
In the era of automation, society has invested significant effort in automating repetitive processes across various sectors to reduce the manufacturing time of many products. However, we have not given similar attention to automating software development, as it involves complex decision-making, contextual understanding, and requires human expertise and coordination. Historically, most organizations followed the waterfall methodology for the Software Development Life Cycle (SDLC), and in the early 21st century, they rapidly adopted agile methodologies with the expectation of delivering more robust and scalable products within a shorter timeframe. However, human involvement has remained central in all these methodologies until the emergence of Agentic AI. Agentic AI has the potential to transform software development in ways that have not been previously explored. In this paper, we propose an agent-driven SDLC framework that adopts an AI-first approach to software development, where human involvement is limited to governance and decision-making. The framework introduces a Central Orchestrator Agent that coordinates with specialized agents responsible for backlog planning, solution architecture, code generation, automated testing, code review, CI/CD, deployment orchestration, and production monitoring with self-healing capabilities. This AI-first approach can significantly reduce human effort and software release time, maintain high code quality through automated validation, and enable rapid incident response through autonomous hotfix generation and rollback mechanisms.
Large Language Models, LLM Guardrails, CI/CD Automation, Autonomous Software Engineering, Multi-Agent Orchestration, Software Development Lifecycle, AI Agents, Self-Healing Systems
Large Language Models, LLM Guardrails, CI/CD Automation, Autonomous Software Engineering, Multi-Agent Orchestration, Software Development Lifecycle, AI Agents, Self-Healing Systems
| selected citations These citations are derived from selected sources. This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically). | 0 | |
| popularity This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network. | Average | |
| influence This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically). | Average | |
| impulse This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network. | Average |
