LangChain

🌉 San Francisco LangChain Meetup: Join us next Wednesday for a fireside chat on deep agents. In this meetup, Sydney Runkle, Python OSS Engineer at LangChain, and Jake Broekhuizen, Deployed Engineer at LangChain, will talk all things deep agents. Deep agents are a powerful way to build LLM-based agents and applications, with built-in task planning, contextual file systems, subagent spawning, and long-term memory. RSVP here: https://luma.com/8r33l2o4

Tools in the LangSmith Playground 🛝 : Define tools once, use them everywhere. - Save & reuse tool definitions alongside your prompts, across playground sessions - Share a tool library across your workspace - Manage tool definitions programmatically with the SDK Learn more: https://buff.ly/PHFMHCY

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 ➡️ https://lnkd.in/gK4Xpgb7

LangSmith for Startups Spotlight: TierZero AI Engineering teams are shipping code faster than ever, but production operations remain heavily manual and concentrated in the hands of a few experienced engineers. The result: slower incident resolution, constant interruptions, and growing operational toil as systems scale. TierZero is the AI platform that helps engineering teams run production systems reliably at scale. Their agents automate incident response, surface reliability risks, and give engineers instant answers to production questions. High-scale teams like Discord, Drata, Framer, and WeightWatchers trust TierZero to accelerate incident resolution and reclaim engineering capacity. At Drata, TierZero reduced issue time-to-resolution by 42% and saved 7,000+ engineering hours annually. According to the TierZero engineering team, LangSmith plays a central role in how they ship reliable agents: - “LangSmith is the single most important tool in our agent development lifecycle - we use it to debug, evaluate, and continuously improve agent quality across our product lines.” - “Beyond tracing and evals, a few things have stood out...custom dashboards once caught a runaway process that would have 10x’d our model provider bills before we were even alerted.” - “LangSmith’s SDK is easy and flexible to build on top of - we recently used it to ship our TierZero <> LangSmith integration, which has cut our own investigation time on agent issues by over 50%.” - “Distributed tracing took 10 minutes to set up and gives great visibility into our MCP services.” Learn more 👉 https://www.tierzero.ai/ Reach out to the team for a free 30-day trial 👉 https://lnkd.in/eeki2Eka

⏳ Last chance to submit a talk for Interrupt (May 13-14, SF) Call for papers closes Friday 2/27. Share what you've learned building and scaling agents in production. Submit your talk 👉 https://lnkd.in/gnWxgv-K

🌉 San Francisco LangChain Meetup: Join us next Wednesday for a fireside chat on deep agents. 🚀 In this deep dive, Sydney Runkle, Python OSS Engineer at LangChain, will share insights from the front lines of open-source development. 🛠️ The evening will be moderated by Jake Broekhuizen, Deployed Engineer at LangChain. 🎙️ Deep agents are a powerful way to build LLM-based agents and applications, with built-in task planning, contextual file systems, subagent spawning, and long-term memory. 🧠🤖 👉 RSVP here: https://luma.com/8r33l2o4

LangChain has been named to The Agentic List 2026 — recognizing the top trending agentic AI companies most admired by industry executives. Selected by enterprise leaders and supported by in‑depth research, we’re honored to be recognized by the people actually building successful businesses with agentic AI. 35% of the Fortune 500 are actively using LangChain products, and half of the Fortune 10 use LangSmith for observing, evaluating, and deploying production agents. We're excited to continue powering large enterprises like Workday, ServiceNow, Cisco, Cloudflare, and more. See the full The Agentic List 2026 → https://lnkd.in/geBXQ8aK cc AI Agent Conference