LangChain

we're doing a meetup! "a summer evening on continual learning" partnering with our friends at prime intellect and baseten come join! https://luma.com/cwn8mze6

Excited to be at #InterruptNYC on September 24th to share how our team builds agentic AI on LangGraph for high-stakes decisions!

This week, don’t miss our Learning Loop event featuring LangChain, Prime Intellect, and Baseten in San Francisco! We’ll dive into continual learning, what it means to own your own intelligence, and how teams are building systems that learn and improve over time. After the talks, we’ll head to the patio where you can meet the LangSmith Engine team, enjoy food and drinks, slot car racing, an AI photo booth, and more. Spots are limited, so be sure to register! https://luma.com/cwn8mze6

Clay uses LangSmith to reconcile 99.5% of its AI spend. Head of AI Jeff Barg sat down with us to share why cost observability finally clicked once LangSmith was in place. Watch the full conversation at https://lnkd.in/eJB-j6Fb

JPMorganChase is speaking at Interrupt NYC, The Agent Conference by LangChain. See the full agenda and get your tickets: https://lnkd.in/gJcqZ_T4

Yesterday, we brought the LangSmith Roadshow to Silicon Valley! 🏎️ It was a packed day featuring technical sessions, hands-on learning, and conversations about building, deploying, and operating agents in production. Attendees also got to hear from Mani Najmabadi, Director of Machine Learning Science at Expedia Group, as well as Harrison Chase and the LangChain team. A special thanks to everyone who joined us! Interested in attending a future LangSmith Roadshow? More stops are coming soon, so check out where we're going next and RSVP: https://lnkd.in/ggm_eEWN

At our recent NYC meetup with Clay, Head of AI Jeff Barg, ML Engineer Vyshnavi Khota and Software Engineer Soroush Khadem shared how they scaled agent evals to 300 million runs a month. Watch the full talk to learn: ✅ How Claygent and Sculptor got to production scale ✅ Clay's four quadrant framework for agentic evals ✅ Why closing the loop between production and offline evals is the hardest part ✅ How a data lake and long context are changing what agents can do with data Check it out on YouTube: https://lnkd.in/grStyZ4m

We're adding support for the new MCP spec in LangChain open source! Our new API is built on top of FastMCP, so you can take advantage of their excellent devx for building MCP servers and clients. An early version is available in langchain==1.4.0a2; let us know what you think! Release notes: https://lnkd.in/gXNCXXCD

On September 17th, join the LangChain Academy team for a live workshop on Deep Agents. We’ll show you how to build your own Deep Agent and see how planning, memory, and subagents let an agent run complex, multi-step tasks. If you’re looking to get up to speed on Deep Agents, you won’t want to miss this. RSVP below: https://lnkd.in/gDSU7i4i

When Podium's agents didn't behave as expected, LangSmith showed the real story: the agent was behaving rationally based on the context it had. Principal Software Engineer Walker Ward on why tracing the full chain of thought in LangSmith changed how they debug agents. Watch the full conversation at https://lnkd.in/guqzDCnv