Harrison Chase
4 Intel
Co-founder and CEO of LangChain, Harrison Chase studied statistics and computer science at Harvard University before leading ML engineering at Kensho Technologies (acquired by S&P Global) and Robust Intelligence. He co-founded LangChain in late 2022 and was named to Forbes 30 Under 30 for Enterprise Technology in 2024.
Is this you? Sign in with X to claim this profile.
Intel
An X post arguing that who controls your agent's memory is inseparable from the harness, and that open harnesses avoid vendor lock-in. A strategic argument to read, not a tool or library.
LangChain's Harrison Chase teaches memory architecture for agents: semantic, episodic and procedural stores, updated either in the hot path or by a background helper agent. The build is an email assistant that learns user preferences and evolves its own instructions.
LangChain's CEO discusses whether inference routing commoditizes, why better models force harness code to be deleted, the open agent memory layer, and what 1,000x more agent requests means for cost and engineering team size.
Harrison Chase of LangChain breaks agents into harness, model and context, and argues when teams should own each part, with evals as the way to keep control of their own intelligence. Includes Q&A.