Harrison Chase

14 statements across 1 episodes · 6 bullish · 0 bearish · 1 people on the record · first statement Mar 12, 2026 by Harrison Chase · across every show →

On the record as a speaker too: Harrison Chase's record, appearances and statements → this page counts the times other people say the name.

Everything said about Harrison Chase, oldest first

Mar 12, 2026
Disclosure
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 Mar 12, 2026 ▶ 25:01 Everything Gets Rebuilt: The New AI Agent Stack | Harrison Chase, LangChain
Mar 12, 2026 bullish
Prediction Not checkable as stated
Chase: Basically all AI agents will write code
“You know, if agents never write any code, then okay, maybe they're not useful, but I think it's trending where Basically all agents will write code, so that's a very interesting piece, I think.”
Harrison Chase Mar 12, 2026 ▶ 28:46 Everything Gets Rebuilt: The New AI Agent Stack | Harrison Chase, LangChain
Mar 12, 2026 positive
Prediction Not checkable as stated
Harrison Chase: AI agents will evolve into synchronous interfaces orchestrating asynchronous sub-agents
“Like, I do think we'll get to a place where we have this kind of like synchronous conversational agent kicking off kind of like longer running asynchronous agents in the background.”
Harrison Chase Mar 12, 2026 ▶ 26:58 Everything Gets Rebuilt: The New AI Agent Stack | Harrison Chase, LangChain
Mar 12, 2026
Assertion Not checkable as stated
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 Mar 12, 2026 ▶ 31:24 Everything Gets Rebuilt: The New AI Agent Stack | Harrison Chase, LangChain
Mar 12, 2026 neutral
Insight
Harrison Chase: Modern AI agent harnesses don't strictly enforce execution plans
“And so now what most things do is they just have that plan in the text file, and the main agent can, like, use that to help guide its actions, but there's nothing that says I'm explicitly doing this step, or I'm explicitly doing another step.”
Harrison Chase Mar 12, 2026 ▶ 13:00 Everything Gets Rebuilt: The New AI Agent Stack | Harrison Chase, LangChain
Mar 12, 2026
Insight
Chase: AI agent context compaction must retain recent messages for flow
“You want to keep around like the last N messages, let's say the last like 10 or so messages, because if you compact everything, it actually like throws it off completely.”
Harrison Chase Mar 12, 2026 ▶ 21:03 Everything Gets Rebuilt: The New AI Agent Stack | Harrison Chase, LangChain
Mar 12, 2026 positive
Insight
Chase: Virtual file systems let LLMs manage their own context windows
“And the way that I think about a file system is it basically lets the LLM manage its own context window. So it can decide what to read from files.”
Harrison Chase Mar 12, 2026 ▶ 15:44 Everything Gets Rebuilt: The New AI Agent Stack | Harrison Chase, LangChain
Mar 12, 2026 positive
Insight
Chase: AI builder differentiation lies in domain knowledge, not harness infrastructure
“I think a lot of the differentiation is in like the instructions and the tools and the skills and that basically, yeah, knowledge of how to do a process that you encode into natural language and give the agent and then the tools and the skills that you let it …”
Harrison Chase Mar 12, 2026 ▶ 45:53 Everything Gets Rebuilt: The New AI Agent Stack | Harrison Chase, LangChain
Mar 12, 2026
Insight
Harrison Chase: Inter-agent communication is the hardest part of working with AI agents
“Communication is the hardest part of life, by the way, it's the hardest part of startups, hardest part of relationships, hardest part of working with agents is getting them to communicate.”
Harrison Chase Mar 12, 2026 ▶ 14:23 Everything Gets Rebuilt: The New AI Agent Stack | Harrison Chase, LangChain
Mar 12, 2026
Assertion Not checkable as stated
Developers are buying Mac Minis as primitive physical sandboxes for AI agents
“That's why people are buying Mac minis as a, you know primitive way of sandboxing them and keeping them in a contained environment.”
Harrison Chase Mar 12, 2026 ▶ 30:49 Everything Gets Rebuilt: The New AI Agent Stack | Harrison Chase, LangChain
Mar 12, 2026 positive
Insight
Chase: Agent harnesses matter more for performance than underlying models
“I, the, so I don't know what happens, but I do know the harness is really, really important. Like, I think this is the thing that matters.”
Harrison Chase Mar 12, 2026 ▶ 8:10 Everything Gets Rebuilt: The New AI Agent Stack | Harrison Chase, LangChain
Mar 12, 2026 positive
Insight
Chase: High reliability AI agents require structured, graph-like scaffolding workflows
“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…”
Harrison Chase Mar 12, 2026 ▶ 2:56 Everything Gets Rebuilt: The New AI Agent Stack | Harrison Chase, LangChain
Mar 12, 2026
Assertion Not checkable as stated
Harrison Chase: Most current agent harnesses feature built-in sub-agents and skills
“Most harnesses today have sub agents built in. They have skills built in.”
Harrison Chase Mar 12, 2026 ▶ 9:16 Everything Gets Rebuilt: The New AI Agent Stack | Harrison Chase, LangChain
Mar 12, 2026
Insight
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.”
Harrison Chase Mar 12, 2026 ▶ 43:25 Everything Gets Rebuilt: The New AI Agent Stack | Harrison Chase, LangChain
Made with StarZero

Turn any episode into a week of clips.

This entire site, over 400 conversations 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.