RAG Agents in Prod: 10 Lessons We Learned — Douwe Kiela, creator of RAG

AI Engineer. Douwe Kiela led the original RAG paper at FAIR and now ships RAG into regulated enterprises. The talk is mostly about what stops working at scale — chunking strategies that don't survive 100k documents, "accuracy is table stakes, inaccuracy is the real problem," and why attribution and observability matter more than the embedding model. Good calibration before re-reading the article's eval and monitoring sections.

Watch next

Continue through the same learning path with the next curated companion videos.

39 minutes

Introducing RAG 2.0: Agentic RAG + Knowledge Graphs (FREE Template)

Compare agentic retrieval and graph retrieval in a concrete implementation.

AdvancedAI for Business

13 minutes

RAG vs Fine-Tuning vs Prompt Engineering: Optimizing AI Models

Choose between prompt engineering, RAG, fine-tuning or a combination based on the actual failure mode.

AdvancedAI for Business

157 minutes

Fine Tuning LLM Models – Generative AI Course

You will be able to run quantisation, LoRA and QLoRA fine-tunes end to end on hardware most developers already have.

AdvancedPrivate / Local AI