The EU AI Act is the first comprehensive regulation for AI systems, and it’s right around the corner.
With the clock running down, we took a deeper look at what these requirements mean for your agents at the Article level, and how LangSmith + @LangChain_OSS directly address them.
LangChain Community Spotlight: Distributed LangGraph Architecture with RemoteGraph 🔗
Production-ready example for distributed LangGraph apps with HTTP-invoked subgraphs. Key insight: RemoteGraph returns full state, not deltas—parents handle reducers.
From https://t.co/XglPp3LWzi.
📦 https://t.co/G06jkKmJYt
Only three weeks until Interrupt!
As a LangChain partner, we help teams get agents integrated, observed, and running reliably inside the systems they already have.
If you're building and need agent expertise, grab time with us at Interrupt. See you there!
https://t.co/WkTmCgLViF
Spent last week at #O11yDayNYC alongside our partners at Honeycomb.
Much of the conversation focused on how observability evolves as systems become more complex. Exactly the work we’ve been leaning into together.
Big thanks to the Honeycomb team for bringing everyone together for such a great event.
Full takeaways ↓
https://t.co/KCzF4g0a0B
Our newest use case is up! Streaming agent state with LangGraph.
If your agent takes ~9 seconds to run a workflow, don’t make users stare at a blank screen.
Stream node updates, tool calls, and LLM tokens to the UI while it runs.
https://t.co/tiarVykRqv
Denver builders 👋
Tomorrow: Official Denver LangChain Meetup.
We’re breaking down what it actually takes to run LangChain systems in production.
Real incident walkthrough. Real lessons learned.
If you’re building agents or moving from experiments to production, join us.
Food + drinks provided.
https://t.co/vbpPMtt0E7
We’re hosting the first official LangChain meetup in Denver in just two weeks!
Lead Agent Engineer Emilio Navarro will walk through how to detect errors early with LangSmith and why eval and observability are critical in production agent systems.
We hope you'll join us → https://t.co/vbpPMtt0E7
I have an interview question I was told is too hard for the Agent Engineer position. How would you solve it?
If you do well you can skip the first two interviews.
Client has asked us to create a RAG for discovery documents for trial. Documents are transcripts from depositions, emails, and SMS.
The client would like the AI to answer the question "has X person ever contradicted themselves, show me where?"
Explain how you'd create a agentic RAG that can solve this problem.
Our AI engineers are deep in it building with @langchain every day.
Focused AI engineer Agustin shares three lessons from his first real-world multi-agent system!
https://t.co/8orMGCjXFY
Our AI engineers are deep in it building with @langchain every day.
Focused AI engineer Agustin shares three lessons from his first real-world multi-agent system!
https://t.co/8orMGCjXFY
LangChain systems break.
The agent blames RAG.
RAG blames the vector store.
And no one knows what actually failed.
Focused builds systems with real structure: https://t.co/lzbZXw6Szs
Arc sparks heated debates.
People either love it or hate it because it has a strong take on how people should browse.
We unpack the hype in the full episode: https://t.co/80qbaWNC8z
What’s the biggest mistake you’ve made with LangChain?
Our CEO says it’s starting with LangChain instead of LangGraph.
Do you agree? https://t.co/lzbZXw6Szs
Prompting isn’t enough.
Software Developer Matias shows how we use LangSmith to debug and scale real LLM pipelines.
Here’s the approach: https://t.co/Zqwpo6yJ9z
We helped Hamlet launch Speaker Search, an LLM-powered tool that makes civic data easier to navigate.
Built with @langchain, LangSmith, and custom evals. Over 90% accuracy. Live in under 3 months.
Full case study: https://t.co/PGqtoteoHX
Our CEO Austin Vance shares how to use LangGraph for persistent memory in LLM agents, and why prompt quality isn’t enough.
Read more: https://t.co/AUFLBnc3Vy
Agents without structure will fail in prod.
LangGraph is the fix.
The agent works once in dev, maybe even passes a few tests, then breaks the second it hits something unexpected.
See how we build it: https://t.co/lzbZXw7qp0