The Software Development Life Cycle (SDLC) encompasses distinct phases, each demanding specialized expertise to ensure high-quality deliverables. Traditionally, the success of these phases has relied heavily on the availability of Subject Matter Experts (SMEs) with phase-specific skills. Recent advancements in Generative AI, particularly Large Language Models (LLMs) such as OpenAI’s GPT and Anthropic’s Claude, have introduced transformative possibilities in software engineering. These models, trained on extensive text corpora, show significant potential to augment various stages of the SDLC. However, the effectiveness of LLMs hinges on the quality of the prompts provided, necessitating systematic and context-aware interactions. This paper presents a novel multi-agent system leveraging systematic prompting strategies grounded in meta-model concepts to address phase-specific challenges in the SDLC. The proposed approach was validated using GPT-o1 in the development of a small yet complex business application. We detail the methodology, highlight the benefits realized, and discuss the challenges encountered during its implementation. Our findings underscore the potential of Generative AI to lower skill barriers, enhance collaboration, and accelerate software development processes, marking a significant step forward in the integration of AI into software engineering practices.