Building AI Research Agents with LlamaIndex

As data grows, finding and synthesizing information manually becomes a major bottleneck. Building autonomous AI agents that can search, analyze, and summarize documents for you is the modern solution to information overload. In this text-only course, you will learn how to build and orchestrate your own AI research assistant. You will progress from understanding core agentic concepts to assembling multi-tool systems that can query diverse data sources, reason through complex tasks, and deliver structured summaries. What you'll learn: - Understand the foundational concepts of AI agents, tool use, and reasoning loops. - Configure LlamaIndex to connect with various data sources and vector databases. - Build custom tools that allow your agent to search, retrieve, and process information. - Orchestrate multi-tool workflows to handle complex, multi-step research queries. - Apply prompt engineering techniques to guide agent reasoning and output structure. - Implement error handling and evaluation strategies to ensure agent reliability. You will begin by mastering essential terminology and the architecture of retrieval-augmented generation (RAG). Then, through clear written explanations and step-by-step code walkthroughs, you will assemble, configure, and refine a fully functional research agent. This course is designed for software developers, data science enthusiasts, and tech professionals who want to learn agentic AI. No prior experience with LlamaIndex or agent orchestration is required, though basic Python knowledge is helpful. Start reading today to build your own intelligent research assistant.