The automation of software development prompted extensive research for decades. Recent advancements in AI, particularly large language models (LLMs), are driving transformative changes in the field. While LLMs have demonstrated impressive performance in code generation, challenges remain in generating complex and domain-specific code. To fully realize their potential, it is crucial to extend their application throughout the entire software development lifecycle. This necessity has driven us to explore and evaluate the role of these models in supporting all stages of the software engineering process. In this article, we propose an LLM-based framework tailored for the development of multi-agent systems (MAS). By focusing on MAS and leveraging the MaSE methodology in conjunction with the JADE platform, our framework ensures the generation of accurate, traceable, and reliable software artefacts efficiently. The framework uses predefined prompts to guide the LLM through each step of the methodology, producing outputs that adhere to domain-specific requirements. Empirical evaluations on sample projects demonstrate that this approach not only accelerates the development process but also results in artefacts that are more comprehensive and modular compared to those produced by human developers, showcasing the transformative potential of LLMs in software engineering.