PostgreSQL, every mention
40 scenes · ← back to PostgreSQL
tap a year for its mentions
every year anyone Shawn Wang 9Reynold Xin 9Michelle Pokrass 7Simon Eskildsen 6Samuel Colvin 4Jo Kristian Bergum 4Steve Yegge 3Jason Liu 3Jake Cooper 3Ankur Goyal 3
Verbatim, from the transcripts: the passages where PostgreSQL comes up
The Agent Cloud: Databricks’ Bet on the Future of AI — Matei Zaharia and Reynold Xin
- ▶ 16:36 Shawn Wang I think one of those things that is, is really interesting to me is, well, first of all, I'll, I'll endeavor to do everything and not call it the modern AI staff, because I think we need a different name, but like, yes, like, you know, um,…
- ▶ 29:36 Reynold Xin There's what we call OLTP databases, which are transactional, and think of your Postgres, your MySQL, your Oracle databases, and the other side is what we call analytics, and sometimes might have the term OLAP. 5 times in the scene
- ▶ 36:06 Reynold Xin But in there, we're writing in Postgres pages. 2 times in the scene
- ▶ 53:10 Reynold Xin Instead of worrying about PostgreSQL and maybe Spark SQL, why not just one? 2 times in the scene
GitHub’s Agent Era: 14x Commits, 200M Developers, Copilot’s Next Act — Kyle Daigle
- ▶ 1:00:39 Shawn Wang The whole Postgres drama.
Devin’s 80% Moment: Background Agents, 7x PRs, & End of Hand-Held Coding — Walden Yan & Cole Murray
- ▶ 57:58 Walden Yan For example, you probably do want a local DB set out the local doc compose and, and Postgres in order
The Agent-Native Cloud: 3M Users, 100K Signups/Wk, Data Centers, & Death PRs — Jake Cooper, Railway
- ▶ 2:32 Jake Cooper You just go to the Canvas, or you talk with Claude, um, and you say, deploy Postgres instance, deploy my GitHub repository, run this code, et cetera, right?
- ▶ 31:55 Jake Cooper Deploy new Postgres instances.
- ▶ 50:30 Jake Cooper I've got access to a Postgres instance now, right?
⚡️ How to turn Documents into Knowledge: Graphs in Modern AI — Emil Eifrem, CEO Neo4J
- ▶ 39:47 Shawn Wang You can tell I'm like very Postgres-centric.
Notion’s Sarah Sachs & Simon Last on Custom Agents, Evals, and the Future of Work
- ▶ 51:40 Shawn Wang Notions underlying database is Postgres, right?
Marc Andreessen introspects on Death of the Browser, Pi + OpenClaw, and Why "This Time Is Different"
- ▶ 45:00 Marc Andreessen Um, and so you wanted to, you wanted to unleash the underlying latent power of whether it was an Oracle database or some other, you know, some other Postgres or whatever, whatever it was.
Anthropic’s Felix Rieseberg on AI Coworkers, Local-First Agents, and the Future of Knowledge Work
- ▶ 27:14 Felix Rieseberg If you want to know something, if you post here, maybe you can do post SQL.
Retrieval After RAG: Hybrid Search, Agents, and Database Design — Simon Eskildsen of Turbopuffer
- ▶ 10:06 Simon Eskildsen And I was just getting their Postgres up to snuff, like, which basically boils down to tuning auto vacuum. 2 times in the scene
- ▶ 16:38 Simon Eskildsen I think neon neon was, was first to, and they're trying to retrofit it onto Postgres.
- ▶ 27:44 Simon Eskildsen So I, I went to San Francisco and I went to their office and the way that I remember it is that Postgres was down. 2 times in the scene
- ▶ 55:44 Simon Eskildsen If you're trying to do not search on Turbo Puffer as the primary use case, you probably shouldn't, but we see some customers that are like, oh, um, like at some point, cursor moved like 20 terabytes of Postgres data into Turbo Puffer,…
⚡️Warp 2.0: the Agentic Development Environment - Zach Lloyd and Ben Holmes
- ▶ 20:14 Zach Lloyd If you go into a, um, a REPL, and here I'm inside a Postgres REPL, you have AI access even within this REPL to do natural language into REPL command translation. 2 times in the scene
Quadratic: The AI Spreadsheet
- ▶ 10:19 Shawn Wang It's, I mean, I think it's very underrated, the amount of data connectors you have, like it connects to Postgres. 3 times in the scene
DeepWiki: The GitHub Encyclopedia
- ▶ 24:31 unnamed speaker Like, like Redis and like, you know, Postgres and like whatever your local networking thing is, if you, if you use that kind of like, if you have like a microservices system, good luck.
