engineering. Using the PRISMA protocol, an analysis of 60 peer-reviewed publications was conducted. Findings indicate that the use of generative tools (such as GitHub Copilot), AI-based testing platforms (like Testim.io and Diffblue), and DevOps automation systems (e.g., Harness.io) can lead to a 20–40% reduction in development time, while also enhancing code quality and minimizing errors. A key academic contribution of the research is the introduction of a three-tier classification of integration barriers – technical, organizational, and legal – that hinder the seamless adoption of AI technologies within the Software Development Life Cycle (SDLC), as well as the lack of standardized methodologies. The recommendations provided in this work are particularly relevant to software engineers, IT project leaders, and academic researchers, as they address crucial concerns related to model interpretability, system instability, the absence of unified standards, and regulatory ambiguity. The practical relevance of the study lies in presenting actionable strategies for the responsible, scalable, and ethically grounded deployment of AI-driven tools in industrial, academic, and research settings.