How Bridgewater turned 100M documents into an edge with its Vault knowledge base
AI Engineer · youtube · 2026-10-24
AI Engineer hosts Sam Green (team lead, Applied AI) and Aaron Linsky (head of product engineering) from Bridgewater Associates on building the Vault.
- What it is: 100M+ documents from 135 external sources plus internal memos and meetings, cleaned, permissioned, and tagged to the firm's internal ontology — extending Bridgewater's 50-year research rigor to unstructured data.
- Lesson 1: humans and agents need different things from search; the biggest wins come from one tool serving both.
- Lesson 2: the real prize is proactive agents that surface what deserves investors' attention (the investor workbench).
- Lesson 3: a hand-built benchmark lifted search precision@10 from 60% to over 90%.
Also covers open web vs Vault comparisons, fast filtering at scale, and getting analysts to change habits — a flagship case of enterprise AI adoption.
More from coding & agent
- Lee Rob's 45-minute masterclass explains how always-on AI agents work — Saboo_Shubham_ · 2026-10-24
- Prompt engineering is 'dead', long live prompt engineering: a cyclist-recipe prompt shows the craft persists — chrisalbon · 2026-10-24
- Few-shot prompting trick: turn examples into a list the system completes — mmitchell_ai · 2026-10-24
- Rewriting the world in Rust: nearly 1T tokens and 50k+ commits per month — doodlestein · 2026-10-24
- NeurIPS paper OAT: attribute agent failures by learning only from success flows — SharonYixuanLi · 2026-10-24
- Claude writes its own parallel-agent prompt and nails the brief, screenshot goes viral — hewarsaber · 2026-10-24