This research is expected to deliver a validated AI-driven, multi-objective decision-support framework capable of optimizing energy and carbon performance during early-stage building design. By integrating Building Information Modeling (BIM), Building Energy Modeling (BEM), and Life Cycle Assessment (LCA) within a Design Science methodology, the framework will enable automated exploration of design alternatives while balancing competing objectives such as operational energy demand, embodied carbon, and overall life-cycle impacts. The expected outcomes include: (1) a computational workflow that improves interoperability between BIM environments and performance simulation tools; (2) an artificial intelligence–based optimization engine capable of generating and ranking design scenarios according to predefined sustainability criteria; and (3) a structured decision-support interface that translates complex simulation outputs into actionable insights for architects and engineers. Through case study applications, the research aims to demonstrate measurable improvements in early-stage environmental performance compared to conventional sequential design processes. The framework is expected to reduce decision uncertainty, shorten iteration cycles, and enhance transparency in trade-off analysis between energy efficiency and carbon mitigation strategies. Beyond the technical contribution, the research will provide methodological advancements by operationalizing Design Science Research in the context of sustainable building design. It will also produce practical implementation guidelines to facilitate adoption in professional practice and inform digital transformation strategies within the construction industry. Ultimately, the project seeks to contribute to the transition toward AI-enabled, low-carbon, and performance-based building design aligned with climate mitigation objectives and circular economy principles.