Tiny Teams: $6m ARR, 5m users with 4 employees — Sid Bendre, Oleve (Quizard AI/Unstuck AI)
- ▶ 21:14 unnamed speaker So I see some details of the stack, which is Python, FastAPI, Flask, Mongo, and Postgres.
The Rise and Fall of the Vector DB category: Jo Kristian Bergum (ex-Chief Scientist, Vespa)
- ▶ 4:38 Jo Kristian Bergum So, and then you have things like PG vector in Postgres.
- ▶ 10:32 Jo Kristian Bergum And if you're already using some database like Postgres, right? 3 times in the scene
- ▶ 14:00 unnamed speaker Like, you know, like a Postgres or MongoDB as their transactional and in the end vector store.
The Creators of Model Context Protocol
- ▶ 51:16 unnamed speaker You know, Postgres servers and whatnot, and, and that's all cool and that's good.
The Agent Network — Dharmesh Shah, Agent.ai + CTO of HubSpot
- ▶ 18:49 Dharmesh Shah I think this is one of the challenges in terms of implementation of graph databases is that the most common approach that I've seen developers do, I've done it myself, is that, oh, I've got a Postgres database or a MySQL or whatever.
Fullstack-Bench: The Eval for Coding Agents — with Sujay Jayakar, Chief Scientist, Convex
- ▶ 0:43 Sujay Jayakar It's a database that's thought from first principles on what if we didn't have to use, you know, MySQL and Postgres and the same things we've been doing for 30 plus years.
Browserbase: Browser Infrastructure For Your AI Agents
- ▶ 18:22 unnamed speaker Serverless Postgres.
Agent Engineering with Pydantic + Graphs — with Samuel Colvin, CEO of Pydantic Logfire
- ▶ 7:19 Samuel Colvin It's probably 80%, and so, everyone needs that stuff, and there's so much yet to be figured out, so much, like, space to do things better in the ecosystem in a way that, like, to go and implement a database that's better than Postgres is…
- ▶ 43:56 Samuel Colvin We started building our database with ClickHouse, moved off ClickHouse onto Timescale, which is a Postgres extension to do analytical databases. 3 times in the scene
Production AI Engineering starts with Evals
- ▶ 5:18 Ankur Goyal He's built the world's best free tier and is building like hyper inexpensive Postgres. 2 times in the scene
- ▶ 1:47:01 Ankur Goyal My conclusion is that this is a very real problem for a very small number of companies, and that is why Datadog, Splunk, Honeycomb, et cetera, et cetera, built their own database technology, which is, in some ways, it's sad because all of…
Building AGI with OpenAI's Structured Outputs API
- ▶ 4:20 Michelle Pokrass It was a Postgres shop, and you had all of the followers in Postgres, and you needed to, like, iterate over the followers and, like, figure out, is this a good notification to send? 7 times in the scene
- ▶ 9:13 Alessio Fanelli What was the helping scaling when you're scaling non-GPU workloads versus like Postgres bouncers and things like that? 2 times in the scene
High Agency Pydantic over VC Backed Frameworks — with Jason Liu of Instructor
The State of AI in production — with David Hsu of Retool
- ▶ 23:05 unnamed speaker Um, he mentioned they just use PostgreSQL's vector.
The Four Wars of the AI Stack - Dec 2023 Recap
The "Normsky" architecture for AI coding agents — with Beyang Liu + Steve Yegge of SourceGraph
- ▶ 1:03:11 Steve Yegge We use Postgres. 3 times in the scene
RAG is a hack - with Jerry Liu of LlamaIndex
- ▶ 1:03:40 Shawn Wang So your current favorite is just put it into Postgres. 2 times in the scene