LangChain

Interrupt is back. May 13-14 in San Francisco. Tickets on sale now. → 1,000+ builders → Keynotes from @hwchase17 + @AndrewYNg on what's next for agents → Real production lessons from @clay, @Rippling, @Workday + more → Hands-on workshops → First look at new products Seats are limited. Get tickets: interrupt.langchain.com/?utm_medium=so…

LangChain Community Spotlight: Agent Memory Course 🧠 DeepLearning.AI and Oracle's free course teaches building memory-aware agents with LangChain. Learn persistent cross-session memory, semantic tool retrieval, and autonomous updates using Oracle AI Database. 📚 Course: deeplearning.ai/short-courses/…

LangChain Community Spotlight: sklearn-diagnose 🔍 An intelligent diagnostic layer for scikit-learn detecting model failures through LLM analysis. Three LangChain agents detect seven failure modes with actionable fixes. Includes multi-provider LLM support and chatbot. 🔗 github.com/leockl/sklearn…

And that's a wrap on GTC week! - We announced our enterprise agentic AI Platform built with NVIDIA. LangGraph and Deep Agents plug directly into NVIDIA's tooling. You can build agents with the latest Nemotron 3 models deployed with NIM microservices, apply NeMo Guardrails for securing agentic applications, and leverage NeMo Agent Toolkit to optimize your agents and monitor with LangSmith Observability: blog.langchain.com/nvidia-enterpr… - Jensen announced in his keynote: LangChain frameworks have crossed 1B downloads - Harrison participated in a panel on Open Models with Jensen, Michael Truell, Aravind Srinivas, Mira Murati, and more

LangChain Community Spotlight: EPI - Flight Recorder for AI Agents 🎙️ EPI captures AI agent execution into signed .epi files that work offline. LangGraph checkpoints + LangChain callbacks preserve context when logs expire. 6,500+ downloads | MIT | Check it out 👇 github.com/mohdibrahimaim…

💫 New LangChain Academy Course: Building Reliable Agents 💫 Shipping agents to production is hard. Traditional software is deterministic – when something breaks, you check the logs and fix the code. But agents rely on non-deterministic models. Add multi-step reasoning, tool use, and real user traffic, and building reliable agents becomes far more complex than traditional system design. The goal of this course is to teach you how to take an agent from first run to production-ready system through iterative cycles of improvement. You’ll learn how to do this with LangSmith, our agent engineering platform for observing, evaluating, and deploying agents. Enroll for free ➡️ academy.langchain.com/courses/buildi…

LangSmith 🤝 @AbridgeHQ 🍩 donut drop!

How to Build Deep Agents for Enterprise Search with NVIDIA AI-Q and LangChain Deep Agents: We recently introduced an enterprise agent platform built with NVIDIA AI to support scalable, production-ready agent development. In this blog, you'll learn: - How to deploy the NVIDIA AI‑Q blueprint with LangChain Deep Agents for enterprise search use cases - How to configure shallow and deep research agents using Nemotron and frontier LLMs - How to monitor agent traces and performance with LangSmith and NVIDIA tools - How to connect internal enterprise data sources through NeMo Agent Toolkit tools Read more: developer.nvidia.com/blog/how-to-bu…

New Conceptual Guide: You don’t know what your agent will do until it’s in production 👀 With traditional software, you ship with reasonable confidence. Test coverage handles most paths. Monitoring catches errors, latency, and query issues. When something breaks, you read the stack trace. Agents are different. Natural language input is unbounded. LLMs are sensitive to subtle prompt variations. Multi-step reasoning chains are hard to anticipate in dev. Production monitoring for agents needs a different playbook. In our latest conceptual guide, we cover why agent observability is a different problem, what to actually monitor, and what we've learned from teams deploying agents at scale. Read the guide ➡️ blog.langchain.com/you-dont-know-…

I cannot explain how good agent fleets are going to be. This seems like an industry changing product. nothing Ive used has even come close. It feels like both large CRMs really tried to do this initially but it failed. Langchain nailed it. Ive only played with it for a few hours but I cant stop. Feels like if you want a personal hobby agent you go with openClaw, if you want an agent to help you at work its claude, but if you want a fleet of agents for your entire workforce? well there is only one place ive seen that vision accomplished and its now langchain. congrats guys. @LangChain @hwchase17

