Harrison Chase: Modern AI agent harnesses don't strictly enforce execution plans
Harrison Chase · Everything Gets Rebuilt: The New AI Agent Stack | Harrison Chase, LangChain · Mar 12, 2026 · at 13:00
Harrison Chase is the co-founder and CEO of LangChain. He is discussing how agent planning mechanisms have evolved from rigid orchestration loops into flexible context scratchpads.
0:00 / 0:10exact quote · 10.7s
▶ Watch the full episode on YouTube → 720p mp4 · rendered on demand · StarZero watermark
“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.”
quote is from the automated transcript, cleaned for reading: filler sounds and stutters are removed, nothing is rephrased. names can be misheard (the analysis reads context, assessments check outside sources). how →
More from Harrison Chase
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.”
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.”
Anthropic's Claude Code uses custom harness tools over model-level RL tools
“It doesn't actually use the tools that are RL into the model. So like anthropic models have some like file editing tools. They have a completely different set of tools in, in the actual harness.”
LangChain adds tools for AI agents to autonomously trigger context compaction
“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.”
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.”
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 …”