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…

One of the core things we’re going to have to contend with in AI is that even the most advanced models in the word can’t have all the relevant knowledge needed to be useful, because everyone has different use-cases and ways they’ve designed their workflows. Perhaps most importantly, as you get into the enterprise, everyone has entirely different access levels to corporate knowledge and information. Continual learning at the model layer, even at a single enterprise level, is near impossible because every user knows and has access to something different than another user. This isn’t like coding where by and large most developers can access all the relevant stuff to their job. On a single banking team, bankers have entirely different sets of documents they’re ever allowed to see. Sanitizing this is hard and having the model keep secrets is impossible. This is why the context layer is going to always be the core part of the AI stack for applied use cases to turn general models turn into useful agents. Can’t fight the physics on this one.

Day 3 of becoming 100xdevs: - make a travel agent with mcp - learn about the state - learn about runtime context - making multiagents - tracking sub-agents from Langsmith

a year ago, it was hard enough to build useful agents that most companies didn't have cost issues. that's changed a lot just from the start of this year! use langsmith to track agent costs and alert when anything unexpected happens

Langsmith taking over San Francisco!!! @LangChain

Very excited to talk about file systems in agents at the @AICouncilConf this May! Grab tickets now before they sell out:

Introducing Cost Alerting in LangSmith 💸 More and more agents are making it to production, and costs are increasing dramatically. Use LangSmith to set configurable alerts on total cost, so you know right away when your agents are spending more than they should. Docs: docs.langchain.com/langsmith/aler… Sign up: smith.langchain.com

we're building out a community middleware page for @LangChain, and we need your help growing it. agent middleware is one of the most powerful building blocks we've shipped. what are you building with it? docs.langchain.com/oss/python/int…

🚀 Interrupt sold out last year, so don't wait: May 13-14 in San Francisco. interrupt.langchain.com Last year, hundreds of builders packed a room to share what's actually working in agent production. This year, we're going bigger. @hwchase17, @AndrewYNg, @cj_mongodb, are headlining. Alongside them: real-world sessions from teams shipping agents today, time with LangChain engineers, and a pioneering AI builder community. If you're working on agents or thinking about it, this is two days with the people furthest along.

the langchain community is so awesome claude code's source leaked last week and @IeloEmanuele immediately built claude's compaction engine as @LangChain middleware drop this into your agents/deepagents today! github.com/emanueleielo/c…

did a big series on using @langchain's middleware to customize your agent harness last week icymi, here's a quick blog explaining 5 different patterns for harness engineering! blog.langchain.com/how-middleware…

Had to hop on the wrong train to get this photo, but LANGSMITH IS IN NYC!

👾 Claude Code 🤝 LangSmith 🦜 We've shipped a new way to trace Claude Code runs to LangSmith! It's a plugin that traces subagents, tool calls, compaction runs, and more. You can run evals to test the impact of skills/MCPs, use LangSmith Insights to look for trends across your org, track token usage, and more! Docs: docs.langchain.com/langsmith/trac… Repo: github.com/langchain-ai/l…

Join @hwchase17 and Chirantan "CJ" Desai, CEO of @MongoDB for a fireside chat at Interrupt — May 13-14 in San Francisco. MongoDB is the company behind one of the most widely used databases for modern applications — used by thousands of teams to power everything from real-time analytics to AI-native workloads. At Interrupt, Harrison and CJ will chat about how teams are building agents at the world's largest enterprises, and what's next for the space. Get your tickets: interrupt.langchain.com

harness eng day 5: toolsets some tools need setup and teardown around the agent loop, like connecting to a tool server or spinning up a sandbox for example, @langchain's ShellToolMiddleware handles init and cleanup, and injects the shell tool into your agent's tool registry!

Great ad by @LangChain “token spend higher than your rent?”

we just added the ability to assign specific reviewers to an annotation queue. as building agents becomes more and more automated, human feedback being part of the loop will be as critical as ever.

harness eng day 4: production readiness deployed agents need to be resilient! model timeouts, rate limits, tool failures are inevitable @langchain's ModelRetryMiddleware handles retry logic with configurable retry count, backoff factor, and initial delay

The LangSmith Signal: Azure's share of OpenAI traffic grew nearly 4x in under 3 months. We're sharing how devs are building agents, by the numbers. While most orgs started by connecting directly to OpenAI, over the past 10 weeks we've watched Azure's share of that traffic grow from 8% to 29%. We've analyzed this trend via LangSmith Observability data across more than 6.7 billion agent runs. Our hypothesis: 💡 Early adopters moved fast and went direct, but the enterprise wave is now arriving in force 💡 Azure gives teams the compliance, security, and procurement infrastructure they already have in place 💡 Azure traffic 4x-ing in 10 weeks likely indicates AI development is maturing quickly