The Agent Evaluation Readiness Checklist Starting to think through how to test your agents? We put together a step-by-step checklist for building, running, and shipping agent evals. We walk through:
→ How to read traces in LangSmith and analyze errors, before building evals
@langchain
-
Agent Evaluation Readiness Checklist: Testing and Shipping Agents
By
–
-
Kensho Multi-Agent Data Retrieval System on LangGraph
By
–
See how @Kensho built a multi-agent data retrieval system on LangGraph to give S&P Global customers a single entry point into verified financial data — equity research, macro, ESG, and more. The architecture consists of a central router + specialized Data Retrieval Agents, one
-
LangSmith for Startups: Free Credits and Tools to Scale
By
–
LangSmith for Startups gives early stage teams the tooling and community they need to iterate faster and win bigger.
— LangChain (@LangChain) 26 mars 2026
Observe, evaluate, and deploy your agents — now with free credits to help you get started.
Our Scale program offers:
• $10,000 in LangSmith credits
•… pic.twitter.com/52o39fkyl6LangSmith for Startups gives early stage teams the tooling and community they need to iterate faster and win bigger. Observe, evaluate, and deploy your agents — now with free credits to help you get started. Our Scale program offers: • $10,000 in LangSmith credits •
-
LangSmith Fleet Integrates Microsoft 365 Tools
By
–
LangSmith Fleet now supports @Microsoft365 tools.
— LangChain (@LangChain) 26 mars 2026
Now you can:
→ Build an agent that triages your Outlook inbox and drafts replies
→ Access Sharepoint docs so your agent has the context it needs
→ Connect any agent to Teams so your whole team can use it
Try Fleet:… pic.twitter.com/ObmwvlhXvTLangSmith Fleet now supports Microsoft 365 tools. Now you can:
→ Build an agent that triages your Outlook inbox and drafts replies
→ Access Sharepoint docs so your agent has the context it needs
→ Connect any agent to Teams so your whole team can use it Try Fleet: -
Agent Middleware Customizes Your Harness for Any Use Case
By
–
Your agent harness needs to bend around your use case. Agent middleware helps you customize your harness without building from scratch.
-
Fleet introduces shareable skills for team domain knowledge
By
–
Fleet now has shareable skills.
— LangChain (@LangChain) 25 mars 2026
Capture your team's domain knowledge once, attach it to any agent, and share it across your workspace.
Create skills from a prompt or previous chat, write them manually, or use a template.
Read more: https://t.co/cP6mepcxch pic.twitter.com/JsHgDTjvkAFleet now has shareable skills. Capture your team's domain knowledge once, attach it to any agent, and share it across your workspace. Create skills from a prompt or previous chat, write them manually, or use a template. Read more: https://
blog.langchain.com/skills-in-lang
smith-fleet/?utm_medium=social&utm_source=twitter&utm_campaign=q1-2026_fleet-launch_aw
… -
Agents in Production: Unpredictability and Monitoring Challenges
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
-
LangChain Showcases New Ecosystem Features at Google Cloud Next
By
–
We’ll be at Google Cloud Next! If you’re attending, stop by Booth #5006 to see what’s new across the LangChain ecosystem: LangSmith for agent observability, evaluation, and deployment
LangSmith Studio for visual agent development
LangSmith Fleet for building agents with natural -
LangSmith Startup Hacking Brunch in New York This Sunday
By
–
New York // LangSmith for Startups Presents: Sunday Hacking Brunch Calling all Startup teams to join us for a hacking brunch with crêpes and coffee this Sunday. You'll meet fellow founders and engineers from teams powered by agents. Get work done, hang out, and chat
-
Moda Launches AI-Powered Design Platform with LangSmith Integration
By
–
Congrats @anvisha and the @trymoda team on the launch.
— LangChain (@LangChain) 25 mars 2026
Moda built a design platform that turns non-designers into design pros.
Under the hood: Deep Agents powering the design agents, with LangSmith providing the observability layer. Lots of smart context engineering in this… https://t.co/7auFmQdhiRCongrats @anvisha and the @trymoda team on the launch. Moda built a design platform that turns non-designers into design pros. Under the hood: Deep Agents powering the design agents, with LangSmith providing the observability layer. Lots of smart context engineering in this