Architecture and Engineering in the AI Era: Definition and Validation of a new AI-Driven Design Work-flow

In recent years, Artificial Intelligence (AI) has become increasingly prevalent across various sectors, including the Architecture, Engineering, and Construction (AEC) industry. AI-powered software tools are being developed to automate tasks and optimize design processes. This paper explores the integration of AI tools including ChatGPT, Midjourney, Stable Diffusion, and ComfyUI with parametric design soft-ware such as Grasshopper and Revit, assessing their potential to transform traditional design workflows. The use of AI chatbots like ChatGPT enables efficient data analysis, allowing for rapid evaluation of urban parameters, cli-mate data, and local energy requirements. In addition, AI-driven image generation tools, such as Midjourney and Stable Diffusion, in combination with ComfyUI, facilitate the rapid exploration of multiple design possibilities. These tools enable iterative and real-time generation of architectural visualizations, providing an almost infinite pool of design options. Additionally, they significantly enhance the efficiency of design control and modification by reducing the time traditionally required for rendering tasks. Furthermore, the study highlights the critical role of parametric design environments as a foundational framework for AI-assisted design, supporting iterative exploration and optimization. This effectiveness and limitations of the proposed methodology are evaluated through its application to a case study.