This course introduces participants to Agentic Retrieval-Augmented Generation (Agentic RAG) and the principles of AI safety, equipping them with the knowledge and practical skills to design reliable, context-aware, and responsible AI systems. Participants will explore how AI agents can retrieve information, reason over knowledge, use tools, and execute multi-step tasks while maintaining appropriate human oversight.
The course also examines key AI safety considerations, including hallucination, bias, privacy, security, data governance, transparency, evaluation, and responsible deployment. Through practical exercises and real-world use cases, participants will learn to build and assess Agentic RAG systems that are not only technically effective but also safe, trustworthy, and aligned with ethical and regulatory requirements.