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 thing I love about LangChain is how the OSS pieces build on each other You can build robust workflows directly with LangGraph, our orchestration framework. We also use it as the foundation for Deep Agents, our higher-level, highly customizable agent harness As Viv mentions, Deep Agents builds on 𝚌𝚛𝚎𝚊𝚝𝚎_𝚊𝚐𝚎𝚗𝚝. Zoom in one layer and 𝚌𝚛𝚎𝚊𝚝𝚎_𝚊𝚐𝚎𝚗𝚝 is built on LangGraph. Zoom out one layer and Fleet, our managed agent platform, is built on Deep Agents You can use whichever level of abstraction you want

one future trend i'm very excited by: models getting good enough where they can power agents that browse the web deepagents + @browserbase is a glimpse of that future See the full example here: github.com/browserbase/in…

✈️ @LATAMAirlines is landing at Interrupt. The largest airline in Latin America built two production agents that handle trip planning and agency coordination. Building them was easy. Operating at scale was the real challenge. At Interrupt, the Agent Conference by LangChain, Head of AI Nico Venegas and Lead Technical Product Manager Claudio Urbina will share what they learned from observing with LangSmith, and how they built Compass, a system that extracts intelligence, improves these agents, and opens new value. Catch this LATAM Airlines talk along with all the others at Interrupt on May 13-14 in San Francisco. Get tickets here 👉 interrupt.langchain.com

💻 Get started: docs.langchain.com/oss/python/int…

Build agents with LangChain + @browserbase. Give your Deep Agents search, fetch, and browser subagents to access the full web. All with full observability with the Browserbase dashboard.

shoutout to the man @kylejeong for cooking this up 🔥 every agent can now get a dedicated browser subagent in seconds to navigate sites, fill out forms, click through things, you get it Deep Agents x Browserbase goes hard

Fleet can now generate and render SVGs and Mermaid diagrams inline! Ask it to make you a diagram, and watch it work its magic. I'm using a mix of our GitHub tools, and @cognition's DeepWiki to make the diagram in this demo. Works super well!

A small, but very useful change! We added this based on our learnings while developing agents in Fleet, so you know it’s a useful addition

And our team is growing!!! 🚀 Open roles: langchain.com/careers

@ryanleecox @nnennahacks @QodoAI @richmondalake Upcoming events: luma.com/langchain

@nnennahacks @LangChain @QodoAI @richmondalake Awesome, can't wait to hear about it!

I gave a talk at @LangChain SF community meetup. It was about “tracing code intelligence” using LangSmith for building complex AI systems at @QodoAI. These folks were really engaged and tuned in! Had so much fun 👍🏽 Shoutout to @richmondalake for these photos + support!

Excited to welcome our sponsor @DEShawGroup back to Interrupt! If you’re a curious mind interested in a career with a leading global investment and technology development firm, take a look at their open roles → deshaw.com/careers

Another amazing meetup! More on the horizon.

most of the time, you want an agent loop to run uninterrupted. that's where the utility comes from! but some decisions shouldn't be delegated to the agent. two situations come up consistently: 1/ before a consequential action, like sending an email, executing a transaction, or deleting files, you want to see exactly what the agent is about to do. approve it, edit it, or push back with feedback so it can revise and try again. 2/ when the agent hits a judgment call it can't resolve alone. not because it's missing a tool, because the answer depends on your preference. "which config file should i modify?" or "should this go to staging or production?" your answer gets fed directly back into the run. here's the part that matters for production: these pauses can last indefinitely. seconds, hours, days. that's only possible if the runtime persists state across the response gap. when the human responds, whenever that is, the agent reloads full context and continues from exactly where it stopped. in langgraph, interrupt() saves state to a checkpointer and surfaces a payload to the caller. command(resume=...) reloads it and picks up execution. langchain and deep agents build on top of those primitives with HITL middleware, so instead of wiring this yourself, you attach HITL policies directly to tool calls. #interrupt-decision-types" target="_blank" rel="nofollow noopener">docs.langchain.com/oss/python/lan…

new mode for LangChain's human in the loop middleware: respond instead of running a tool, you can return the human's interrupt response directly as the tool's output handy for "ask user" stubs or headless tools that depend on direct user input! docs.langchain.com/oss/python/lan…

Watch the full conversation: ⏯️ YouTube: youtube.com/watch?v=YTTH-0… 🎧 Apple Podcasts: podcasts.apple.com/us/podcast/how… 🎧 Spotify: open.spotify.com/episode/5t8U5I…

Should you use a sandbox for your agent? @ListenLabs Co-Founder & CTO @florian_jue shared what can go wrong on the Max Agency podcast hosted by @hwchase17 .

Learn how Madrigal built a flexible and scalable multi-agent research and intelligence platform for pharma with @LangChain in a new blog post by our own Ron Filippo and Parth Patel. LangSmith has been a critical partner in our journey as we grow scale AI across our operations. Read more: lnkd.in/ddu3ifXh

All aboard!

Meet @merge_api at Interrupt! Merge provides one platform for the hardest parts of building AI, handling the integrations, agent infrastructure, and model routing so your team can stay focused on product.