pretty good weather to be in nyc rn!

turbopuffer crossed $100M run-rate in March. 19mo after $1M. Profitable & <$1M raised. Cursor・Anthropic・Notion・Cognition・Harvey・Bridgewater・Ramp・Linear・Legora・Superhuman・Atlassian・Granola We’d be nowhere without them. We work like hell to exceed their expectations.

SID-1 is an agentic search model by @SID_AI → 1.9x recall over RAG rerank → 24x faster, 99% cheaper than GPT-5.1 trained using large-scale RL on turbopuffer at 1k QPS bursts over 10M document corpora across thousands of steps tpuf.link/sid-1

A conversation with @sirupsen on scaling Shopify, building turbopuffer, and the future of databases. 0:00 - Scaling Shopify through flash sales and outages 8:13 - How top infrastructure teams collaborated in the 2010s 10:35 - Engineering principles from Logrus and on-call 17:38 - The story behind Simon’s famous-ish blog, Napkin Math 23:05 - Why new database companies keep winning 32:21 - How Simon became a fan of databases 35:45 - AI coding, and where agents still fail 42:10 - Hiring P99 engineers in the AI era 48:45 - What’s next for databases

someone said @turbopuffer is the fastest infrastructure company buildout they've seen, and we're not kidding!

Starting to map the graph for a founding engineer at Perfloop. Looking for real systems depth - perf, infra, observability, AI infra, devtools, databases, runtimes - plus extreme agency, product/architecture judgment, and native agentic building. Europe / near-Europe overlap preferred.

THIS TEAM PUFF'S

we couldn’t afford the sphere so we got the next best thing costs less, hits harder

1/ When we launched Notion AI Q&A in Nov 2023, we knew we were embarking on an ambitious journey. What we didn’t anticipate was how quickly we’d need to scale—or how much we could optimize costs. Notion vector search over the past 2 years: 10x scale, then 1/10th cost. 🧵

we’ve reduced query prices by up to 94%, thanks to infrastructure improvements we've made under the hood puff harder, for much less

what if we dove into search infrastructure together under the fish?

there's so much alpha in co-designing the db and infra together

some amount of `fuck it` energy is necessary in life

turbopuffer is looking for a security engineer or an infra person with a special interest in security! If you know someone who could be a good fit, would appreciate you sharing the link below or DM me! 🤝 turbopuffer.com/jobs?ashby_j…

tpuf ANN v3, for when you need to index the entire web 100B vectors @ 50ms p50 / 200ms p99 latency blog: tpuf.link/ann-v3

december changelog tpuf.link/chlog

time moves different at turbopuffer! excited for the next year!

yesterday: short human queries, scalar CPUs today: long LLM queries, wide SIMD lanes for FTS v2, we use a vectorized MAXSCORE algorithm instead of WAND, because dumb & serial beat smart & random algorithms on modern CPUs tpuf.link/maxscore

10x smaller index and up to 20x faster queries on FTS. we're just getting started.

no more re-upserting for cross-region copies, it's a one-liner now!