The current research introduces a multi-agent artificial intelligence framework designed to transform traditional Root Cause Analysis (RCA) methodologies in manufacturing quality assurance contexts. The framework implements a structured collaborative system of role-specific AI agents which addresses inherent limitations of conventional approaches such as cognitive biases, knowledge fragmentation, and documentation inconsistencies. These specialized agents represent the perspectives of department representative like production, quality assurance or management with each drawing insights from domain-specific data files. This architecture centers on an Orchestrator Agent that coordinates the analysis and facilitates structured communication between agents and checks the results for inconsistencies. A reporting agent synthesizes the findings into comprehensive report using the categories of the Ishikawa diagram. This approach helps ensure traceable, iterative, and cross-domain analysis aligned with Industry 5.0 principles which emphasize human-AI collaboration. The framework's functionality is demonstrated through a case study examining the case of a burst hydraulic hose. Results indicate the multi-agent system has the potential to help produce more comprehensive cause mapping. They can improve analytical efficiency, traceability, and decision confidence. This research contributes by presenting a scalable, transparent methodology that effectively bridges data-driven analysis with collaborative human expertise. It has the ability to increase the efficiency and depth of typical root cause analyses while still being human-centric.