Tired of constantly checking if your long-running agent is done? Use the LangSmith Deployment webhook feature to send a slack ping when your run finishes! Here's how to wire it up in a couple of minutes https://
youtu.be/SR6eTBb0k2U Docs: https://
docs.langchain.com/langsmith/use-
webhooks
…
@langchain
-
LangSmith Webhooks: Get Slack Notifications When Agents Complete
By
–
-
Fix Your Agents with LangSmith Startup Credits
By
–
Fix your agents with LangSmith Was great seeing our friends at @AbridgeHQ @cogent_security @ListenLabs @Rippling Netic and more for our donut drop Sign up for LangSmith for Startups. Qualifying startups for our Scale tier can receive $10,000 in LangSmith credits:
-
LangChain and NVIDIA Launch Enterprise Agentic AI Platform
By
–
And that's a wrap on GTC week! – We announced our enterprise agentic AI Platform built with NVIDIA. LangGraph and Deep Agents plug directly into NVIDIA's tooling. You can build agents with the latest Nemotron 3 models deployed with NIM microservices, apply NeMo Guardrails for
-
LangChain Academy: Building Reliable Production Agents Course
By
–
💫 New LangChain Academy Course: Building Reliable Agents 💫
— LangChain (@LangChain) 22 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/cBmDKF4T2nNew 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
-
Building Enterprise Search Deep Agents with NVIDIA and LangChain
By
–
How to Build Deep Agents for Enterprise Search with NVIDIA AI-Q and LangChain Deep Agents: We recently introduced an enterprise agent platform built with NVIDIA AI to support scalable, production-ready agent development. In this blog, you'll learn:
– How to deploy the NVIDIA -
Agents in Production: Unpredictable Behavior Beyond Traditional Software Testing
By
–
New Conceptual Guide: You don’t know what your agent will do until it’s in production With traditional software, you ship with reasonable confidence. Test coverage handles most paths. Monitoring catches errors, latency, and query issues. When something breaks, you read the
-
LangSmith Prompt Hub: Secure Production Prompt Access Control
By
–
In LangSmith Prompt Hub 💬
— LangChain (@LangChain) 20 mars 2026
Define clear access to your production prompts:
• Assign Owners for each prompt
• Owners-only mode restricts who can promote prompts to production
• All other users keep committing without friction
Iterate fast. Promote carefully! 🔒️ pic.twitter.com/d4XILE4q91In LangSmith Prompt Hub Define clear access to your production prompts:
• Assign Owners for each prompt
• Owners-only mode restricts who can promote prompts to production
• All other users keep committing without friction
Iterate fast. Promote carefully! -
AI Agents: Unpredictable Production Behavior and New Testing Challenges
By
–
AI agents introduce a new production challenge: you simply don’t know what your agent will do until it’s in production. They interpret open-ended language, behave differently based on subtle shifts in phrasing, and take multi-step actions that are hard to predict in development
-
Listen: Autonomous AI Agent Conducts Thousands Customer Interviews
By
–
LangSmith for Startups Spotlight: @ListenLabs
— LangChain (@LangChain) 20 mars 2026
Listen is an autonomous research agent that conducts thousands of customer interviews simultaneously. Teams bring a business question, and Listen runs the entire research process: designing studies, recruiting participants,… pic.twitter.com/Il1uYmotuQLangSmith for Startups Spotlight: @ListenLabs Listen is an autonomous research agent that conducts thousands of customer interviews simultaneously. Teams bring a business question, and Listen runs the entire research process: designing studies, recruiting participants,
