Agile Software Development has revolutionized the process of developing software with the focus on flexibility, collaboration and constant enhancement. The recent progress in Generative AI technologies, e.g., Large Language Models (LLMs), GitHub Copilot, and OpenAI Codex, prompt software development teams to consider AI-driven options that do not conflict with Agile practices. This review studies existing literature, including AI-based code generation, automated testing, requirements engineering, and Agile project management, and the possibility of using generative AI in Agile software engineering. The paper addresses automated processes in Agile, such as AI-based backlog refinement, AI-based sprint planning, AI-based defect-predictive, and AI-based continuous integration (CI). It also discusses the effect of AI-powered workflows on the collaboration of members of the Agile team and Agile efficiency. The paper indicates that despite the fact that AI applications have enhanced productivity, there are still considerable issues that have been noted, such as AI bias, vulnerability to AI-induced software vulnerabilities, and human interaction. Generative AI has significant potential to impact Agile software development, and these issues should address both social and technical concerns when deploying a generative AI system. Finally, the paper suggests the research directions for the future of implementing AI into software engineering without compromising the fundamental principles of Agile Software Development.
No takes yet. Share an insight, caveat, or question.
Al-Tarawneh et al. (2026) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: