LangChain

“So people ended up building scaffolding around the models to make them do things in a more predictable and reliable way. And that's why we at link chain, we built lane graph, which was another framework really aimed at that kind of like. Graph like workflows a…”

“We talk a bunch about this internally because we're debating whether we should build like a different type of agent harness for these types of agents.”

“Is if you call a tool and it comes back with like 60,000 tokens, we don't show that all to the LLM because that's a ton of tokens. Rather, we actually put that in a file and then say, hey, here are the first like thousand tokens. If you want to read the rest, …”

“One interesting thing there, actually, that we haven't yet released as of this recording, but will probably be released by the time it comes out, is we actually give the agent a tool to trigger its own compaction.”

“So one of the things that we do in deep agents is we represent those all as files. And so the agent can update those as they go along so it can learn things. And so when we say agents kind of like can learn with deep agents, what that really means is it can mo…”

“In practice, we see people doing about fifty-fifty between each of these.”

“I don't think we have a one year roadmap.”

“Basically Langchain was too bad at the time, so we built our own agent architecture, and that, we did that very early, which I'm very proud of, and that was like the right direction to continue on.”

“Yeah, I think we're not the size of Revolut or Deal, right? And so it probably doesn't make sense for us to do that. And Langchain and a lot of their surrounding tools have gotten a lot better. And so I think we're in the job of, and our engineering team is in…”

“Around deploying agents and co-pilots in the enterprise is going to be a very important area. So there are at least two parts to it. One is companies which are doing orchestration of these tiers itself. In old school year, now old school companies like LangCha…”

“Simple, which is an agent orchestration platform that uses MCP and Langchain to coordinate multi-model responses across a stack that we built to predict what a salesperson is going to do next. That then uses function calling to perform automations.”

“And to be honest, a lot of the stuff that we built while building co-council was exactly like this. Every time you do this task, you're basically gonna take the same six or seven steps. And you don't need to have, frankly, like fucking Langchain or whatever. J…”

“I like the take that apply multi-agents to problems that are easily parallelizable, that are read-only, for example, context gathering for deep research, and do, like, the final quote-unquote write, in this case report writing, at the end. I think this is tric…”

“For many years running, Chrome has been the number one used project broadly, but also within communities like LinkChain and Llama Index.”

“Well, I have a, I have, I don't know if this is an unpopular opinion, but, like, people keep telling me, ah, Langchain isn't popular, but if you look at its stats, like, it has twenty million downloads per month. How can you have not popular framework when it …”

“Most of the AI crypto projects we had seen had been just like not really interesting. It was more like copy paste from existing AI companies, and then they would like slap a token on top. So it would be like character AI with a token, like Langchain, but with …”

“I suspect Pedantic AI will be the first agent framework that implements those semantic attributes properly, because again, we control Pedantic AI, and we can say this is important for observability, whereas most of the other agent frameworks are not maintained…”

“So if you look at, you know, like chain still growing. These are the last, last six months. Lama index still growing. What I've basically seen is like things that one, obviously these things have a commercial product. So there's like people buying this and sti…”

“We are a no-code platform letting you build your own AI agents easily. So you can think of, we are to Langchain as Airtable to MySQL. Like you can just pin up AI agents super easily by clicking around and no code required. You didn't have to be an engineer and…”

“And there's such a long tail of other ones, but in practice, like, when people go to production, they generally have their own tools, or maybe one of those three, maybe some other ones, but, like, very, very few other ones.”

“I don't think we have like an off the shelf kind of like implementation of reflection and kind of like the general sense. I think the concepts like absolutely we see used in different kind of like specific cognitive architectures, but I don't think we have one…”

“I would say like reacts probably like the most popular. I think there's aspects of reflection that Get used. Tree of thought, probably like the least so.”

“I saw some paper that used TypeScript notation instead of JSON notation for tool calling and it got a lot better performance.”

“The memory service we launched, I don't think really found product market fit.”

“I think the bigger challenge is like, okay, a hundred million dollars, probably pretty, pretty easy. It's just time and effort. And they have both like the manpower and the money to sort of solve those problems. I think it's just like, again, if you go the VC …”

“I don't think anyone knows how to deal with memory, and so I think all these different approaches are...”

“So one of the issues that we haven't really tackled is in this journaling app, if you notice in here, there's a bunch of ones that are really similar, right? And so, like, there's a clear kind of, like, consolidation or update or something procedure that, that…”

“I think when we see people building agents that work right now, it's often breaking it down into a bunch of smaller components and kind of like imparting their domain knowledge about how information should Flow through these components. Because I think the ele…”

“We see people experimenting with it. I think the only real place where they're doing it is when they've reached like really critical scale which I still don't think is that many applications to date.”

“Like there's, I think we see increasingly interest in open source, but the reasoning abilities are still just like lagging behind Cloud three or GPT four. And I think like for a lot of the applications that it kind of, it probably depends on the types of appli…”

“If I wasn't doing LinkedIn, if I was starting a company right now, I'd probably start something at the application layer, and it would probably be something that really takes advantage of, like, long-term memory.”

“To me, GPT and other models is like a base layer of capability, like cloud computing that a lot of companies, if not all companies will plug into to some degree. And there'll be another layer of technologies that help you get the most out of it. Langchain's a …”

“Building, like, RAG from scratch. I mean, I think everybody should do it, I think. Like, I would check out the guide if you guys haven't already, and I think it's in our docs, but instead of just using you know, either the kind of, like the retriever query eng…”

“You know, I like Langchain. Never used it. Never ever used it.”

“Obviously with investment in Langtrain and we have a few others at Benchmark Cerebrus, which is you know, an AI chip for training and inference. We backed a team that worked on and was the leads of PyTorch and has got a new company and some others.”

“At LangChain, obviously, like we have more capital than we need right now.”

“Blind train is a great application framework for you to just like get us out of building blocks for a lot of different components, for instance, from like LL modules to prompts to some basic like retrieval and vector database abstractions to like also agent fr…”

“And actually for prototyping, it's great to use that. Now get that into production at scale. And that's when you're going to start running into hiccups in terms of scalability cost wise, scalability performance wise on the ingest side, and then on the query ru…”