StarZero All shows Try the podcast clipper →

Harrison Chase

Co-founder & CEO, LangChain · 2 appearances on the record.

computed by AI from the episodes · how this works → · full disclaimer →

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.

14statements → 3claims → 3claims resolved → 100%fully supported → 3.5/5average certainty → 1.93/5average debate potential → 20said about them ↓

3 supported 0 partly supported 0 contradicted how the 3 claims stand · each chip opens the sources

3 assertions · 5 opinions · 3 insights · 3 disclosures · every statement was checked. The predictions and assertions are the 3 claims: statements the public record can support or contradict. 3 are resolved. Everything else (opinions, insights, what ifs, disclosures) can never be settled by the record, so it carries no assessment.

The record, in short

What the tape says about how Harrison argues and how the claims held up. Everything they said, and everything said about them, is in the tabs below.

Their most notable supported claim

Assertion Supported
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 Sep 27, 2024 ▶ 17:05 Language Agents: From Reasoning to Acting — with Shunyu Yao of OpenAI, Harrison Chase of LangGraph

Expressed certainty vs assessment result

none yet certainty 1
none yet certainty 2
100% certainty 3
100% certainty 4
none yet certainty 5

weighted support: a fully supported claim counts one, a partly supported claim counts half. Each filled bar is clickable and opens exactly those claims; "none yet" means nothing said at that certainty level has resolved yet

How they sound: not measured why? →

We measure speaking style by listening to the audio itself, and a fair number needs at least 2,000 words from one person on tape we have measured. There is too little of Harrison Chase on measured tape to publish a rate. This says nothing about how they speak.

Everything Harrison Chase said on Latent Space that made the record, most notable first. Filter by type, assessment or year in the ledger →

Opinion
Chase: Nobody in the AI industry knows how to properly solve memory.
“I don't think anyone knows how to deal with memory, and so I think all these different approaches are...”
Harrison Chase Apr 6, 2024 ▶ 54:05 Personal AI Meetup - Bee, BasedHardware, LangChain LangFriend, Deepgram EmilyAI
Opinion
Harrison Chase says coding AI agents are not yet a proven success
“There's a bunch of people doing coding stuff. We've already talked about that. I think that's a little bit, I wouldn't say that's a success yet, but there's a lot of excitement and stuff there.”
Harrison Chase Sep 27, 2024 ▶ 1:20:50 Language Agents: From Reasoning to Acting — with Shunyu Yao of OpenAI, Harrison Chase of LangGraph
Insight
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.”
Harrison Chase Sep 27, 2024 ▶ 9:49 Language Agents: From Reasoning to Acting — with Shunyu Yao of OpenAI, Harrison Chase of LangGraph
Assertion Supported
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 Sep 27, 2024 ▶ 17:05 Language Agents: From Reasoning to Acting — with Shunyu Yao of OpenAI, Harrison Chase of LangGraph
Opinion
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 Sep 27, 2024 ▶ 25:23 Language Agents: From Reasoning to Acting — with Shunyu Yao of OpenAI, Harrison Chase of LangGraph
Assertion Supported
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.”
Harrison Chase Sep 27, 2024 ▶ 46:42 Language Agents: From Reasoning to Acting — with Shunyu Yao of OpenAI, Harrison Chase of LangGraph
Opinion
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 Sep 27, 2024 ▶ 1:03:16 Language Agents: From Reasoning to Acting — with Shunyu Yao of OpenAI, Harrison Chase of LangGraph
Insight
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 Sep 27, 2024 ▶ 1:08:52 Language Agents: From Reasoning to Acting — with Shunyu Yao of OpenAI, Harrison Chase of LangGraph
Disclosure
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.”
Harrison Chase Sep 27, 2024 ▶ 1:12:12 Language Agents: From Reasoning to Acting — with Shunyu Yao of OpenAI, Harrison Chase of LangGraph
Opinion
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.”
Harrison Chase Sep 27, 2024 ▶ 1:20:38 Language Agents: From Reasoning to Acting — with Shunyu Yao of OpenAI, Harrison Chase of LangGraph
Insight
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.”
Harrison Chase Apr 6, 2024 ▶ 54:48 Personal AI Meetup - Bee, BasedHardware, LangChain LangFriend, Deepgram EmilyAI
Assertion Supported
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…”
Harrison Chase Sep 27, 2024 ▶ 12:10 Language Agents: From Reasoning to Acting — with Shunyu Yao of OpenAI, Harrison Chase of LangGraph
Disclosure
Chase: LangGraph is adding cross-thread state persistence for agent memory
“Right now they're all persistent for a single thread. [4392] We're going to add the ability to persist that between threads. [4395] So then if you basically want to scope a memory to a user ID or to an assistant or to an organization, then you can do that.”
Harrison Chase Sep 27, 2024 ▶ 1:13:10 Language Agents: From Reasoning to Acting — with Shunyu Yao of OpenAI, Harrison Chase of LangGraph
Disclosure
Chase: LangChain's experimental AI journaling app struggles to consolidate redundant memories.
“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…”
Harrison Chase Apr 6, 2024 ▶ 57:19 Personal AI Meetup - Bee, BasedHardware, LangChain LangFriend, Deepgram EmilyAI

The other half of the tape: Harrison Chase's own voice is left out of every number here. Other people bring the name up 20 times in 12 episodes on Latent Space. every mention, with the transcript →

Who brings them up most Shawn Wang 7Alessio Fanelli 4Aymeric (Emmerich) 3Youssef Rizk 1Lance Martin 1Andrew White 1

Every mention by year

tap a year for its mentions
00531062023202420252026episodesmentions
0362023202420252026episodes it came up in
001.332.562023202420252026episodesmentions per episode
2026 1 mention in 1 episode
2025 9 mentions in 6 episodes 2 per episode
2024 1 mention in 1 episode
2023 9 mentions in 4 episodes 2 per episode

Appearances (2)

EpisodeDateSpeaking time
Language Agents: From Reasoning to Acting — with Shunyu Yao of OpenAI, Harrison Chase of L Sep 27, 2024 18m
Personal AI Meetup - Bee, BasedHardware, LangChain LangFriend, Deepgram EmilyAI Apr 6, 2024 10m
Made with StarZero

Turn any episode into a week of clips.

This entire site, over 200 episodes transcribed, diarized, checked and made playable, runs on the StarZero media pipeline. Drop in your own episode and the podcast clipper finds the moments worth sharing, cuts them, captions them, and reframes them for every feed.

Try the podcast clipper Learn more