life update: i’ve joined langchain to work on all things ai! we’re shipping insanely fast, are ripping through the roof, and are hiring for all roles. reach out!

Congrats to on raising a $125M Series B! 🦜☀️ 3 years ago (a month before ChatGPT launched!), Harrison Chase released LangChain as a popular "get started" booster pack. It was the first LLM agent package to really take off. As the agent space matured and changed

🤯 I'll never forget the "holy shit" moment I had three years ago when I got a GPT-3 powered LangChain agent to search the web for Leo DiCaprio's current girlfriend and perform arithmetic on her age. I immediately knew LLMs would shake the foundations of software, and that

Thrilled to announce our Series B today which at a $1.25B valuation. Huge thank you to Tom Loverro and the team at IVP for leading this round, with participation from Alphabet’s CapitalG and Sapphire Ventures and continued support from Sequoia Capital, Benchmark and Amplify Partners

Super pumped for whats in store LangChain! Have been working with an incredible OSS team to ship to ship the 1.0 versions of our flagship packages. If you haven't tried them out already, let us know what you think!

super excited for these releases, huge shout out to the LangChain and LangGraph teams for the awesome work 👏👏👏

We're finally adding our first agent to LangSmith: Insights! It's inspired by on architecture from Anthropic's CLIO paper: anthropic.com/research/clio Anika Somaia Bagatur Askaryan and Maddy Adams put a ton of great work here taking theory into practice. Links in the replies 👇

LangSmith processes nearly 1 billion events and 10s of TB of data every day! In order to help users sift through all of the data they're sending us, we launched Insights Agent! This agent automatically processes your traces in the background and gives you insights into how users

Insights Agent is our first in-product agent - give it a try!! Was awesome working on this with the team Anika Somaia Bagatur Askaryan

Agent builder makes it so easy to build agents, maybe I'll finally make it to inbox zero with my new email assistant

When iterating on an LLM app (e.g. changing the model or prompt), compare different experiments side-by-side to quickly understand what changed. Our redesigned experiment comparison view lets you surface regressions, improvements, and other key differences between experiments.

Come hang out :)))

x.com/i/article/2016…

🎉📅 Interrupt 2026 — the AI Agent Conference by LangChain — is back May 13-14 in SF 1,000+ practitioners. Production agents. Real world lessons. Why you should come: → Hear from teams scaling agents in production → Get hands-on in workshops with the LangChain team → See new

We just shipped Baseline Experiments 🚀 You can now pin any experiment as your baseline in LangSmith. This allows you track performance deltas, anchor your results, and quickly identify improvements or regressions in an experiment list. Docs: docs.langchain.com/langsmith/anal…

What? LangChain is evolving! Meet our final form ➡️ langchain.com

Introducing LangSmith Fleet: an enterprise workspace for creating, using, and managing your fleet of agents. Fleet agents have their own memory, access to a collection of tools and skills, and can be exposed through the communication channels your team uses every day. Fleet

The hardest part of debugging an AI agent isn't knowing it failed--it's knowing why. We rebuilt the detail view in LangSmith Experiments from the ground up to answer that question faster. Next time you click and inspect any experiment results, you will find: * Less clutter *