Agentic Orchestration for Pedagogy: Knowledge-aligned Multi-agent Learning Assistant

A team at the Faculty of Engineering has developed a multi-agent AI chatbot designed to enhance teaching and learning across various courses, including Electrical and Electronic Engineering, Philosophy, and Biomedical Sciences. This chatbot features specialized agents, such as an ‘administrative agent’ and a ‘student analyzer agent,’ which efficiently direct student inquiries to appropriate resources. Utilizing a knowledge-graph approach, the chatbot maintains a customized knowledge base, ensuring responses reflect instructors’ insights. Its modular design allows for ongoing adjustments and enhancements, facilitating continuous improvement and reporting of results.