Tools Harrison Chase has publicly discussed or demonstrated using. Curated by Magpie's editorial team from podcasts, posts, and public stacks.
About
Harrison Chase is co-founder and CEO of LangChain. The agent-stack is his job; he posts his own dev workflow on X and the LangChain blog and is one of the most-quoted public voices on how to build production AI systems.
Chase is co-founder and CEO of LangChain and the public voice for the agent framework. He shipped LangChain 1.0 in 2025 with revamped docs, general agent architectures and high-quality integrations, and continues to ship deep-research courses and DeepAgents Deploy as the no-code path to production agents. As CEO he's the structurally tightest endorsement surface for the framework.
We're working towards `langchain` 1.0! Langchain will be the easiest place to get started building LLM apps. This 1.0 release will include: revamped docs, general agent architectures and use cases, built on langgraph, high quality integrations.
LangGraph is the LangChain team's stateful agent framework, presented as 'a LangChain extension that makes it really easy to define agents as graphs'. Chase frames LangGraph as the best way to build agents because of three properties: controllability, memory, and novel UX paradigms. He partnered with DeepLearning.AI on a dedicated AI Agents in LangGraph course.
LangGraph is a LangChain extension that makes it really easy to define agents as graphs If you look at all the papers about agents, they describe and visualize agents as graphs - so why shouldn't we have an easy way to create them that way?
LangGraph is an extension of LangChain for building agent & multi-agent systems. I believe its the best way to build agents for a few reasons: Controllability, Memory, Novel UX paradigms.
LangSmith is LangChain's observability product. Chase uses it to debug agents in production and posts traces and screenshots on X and the LangChain blog. He frames LangSmith as the production-grade tooling layer that makes agent debugging tractable, and the blog docs treat it as a first-class part of the LangChain stack.
Chase builds against Claude as a primary model in agent workflows and has discussed Claude's tool-use behaviour on X. LangChain's deep integration with Claude (and especially Claude Code) is a recurring topic in his X posts about agent skills and DeepAgents. He treats Claude as a default frontier model the LangChain stack should run well on.
Frequent ChatGPT user. Chase has discussed prompt patterns for agent workflows in LangChain blog posts and treats ChatGPT alongside Claude as the canonical LLM defaults the LangChain stack must integrate cleanly with. His agent-builder framing is model-agnostic but pragmatically benchmarks against the OpenAI and Anthropic frontier models.
These tools have been mentioned by the people featured in podcasts, interviews, posts, and other public media. Source links and citations are included wherever possible. Magpie AI has no direct relationship with the people on these pages. Spot a missing tool or a wrong attribution? Suggest a correction →