Retrieval After RAG: Hybrid Search, Agents, and Database Design — Simon Eskildsen of Turbopuffer
Source
youtube.com
Author
Latent Space
Date
Why it matters
Shows how retrieval is changing as agents replace simple RAGRetrieval-augmented generation — fetching relevant documents first and pasting them into the model's context so it answers from your data instead of memory.Full definition → pipelines, covering hybrid searchCombining keyword and semantic search in one ranked result, so exact terms and paraphrases both find what they should.Full definition → and database design choices that affect cost and quality of AI agentAn AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.Full definition → memory and search.
Terms in this piece · Glossary
RAG — Retrieval-augmented generation — fetching relevant documents first and pasting them into the model's context so it answers from your data instead of memory.
hybrid search — Combining keyword and semantic search in one ranked result, so exact terms and paraphrases both find what they should.
AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
videoScaling Past Informal AI - Carina Hong, Axiom Math
videoDreamer: the Agent OS for Everyone — David Singleton
videoAgent Inference at the "Speed of Light" — How NVIDIA moves like a $4.3 Trillion Startup
video⚡️Claude Sonnet 4.5 and Anthropic's roadmap for Agents and Developers — Mike Krieger, Anthropic
