A Generative-AI Chatbot Enhanced by a Flexible Knowledge Base and Student Engagement to Enrich Teaching and Learning

Facing limited resources, teachers often find it challenging to promptly address students’ queries. To tackle this, a GenAI contextual chatbot was developed and deployed on the Discord platform and tested in various courses, aiming to enhance students’ learning, improve inter- and intra-group communication, and reduce teachers’ workloads. The contextual chatbot uses retrieval-augmented generation (RAG), a technique that enhances the accuracy and reliability of GenAI models by incorporating facts from external resources. Course instructors curate and manage a knowledge base using materials from previous semesters to train the chatbot in addressing students’ issues related to both hardware and software. Surveys show positive student feedback, highlighting the resource’s helpfulness.