Building AI Agents with LlamaIndex and RAG

As artificial intelligence evolves, static language models are no longer enough; modern applications require AI that can actively retrieve custom data and execute multi-step tasks. This course teaches you how to bridge the gap between large language models and your own data sources using LlamaIndex. You will start with the foundational concepts of AI agents and Retrieval-Augmented Generation (RAG), moving step-by-step through the process of building robust, data-backed agentic workflows. What you will learn: Understand the foundational terminology of AI agents, LLMs, and RAG architectures. Configure LlamaIndex to ingest, index, and query your custom data sources. Build basic RAG pipelines to improve the accuracy and relevance of AI responses. Design agentic workflows that can break down complex queries and route tasks effectively. Integrate modern vector databases to store and retrieve data efficiently. Apply prompt engineering basics to guide your agents toward reliable outputs. The course begins with essential terminology and fundamental concepts before guiding you through written exercises to construct your first data indices and agentic loops. You will progress from simple document queries to designing multi-step AI agents capable of reasoning over complex datasets. This course is designed for beginners, aspiring data engineers, and developers with no prior AI experience who want to understand the mechanics of agentic workflows. Start reading today to unlock the potential of your data and build your first intelligent AI agent.