We just shipped an update to openevals, our open-source library for evaluating LLM applications. Multimodal support: pass images, audio, and PDFs
@langchain
-
Watch Interrupt Keynote Livestream with Harrison Chase on Agents
By
–
New: watch the Interrupt keynote livestream from anywhere. Harrison Chase on where agents are headed, what’s working in production today, and first look at new products. May 13th & 14th · 9:30-10:00 AM PT · Free to register https://
interrupt.langchain.com/livestream -
New LangChain Academy Course Building Reliable Production Agents
By
–
💫 New LangChain Academy Course: Building Reliable Agents 💫
— LangChain (@LangChain) 15 mars 2026
Shipping agents to production is hard. Traditional software is deterministic – when something breaks, you check the logs and fix the code. But agents rely on non-deterministic models.
Add multi-step reasoning, tool… pic.twitter.com/V3XkTrFqW8New LangChain Academy Course: Building Reliable Agents Shipping agents to production is hard. Traditional software is deterministic – when something breaks, you check the logs and fix the code. But agents rely on non-deterministic models. Add multi-step reasoning, tool
-
Harrison Speaking at NVIDIA GTC Keynote Pre-Game on Agentic AI
By
–
Hear Harrison at the NVIDIA GTC Keynote Pre-Game on Monday, March 16 (8-11 AM PT) during the session “The Agentic AI Inflection Point.”
— LangChain (@LangChain) 15 mars 2026
He’ll be joined by:
Peter Steinberger, OpenClaw
Sam Rodriques, Edison Scientific
Vincent Weisser, Prime Intellect
📅 Add it to your calendar:… pic.twitter.com/JUr79tqgL6Hear Harrison at the NVIDIA GTC Keynote Pre-Game on Monday, March 16 (8-11 AM PT) during the session “The Agentic AI Inflection Point.” He’ll be joined by: Peter Steinberger, OpenClaw
Sam Rodriques, Edison Scientific
Vincent Weisser, Prime Intellect Add it to your calendar: -
Open Models Panel at GTC 2026 with Industry Leaders
By
–
Join us Wednesday, March 18th at 12:30pm at GTC for “Open Models: Where We Are and Where We’re Headed”, a panel featuring Harrison, Jensen, and the CEOs of Cursor, Thinking Machines Lab, Perplexity, and more. Add it to your schedule https://
nvidia.com/gtc/session-ca
talog/sessions/gtc26-s82480/
… -
LangSmith Startup Sunday Hacking Brunch in New York
By
–
New York // LangSmith for Startups Presents: Sunday Hacking Brunch Calling all Startup teams to join us for a Sunday hacking brunch with crêpes and coffee. You'll meet fellow founders and engineers from teams powered by agents. Get work done, hang out, and chat with our
-
Post-Cloud AI Infrastructure: Rebuilding the Agent Stack
By
–
What does post-cloud AI infrastructure actually look like? Our co-founder and CEO @hwchase17 sat down with the MAD Podcast at Daytona COMPUTE in SF to go deep on how the agent stack is being rebuilt from scratch — including context windows, memory, orchestration, observability,
-
Honeywell RAG Agent for Field Technician Equipment Diagnostics
By
–
.
@Honeywell built a RAG-powered agent that helps field technicians diagnose and fix equipment on-site, running fully air-gapped on-prem. Alpesh Desai will break down how they built it at Interrupt. https://
interrupt.langchain.com -
Cogent Security Builds AI Agents to Fix Cybersecurity Vulnerabilities
By
–
🚀 LangSmith for Startups Spotlight: @cogent_security
— LangChain (@LangChain) 12 mars 2026
Cogent is building AI agents that protect the world's largest organizations from cyberattacks. One of the hardest problems in cybersecurity is going from finding a vulnerability to actually fixing it. Cogent is automating… pic.twitter.com/c24YautdXcLangSmith for Startups Spotlight: @cogent_security Cogent is building AI agents that protect the world's largest organizations from cyberattacks. One of the hardest problems in cybersecurity is going from finding a vulnerability to actually fixing it. Cogent is automating
-
Agents in Production: Monitoring Challenges Beyond Traditional Observability
By
–
New York Meetup It Worked on My Laptop: Agents in Production Unlike traditional software, you don't know what your agent will do until it's in production. This means that production monitoring for agents requires different capabilities than traditional observability. Agents