Synced transcript
Follow the talk
Automated overview
What this talk covers
Jerry Liu, CEO of LlamaIndex, explains how to move beyond simple RAG to build production-grade knowledge assistants. He details three steps: advanced data processing with LlamaParse for accurate PDF parsing, single-agent flows with query planning and tool use, and multi-agent task solvers via the newly announced Llama Agents framework. Llama Agents treats each agent as a deployable microservice that communicates through a central API, enabling specialization, parallelism, and easier production deployment. Jerry also highlights that naive RAG is insufficient for complex queries, and that good data quality—like proper parsing of tables and charts—is essential to reduce hallucinations.
This overview is derived from the transcript and has not been independently fact-checked by AI Engineer.
Generated highlights
Key moments
RAG was basically just a hack.
LlamaIndex CEO Jerry Liu warns poor parsing causes hallucinations when processing PDFs with tables.
LlamaIndex's Agentic RAG uses LLMs to interact with data services as tools during query processing.
Specialist agents outperform general agents on focused tasks, says Jerry Liu.
Multi-agent architectures can cut costs by letting each agent use only 5–10 tools and a weaker model.
LlamaIndex launches Llama Agents, a preview feature that turns agents into microservices.
These moment labels are generated from the unreviewed transcript and may contain errors.
Community discussion
Add context, evidence, or a useful disagreement
Build on the talk with an example, caveat, connection, or elaboration. Draft here, add the moment you’re discussing, then choose the direct-post pilot or the YouTube handoff.
Make it useful: add one concrete point, then support it with context, evidence, an example, or a caveat. Your words stay exactly as written.