In LangSmith Prompt Hub 💬 Define clear access to your production prompts: • Assign Owners for each prompt • Owners-only mode restricts who can promote prompts to production • All other users keep committing without friction Iterate fast. Promote carefully! 🔒️

AI agents introduce a new production challenge: you simply don’t know what your agent will do until it’s in production. They interpret open-ended language, behave differently based on subtle shifts in phrasing, and take multi-step actions that are hard to predict in development alone. Join Harrison Chase, Co-founder and CEO at LangChain, for a technical deep dive into why production monitoring for AI agents requires a new approach to observability. RSVP: luma.com/xyzkhl42

LangSmith for Startups Spotlight: @ListenLabs Listen is an autonomous research agent that conducts thousands of customer interviews simultaneously. Teams bring a business question, and Listen runs the entire research process: designing studies, recruiting participants, moderating conversations with intelligent follow-ups, and delivering structured insights overnight. Listen is trusted by Google, Microsoft, Perplexity, Robinhood, Replit and hundreds of other enterprises to power their customer research. Listen uses LangSmith as core infrastructure for production tracing and observability. Their team relies on it to monitor the LLM calls that power their interviewing, analysis, and report generation agents. Join the team if you want to build the future of customer understanding! 👉 listenlabs.ai/careers

💫 New LangChain Academy Course: Building Reliable Agents 💫 Shipping agents to production is hard. Traditional software is deterministic – when something breaks, you check the logs and fix the code. But agents rely on non-deterministic models. Add multi-step reasoning, tool use, and real user traffic, and building reliable agents becomes far more complex than traditional system design. The goal of this course is to teach you how to take an agent from first run to production-ready system through iterative cycles of improvement. You’ll learn how to do this with LangSmith, our agent engineering platform for observing, evaluating, and deploying agents. Enroll for free ➡️ academy.langchain.com/courses/buildi…

Build deep agents for enterprise search with the NVIDIA AI‑Q blueprint and LangChain 🔍 Our new technical tutorial walks you through: ✅ Connecting agents to your enterprise data sources ✅ Configuring the agents with Nemotron models ✅ Monitoring and debugging performance in LangSmith 📝 nvda.ws/47ezM5j

Introducing LangSmith Fleet. Agents for every team. → Build agents with natural language → Share and control who can edit, run, or clone each agent → Manage authentication with agent identity → Approve actions with human-in-the-loop → Track and audit actions with tracing in LangSmith Observability Try Fleet: smith.langchain.com/agents?skipOnb…

🎉 Agent Builder is now Fleet! With this rebrand, we're also releasing lots of exciting new features: - Dedicated Slack bots for your agents, so each agent can have its own Slack user - "Claws" and "Assistants" Agent Identity concepts, that allow for better sharing of your agents across your team - Many more smaller QOL improvements Try it out today: langchain.com/langsmith/fleet

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 includes: → Agent identity and credential management with “Claws” and “Assistants” → Sharing and permissions to control who can run, clone, and edit (just like Google Docs) → Custom Slack bots so each agent has its own identity in Slack Try Fleet: smith.langchain.com/agents?skipOnb… Read the announcement: blog.langchain.com/introducing-la…

New York Meetup 🗽 It Worked on My Laptop: Agents in Production Unlike traditional software, you don't know what your agent will do until it's in production. This means that production monitoring for agents requires different capabilities than traditional observability. Agents operate differently. Robert Xu, Deployed Engineer @LangChain, will walk us through why agent observability has distinct challenges, what you need to monitor, and what we've learned from teams deploying agents at scale. 🗓️ March 24 | 🕧 6 PM | 🏙️ NYC (Flatiron) RSVP 👉 luma.com/g55ktjw7

Our agents are out in the wild today - and they're bringing donuts 🍩 @sofia_montoyac @jakebroekhuizen

We take our pastry alignment very seriously. The pleasure was ours!