Building Agentic RAG with LlamaIndex

What the course covers

This short course is about giving a language model agents that decide how to query a document collection, instead of running one fixed retrieval step. You work with LlamaIndex to build a system that answers questions over documents and produces summaries.

Skills you practice

• Guiding agent reasoning so it chooses sensible retrieval steps
• Debugging agent behavior when answers go wrong
• Combining document Q and A with summarization in one workflow

Who it is for

Developers who already know how retrieval-augmented generation works and want to move from a static pipeline to an agent that navigates data on its own will find the most value here. The focus is hands-on, with time spent on tracking down where the agent's reasoning goes off course.