Harrison Chase
Co-founder & CEO, LangChain. On 3 shows, 4 appearances. The Shows tab opens the full record on each.
founderexecutiveengineer@hwchase17 ↗LinkedIn ↗langchain.com ↗
Harrison Chase created LangChain in October 2022 and leads the company in developing developer frameworks and tools for building LLM applications. Prior to founding LangChain, he served as Head of Machine Learning at Robust Intelligence and led machine learning engineering teams at Kensho Technologies.
3shows
4appearances
51statements
5resolved
5supported
0contradicted
100%fully supported
21said about them ↓ Everything Harrison Chase said on any show that made the record, most notable first. Each card names its show and opens the statement there.
LangChain sees a 50-50 split in how developers deploy agent sandboxes
“In practice, we see people doing about fifty-fifty between each of these.”
Harrison Chase: AI evals and prompt optimization are closely tied, unlike memory
“I guess evals and prompt optimization are pretty closely tied, but like evals and memory are actually not at all tied.”
Chase: LangChain does not maintain a one-year product roadmap
“I don't think we have a one year roadmap.”
Harrison Chase says production AI agents rely on three main defaults
“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.”
Chase: LangChain and other frameworks lack off-the-shelf Reflexion implementations
“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…”
Harrison Chase says ReAct is the most popular agent prompting framework
“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.”
Harrison Chase says TypeScript yields better LLM tool-calling performance than JSON
“I saw some paper that used TypeScript notation instead of JSON notation for tool calling and it got a lot better performance.”
Chase: Few-shot prompting works better than detailed instructions for agent trajectories
“I'm pretty bullish on it, to be honest, for a few reasons. Like, one, I think it can maybe help for more complex things, but then also, two, like, it's a form of prompting, and prompting is just Communicating with the model what you want it to do. And sometime…”
Harrison Chase says developers should guide agent planning explicitly in code
“Sometimes I say that like the LLMs aren't
[4137] Great at planning yet.
[4138] So we can help them plan by telling them how to plan and code.
[4140] Cause that's very explicit and that's a good way of communicating how they should plan and stuff like that.”
Harrison Chase admits LangChain's memory service lacked product-market fit
“The memory service we launched, I don't think really found product market fit.”
Chase: Customer support is a clear production success area for AI agents
“One big area where there's clearly been success is in customer support.
both companies doing that as a service, but also larger enterprises doing that and building that functionality inside.”
Chase: Long-term LLM memory systems must incorporate mechanisms for memory decay.
“Yeah, I think there absolutely needs to be some sort of memory decay, or some sort of, like, invalidating previous memories.”
Chase: AI agents fundamentally require cyclical graphs, not linear architectures
“So, you know, all these agents are basically running an LLM in a loop. You need cycles and so lane graph helps with that.”
Chase: Working AI agents require hardcoded domain structure, not LLM autonomy
“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…”
Chase: Few-shot prompting effectively builds procedural memory for AI agents
“So on the procedural side, I think the main thing that we see people doing and that we think is pretty effective is few-shot prompting and maybe fine-tuning for how to use for how to use tools, because that's basically what it comes down to. What's the right w…”
Chase: Passive background insight extraction will drive AI personalization memory
“I also think one thing that I'm bullish on is a more kind of, like passive background process that kind of looks at conversations and almost, like, extracts insights. And then you can use those insights in kind of, like, future conversations.”
Chase: LLM prompts will likely converge as models become more intelligent
“I do think
the prompts will probably start to converge in the sense that if you think the models are getting more and more intelligent than like, hopefully these small idiosyncratic sees don't matter as much.”
Chase: New AI startups should build applications leveraging long-term memory
“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.”
Chase: Few-shot example datasets are faster and cheaper than model fine-tuning
“Building up few shot example data sets and really using those. I think it's much faster and cheaper than fine tuning models. It's easier to do than trying to like. Programmatically change the prompt in some way.”
Chase: LangChain is debating building a separate harness for conversational agents
“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.”
LangChain's Deep Agents offloads large tool outputs into virtual files
“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, …”
Manus, Claude Code, and Deep Research share four core architectural primitives
“We saw Manus, we saw Cloud Code, we saw Deep Research, they all had these four things and we were like, okay, that's pretty common, let's put it into a Python package and make it easy for people to build their own versions of that.”
Chase: DeepAgents enables agent learning by editing procedural memory files
“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…”
Harrison Chase says OpenAI recommends adding a thought field to tool schemas
“I think open AI even recommended, like when you're doing tool calling, it's sometimes helpful to put like a thought field in the tool along with all the actual acquired arguments and then have that one first. So it fills out that first and then, and that's, th…”
The other half of the tape: Harrison Chase's own voice is left out of every number here. Other people bring the name up 21 times in 13 episodes across the shows. every mention, with the transcript →
Who brings them up most Shawn Wang 7Alessio Fanelli 4Aymeric (Emmerich) 3Youssef Rizk 1Lance Martin 1Elad Gil 1Andrew White 1
Every mention by year
tap a year for its mentions
Latent Space 20
No Priors 1
2026 1 mention in 1 episode
2025 9 mentions in 6 episodes 2 per episode
- smol agents are all you need
- 2024 Year in Review: The Big Scaling Debate, the Four Wars of AI, Top Themes and the Rise of Agents
- Context Engineering for Agents - Lance Martin, LangChain
- The AI Coding Factory
- DeepSeek V3, SGLang, and the state of Open Model Inference in 2025 (Quantization, MoEs, Pricing)
- Beating Google at Search with Neural PageRank and $5M of H200s — with Will Bryk of Exa.ai
- every mention in 2025, scene by scene →
2024 1 mention in 1 episode
2023 10 mentions in 5 episodes 2 per episode
- RAG is a hack - with Jerry Liu of LlamaIndex
- Generating your AI Media Empire - with Youssef Rizk of Wondercraft.ai
- Beating GPT-4 with Open Source Models - with Michael Royzen of Phind
- Powering your Copilot for Data - with Artem Keydunov from Cube.dev
- No Priors Ep. 26 | With Weights & Biases CEO Lukas Biewald
- every mention in 2023, scene by scene →
One line per show, most statements first. The link opens Harrison's full record on that show: the calibration, argument clarity, speaking style and every statement made there.
| Show | Role there | Eps | Statements | Record | |
|---|---|---|---|---|---|
 MADLEDGER | Co-founder & CEO, LangChain | 1 | 23 | 100% 2/2 | full record on the MAD Podcast → |
| LATENT SPACELEDGER | Co-founder & CEO, LangChain | 2 | 14 | 100% 3/3 | full record on Latent Space → |
| NO PRIORSLEDGER | Co-founder & CEO, LangChain | 1 | 14 | — | full record on No Priors → |