aiagentrank.io
Abonnieren
DeepLearning.AIHands-on reviewed

Building Agentic RAG with LlamaIndex

Reviewed by AI Agent Rank editors · Last verified 2026-05-24

Our take

The follow-up to Building and Evaluating Advanced RAG. Where the earlier course covered retrieval-engineering fundamentals, this one introduces agentic RAG — the loop where the agent decides what to retrieve, evaluates the result, and re-queries if needed. Production-grade pattern that solves the 'hallucination on retrieved context' problem most basic RAG apps have. Free, taught by Jerry Liu, the LlamaIndex co-founder.

About the instructor

Jerry Liu
Co-founder, LlamaIndex

LlamaIndex co-founder teaching the agentic-RAG pattern — where the retriever and the LLM iteratively refine the query, not just fetch-and-stuff.

Pros

  • +Solves a real production-RAG failure mode (single-shot retrieval misses context)
  • +Free, by LlamaIndex co-founder
  • +Material follow-up to the basic-RAG course

Cons

  • −Strong pre-reqs: basic RAG + LlamaIndex familiarity assumed
  • −LlamaIndex-flavored — patterns transfer but examples are vendor-specific

Best for

  • · Engineers whose basic RAG works in dev but fails in prod
  • · Anyone building research agents (Perplexity-style)

Not ideal for

  • · First-time RAG builders — take Building and Evaluating Advanced RAG first
Ready to enroll?

Free on DeepLearning.AI · ~2 hours (4 lessons)

Open DeepLearning.AI course →

After this course

These are the agents and tools where the skills from this course actually pay back.

Perplexity Labs

Mehrstufiger Recherche-Agent, der aus einer einzigen Frage belegte Reports erzeugt.

Gemini Deep Research

Long-running researcher inside Gemini that plans, browses and writes briefs.

Alternatives we considered

Other courses on the same topic. The right pick depends on your level and constraints — see each card for the trade-offs.

Building Agentic RAG with LlamaIndex — review (2026) | AI Agent Rank · AI Agent Rank