Things Harrison Chase Has Said on Podcasts

“The hardest part about memory is actually not the database at all. When we talk to a number of companies, the way that they do memory is they just store it in a single file. Very, very kind of simple. The hard part is taking all of the observations that happen … and distilling that into information that's valuable enough to go into this context layer.” — Harrison Chase, The Twenty Minute VC (20VC): Venture Capital | Startup Funding | The Pitch

Asked about the data layer for agents, the LangChain founder argues that an agent's memory system will look more like an agent wrapped around a database than like a database alone. He says models are still poor at the reflection needed to decide what's worth remembering.

The Twenty Minute VC (20VC): Venture Capital | Startup Funding | The Pitch · 2026-10-17 Permalink → Listen →

The Twenty Minute VC (20VC): Venture Capital | Startup Funding | The Pitch Around 18:52 into the episode

Harrison Chase

…happen, whether it's from the user interacting with like the, let's say, such traditional SaaS interacting with the software, or the user interacting with the agent and distilling that into information that's valuable enough to go into this context layer. That's the hard part in memory right now.

Harry Stebbings

Why is that so hard?

Harrison Chase

Because it's tricky to get LLMs to do what you want them to do. And this type of like meta-reflection, I think, is something that LLMs actually still struggle at a lot, like reflecting on kind of like prompts and improving prompts, reflecting on agent architecture, improving agent architecture. We should build a benchmark for this. Internally, we do have some benchmarks for this in terms of Engine, which is our agent that's running on things. But I think this type of meta-reflection is still really difficult for agents. I think it's also generally like a hard thing for humans to do as well. Like, I don't know if we actually understand, some people probably do, so I shouldn't say this, but I don't know if we understand like what goes on inside our brain. Like, I feel like our brains are still kind of like complex things that we don't fully understand. And so, if we're trying to now replicate this kind of like learning process in a system, I think there's a bunch of different pieces. And so, I think models aren't great at kind of like reflection. And I don't think we know what this system should look like. What should the inputs be?…

Harry Stebbings

Will the models be meaningfully better at reflection in 12 months?

Harrison Chase

Probably. I mean, it seems like they'll get better at everything. Do

Harry Stebbings

you think the speed of model improvement will continue in the same manner of acceleration that it has done? Or do you think we are approaching some form of asymptotic plateauing?

Speaker names from our own diarization · position estimated from where the line sits in the episode

“The main way our business changes as the models get better, we basically have to erase big parts of our product. … Cursor said this really well as well. I think this is one of their actual operating principles as a company: erase the product or delete the product. … These models get better, and things that you had to do six months ago, you no longer have to do.” — Harrison Chase, The Twenty Minute VC (20VC): Venture Capital | Startup Funding | The Pitch

Harry Stebbings asked how LangChain's business changes as the models improve in ways outsiders don't see. Chase says the right way to wrap a model changes every few months, so much of the framework has to be thrown away and rebuilt.

The Twenty Minute VC (20VC): Venture Capital | Startup Funding | The Pitch · 2026-10-17 Permalink → Listen →

The Twenty Minute VC (20VC): Venture Capital | Startup Funding | The Pitch Around 04:25 into the episode

Harrison Chase

…years ago to agents today, they've gotten a lot better. And the main thing that's happened is: one, the models have gotten better, and two, we've figured out how to build systems that basically harness these models better. And that second part, the harnessing of these models, is what we focus on.

Harry Stebbings

How does your business change in a way that people don't see as the models get better?

Harrison Chase

The main way our business changes as the model gets we basically have to erase big parts of our product. So, what I mean by that, and Cursor said this really well as well. I think this is one of their actual operating principles as a company: erase the product or delete the product, I think is what they called it. Where basically, like, these models get better, and things that you had to do six months ago, you no longer have to do. And so, this is very relevant in our open source. So, our open source is all about basically the harness and the framework for taking these models and helping them do things. And the right way to take these models and help them do things changes every month, three months, six months. Choose your time period, but it changes pretty rapidly.

Harry Stebbings

How do you build for such an uncertain future? Do you just have to get in bed with the labs to know the roadmap so you don't waste six months building something that then they erase?

Harrison Chase

There's no easy answer. On one hand, what are you going to do? Not build? Like, that's what I like to say to founders who ask this: like, what do I do? Like, stuff is changing. You know, the models are changing. If I build something now, it might not be relevant in six months. What's the…

Harry Stebbings

Why do we need neutral harnesses? We see, you know, Bunty, very brilliant agent builders from the models themselves. Why does your letter not just get eaten by them?

Speaker names from our own diarization · position estimated from where the line sits in the episode

Things Harrison Says on Podcasts

Where to Find Them

What They Said

Collections They Appear In