From Vector Databases to Knowledge Engines: The Next Layer of AI

**Ash Ashutosh** (0:00)
About eight, nine months ago, we started seeing a massive shift to who our users are. It turns out it wasn't a human being anymore, it wasn't a different persona, it was an agent. Eighty-five percent of the agents work. These are just retrieving knowledge. Only 15 percent is the models. The models aren't a problem. The problem is the underlying system that you're trying to get information from, brought it down from 40,000 to about 2,000.
It's under 500 milliseconds from a minute to two minutes.
Most importantly, the accuracy dramatically goes up from, I think, best case, we were 68, we were well over 90 percent accuracy, and that is just version one. We finally understood why these things were taking so long, and they were fundamentally running on a system that was designed for human beings.

**SPEAKER_2** (0:53)
What happens when software is no longer built for humans, but for agents? For years, systems like databases and search were designed around human interaction. A person asks a question, evaluates the response, and decides what to do next. But with the rise of agents, that model starts to break down.
Agents don't have context. They brute force their way through systems, issuing dozens of queries, consuming tokens, and often failing to complete tasks. This creates a new bottleneck, not in the models themselves, but in how data is retrieved, structured and understood.
In this episode, Peter Levine speaks with Ash Ashutosh, CEO of Pinecone, about the shift from vector databases to knowledge engines, and what it takes to build systems that actually work for agents.

**Peter Levine** (1:44)
Hey Ash, welcome.

**Ash Ashutosh** (1:45)
Hey Peter, been a while.

**Peter Levine** (1:47)
Yeah, it has been a while. Good to see you. So we're here to talk about, at least I'm here to talk about Pinecone's new, the launch.

**Ash Ashutosh** (1:58)
Yeah.

**Peter Levine** (1:58)
And I know we, I'm a board member with you, and we've been on this journey together now for a bit, and you all have been working on this new product called Nexus. And I'd love to hear more about it, and sort of the genesis of it, and then what's happening at the launch, and kind of where to from here.

**Ash Ashutosh** (2:24)
Yeah. I think we've been talking about it at our board level for several months now. About eight, nine months ago, we started seeing a massive shift of who our users are. It turns out it wasn't a human being anymore, it wasn't a different persona, it was an agent.
And that shift fundamentally changed how we thought about what's the best way to serve this new user in the world of retrieval. If you think about what we had done for five years, six years since we first pioneered the vector database market, the idea was you provided an interface to a human being who did a query, got a response back, and it was the human being who provided the context about whether the response was accurate, whether they had to re-ask the question, and they would finally take the action based on whether they verified the information or not. Unfortunately, agents don't have the luxury. They, the human gives them a task, and agents go there and start trying to perform the task.

**Peter Levine** (3:40)
Right.

**Ash Ashutosh** (3:40)
And they spend a ton of time going through this brute force loop of querying.

**Peter Levine** (3:46)
Right.

**Ash Ashutosh** (3:47)
Getting some chunks of data back.

**Peter Levine** (3:49)
And when you say, just so I have the context, when you say agents spend a lot of this brute force, what are they actually, let's say right now, before Nexus has launched, what are they actually doing in the background? Like querying what and what's the nature of that whole data flow? Yeah.

**Ash Ashutosh** (4:09)
So you give it a task to an agent to say, is this product under warranty?

**Peter Levine** (4:19)
Right now, let's say without Nexus.

**Ash Ashutosh** (4:22)
Customer service.

**Peter Levine** (4:23)
Okay.

**Ash Ashutosh** (4:23)
The agent comes in and says, can you let me know if this product is under warranty?

**Peter Levine** (4:29)
Right.

**Ash Ashutosh** (4:29)
Agent does something called a query expansion, breaks up the queries, and then says, okay, let me go figure out what this product is. And it goes to five or six different systems. Sometimes it might be sales order system, product definition system, things about warranty information. And then it sends out different queries, just like a human being would, because that's the interface we provided, this product to database.
So here's an agent trying to solve a problem without having any context with a system built for human being. And so it goes out, issues a query, and it asks six or seven different queries before it first starts to get an idea about the first, we think of it as the first line of code, effectively. Sometimes it could be 40 different queries.