Can Your AI Analyst Keep a Secret? - Aaron Linsky, Bridgewater & Nikhil Benesch, turbopuffer
Source
youtube.com
Author
AI Engineer
Date
Why it matters
Post-filtering loses recall and pre-filtering is slow when every document has its own permissions. Native filtering over a clustered vector index keeps both, a pattern to use for any permissioned 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 → system.
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.
videoWhat Does an AI Engineer Do Now? - Aparna Dhinakaran, Arize AI
videoDo Not Let Models Invent Numbers - Vinoo Ganesh, Kepler
videoWhy Frontier Models Fail as Buy-Side Analysts - Janie Gu, Google DeepMind & Suyeol Yun, LinqAlpha
videoAI Writes the Code. So What's Left for Engineers? - Laurie Voss, Arize AI
videoHow Bridgewater Turned 100 Million Documents Into an Edge - Sam Green & Aaron Linsky, BridgewaterAI Engineer
videoTurning My Obsidian Vault Into a Local AI Engineer — Filip Makraduli, SuperlinkedAI Engineer
videoConnect AI to Billions of Legal Documents — Simon Eskildsen, turbopuffer & Jacob Lauritzen, LegoraAI Engineer