What Happens When Billions of AI Agents Hit Your Database? (Andy Pavlo)

Andy Pavlo (0:00)

What is a file system? It's a database, right? Everything is a database. Every month there's a story where someone lost their production database because the agent deleted something. It's the Wild West for people that don't know their history databases. It's just like taking a cheetah, giving it a bunch of cocaine and putting it in a Ferrari. The amount of speed that people are developing these things is insane.

Matt Turck (0:16)

That is Andy Pavlo. In the world of databases, Andy is about as close to a god as it gets. The Carnegie Mellon professor whose courses taught an entire generation of engineers about databases, and as it turns out, the AI models too. Andy recently made some waves by joining ClickHouse to found ClickHouse Labs. Now, not long ago, databases in AI meant vector search and RAG. But today, agents create databases, write to them, and sometimes even delete them. Welcome to Databases in the Age of Agents. I'm Matt Turck, and this is the MAD Podcast.

Andy, welcome.

Andy Pavlo (0:52)

Hey Matt, how are you doing, man?

Matt Turck (0:53)

Good. I'm excited to talk about all things AI, agents, databases, Larry Ellison. We have to, and then Wu-Tang Clan?

Andy Pavlo (1:01)

We definitely would do Wu-Tang Clan.

Do we have to talk about Larry Ellison? I mean, it's a little early to come out of the gate. Although he is hilarious, because he's like the super villain of the databases. He owns a Hawaiian island.

Matt Turck (1:11)

Well, that seems to be working out for him. All right, we can graduate to talking about Larry Ellison later in the conversation.

Andy Pavlo (1:17)

I will say my contract with ClickHouse does allow me to talk about Larry Ellison. I made sure that was in writing.

Matt Turck (1:22)

Awesome. I want to take it from the top. So two years ago, the topic of databases and AI came up. There was a whole era of vector databases and this whole idea that you need to do RAG in connection with chatbot searches. That was kind of two years ago. I think a lot of people's mental models kind of like stopped there in terms of like this intersection of databases and AI. Clearly, we are in the age of agents now.

How is that different? What does that change?

Andy Pavlo (1:54)

I mean, the vector databases, although you are right, that in terms of being in the zeitgeist of AI and databases, probably two years ago is when the RAG vector databases came into play, but the vector databases themselves, a lot of them were around since 2016 It's just now that the use for them became obvious because you can use them to enhance and improve agents doing things.

I think the vector database market is interesting because they were early in the space, but they were really pushing the idea that you want to do this approximate similarity search on vectors or embeddings, instead of doing an exact search that the database systems have traditionally done. This helps too when you're dealing with natural languages, that where the semantics, maybe what you're trying to look for or query against isn't, you can't precisely define, find me all the albums from artists in New York City, that talk about doing certain kind of activities. It's very hard to define exactly what that is, and the magic of approximate nearest neighbor search, or these vector embedding searches in a vector database, is that you can look up things based on the semantics of the thing you're looking for and it works out that way, because you're not trying to do exact keyword searches. So, when ChatDB blew up in 2024, 2023, and again, when everyone became aware that this is now a technology that exists, the vector databases were in the right position at the right time, because they could augment and improve these chatbots, but the moat, if you will, wasn't that big, because at the end of the day, it's just an index, and within a year, pretty much every single database vendor had their own vector index, and now it's become sort of standard table stakes. Every data system that we're using has their own vector index.

Now, it doesn't say that the vector databases can't do certain things better than what the traditional data system could do, it's just now that everyone has that basic functionality. So, I think that you still use vector searches to enhance and improve the chatbots or the agents now, it's just the, you don't need to have a specialized one database that can only do that.

Matt Turck (4:09)

And agents now create databases, use databases, can make changes to databases. So maybe a year ago when Databricks acquired Neon, there was a stat that I believe said that the number or the percentage of agents creating Neon databases went from 30% to 80%.