Fixing agent failures in production: Interrupt 2026 recap | LangChain Newsletter

Product Updates


LangSmith Engine: Accelerate the entire agent development lifecycle

Improve agents without spending hours buried in traces. LangSmith Engine watches your production traces, clusters recurring failures into named issues, diagnoses root causes, and proposes fixes for review.

Read the announcement →

Sandboxes GA: Secure code execution environments for agents

LangSmith Sandboxes are Generally Available: secure, scalable environments built for agent code execution, and integrated with the Deep Agents SDK and the LangSmith platform.

Read the announcement →

Everything else we shipped at Interrupt 2026

Other updates focused on two areas: production-grade agent infrastructure and stronger observability and governance.

Read the blog →

Watch Every Interrupt 2026 Session


Two days, 1,000+ builders, and what's actually working with agents in production. Watch all 23 talks from teams at Cisco Customer Experience, LinkedIn, Rippling, and more. Now available on demand.

Watch now →

Speak the Lang

See our favorite use cases, best practices, and customer stories covering the most top-of-mind topics in the AI space.

Introducing LangChain Labs: Advancing continual learning for agents


At Interrupt we launched LangChain Labs, a new effort focused on continual learning to advance open, applied research for every agent. We're excited to partner with Harvey, NVIDIA, Prime Intellect, Fireworks, and Baseten on this initiative.

Read the announcement →

🎙 Max Agency Podcast: Cogent's three-agent architecture for autonomous defense

On the latest episode of Max Agency, Harrison sits down with Cogent Co-Founder & CTO Geng Sng to explore the world of autonomous cyber defense and what it takes to get enterprises to trust an agent within their production environment. Watch below or listen on Apple or Spotify.

Inside Cogent's three-agent architecture for autonomous defense \| Geng Sng (Co-founder, Cogent) - YouTube

Tap to unmute

Inside Cogent's three-agent architecture for autonomous defense \| Geng Sng (Co-founder, Cogent) LangChain

LangChain182K subscribers

ICYMI, watch our _previous episode_ with Alex Shevchenko, Head of Applied Research at Ramp.

Upcoming Events

🗽 June 2 // New York City: Inside the Agent Engine

‍ A technical fireside chat with Harrison and Traversal CEO Anish Agarwal discussing how to build, test, and monitor agents in production. [RSVP →\\

\\

‍](https://luma.com/9k5ttsg2)

🗽 June 3 // New York City: Interrupt Resume

‍ Interrupt is coming to New York! Expect a half-day session including a keynote from Harrison, fireside chat with Pendo, and a hands-on Deep Agents workshop. [RSVP →\\

\\

‍](https://events.langchain.com/register/NYC-InterruptResume-June3/)

⚙ June 10 // Pittsburgh: Improving Production Agents

‍ Hear best practices on how teams turn production traces into insights, issues, and better agent experiences from teams at LangChain team and Credit Genie. [RSVP →\\

\\

‍](https://luma.com/e5tmf1t6)

💻 June 11 // Virtual: How to Shorten the Path from Agent Issue to PR with LangSmith Engine

‍ See how Engine automates the whole agent development loop, from production failure to fix to eval. [Register now →\\

\\

‍](https://events.langchain.com/webinar/how-to-shorten-the-path-with-langsmith-engine/)

💻 June 24 // Virtual: The Agent Development Lifecycle 101

‍ Join Harrison Chase for a walkthrough of the Agent Development Lifecycle and why it matters for teams moving agents into production. [Register now →\\

\\

‍](https://events.langchain.com/webinar/the-agent-development-lifecycle-101/)

🏙 June 29 // Chicago: LangChain X AWS Workshop

‍ A hands-on session on deep agents, including how to integrate them with AWS services to ensure they are scalable, reliable, and enterprise-ready. RSVP →

‍

See all events →

‍

How can you follow along with the Lang Latest? Check out the LangChain blog, Changelog, and YouTube channel for more product and content updates.

For any additional questions or feedback, email us at hello@langchain.dev.