Improving Deep Agents with harness engineering Our coding agent went from Top 30 to Top 5 on Terminal Bench 2.0. We only changed the harness. The goal of a harness is to mold the inherently spiky intelligence of a model for tasks we care about. Harness Engineering is about
@langchain
-
LangChain Hosts SF Tech Talk on the Future of Agents
By
–
We’re thrilled to be hosting and speaking at @contrary 's next SF Tech Talk, featuring eng leads from @cognition_labs
, @elevenlabs
, and @andocorporation
. We'll be speaking to the future of agents. Each company will live demo their latest product features for leading builders -
Three Ways to Optimize LangSmith Agent Memory and Performance
By
–
LangSmith Agent Builder uses memory to improve with feedback. Three practical ways to get the most out of memory: → Tell your agent to remember what works
→ Use skills to give it specialized context when needed
→ Edit its instructions directly when that's faster Full -
LangSmith for Startups: Free Tools for Early-Stage Teams
By
–
🚀 Introducing: LangSmith for Startups
— LangChain (@LangChain) 19 février 2026
We are launching LangSmith for Startups to give 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… pic.twitter.com/WizxZ2iBa9Introducing: LangSmith for Startups We are launching LangSmith for Startups to give 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
-
LangSmith Traces Filtering Experience Enhanced with New Updates
By
–
🚀 New updates to the LangSmith filtering experience when viewing Traces!
— LangChain (@LangChain) 19 février 2026
It’s now easier to:
• Apply filters and edit filters
• See active filters at a glance
Happy tracing! pic.twitter.com/ASlK34Wds8New updates to the LangSmith filtering experience when viewing Traces! It’s now easier to:
• Apply filters and edit filters
• See active filters at a glance Happy tracing! -
LangSmith Agent Builder Major Update: New Chat and File Features
By
–
🚀 We just shipped a major update to LangSmith Agent Builder:
— LangChain (@LangChain) 18 février 2026
• New agent chat: One always-available agent with access to all your workspace tools
• Chat → Agent: Turn any conversation into a specialized agent with one click
• File uploads: Attach files directly to Agent… pic.twitter.com/tNDIKLTcY4We just shipped a major update to LangSmith Agent Builder: • New agent chat: One always-available agent with access to all your workspace tools
• Chat → Agent: Turn any conversation into a specialized agent with one click
• File uploads: Attach files directly to Agent -
Monday.com Accelerates AI Agent Evaluation with LangSmith Platform
By
–
Many teams treat evals as a last-mile check. @mondaydotcom Service made them a Day 0 requirement for their AI service agents. Using LangSmith, the monday Service team has been able to: Achieve 8.7x faster evaluation feedback loops (from 162 seconds to 18 seconds).
Get -
Agent Observability Powers Agent Evaluation New Conceptual Video
By
–
✨ New Conceptual Video: Agent Observability Powers Agent Evaluation ✨
— LangChain (@LangChain) 17 février 2026
When something goes wrong in traditional software, you know what to do: check the error logs, look at the stack trace, find the line of code that failed.
But AI agents have changed what we're debugging.… pic.twitter.com/31VzoUhtmhNew Conceptual Video: Agent Observability Powers Agent Evaluation When something goes wrong in traditional software, you know what to do: check the error logs, look at the stack trace, find the line of code that failed. But AI agents have changed what we're debugging.
-
Harness Engineering Improves Deep Agents for Advanced Coding
By
–
Great deep dive into how we're doing Harness Engineering to improve Deep Agents at the frontier of coding!
-
LangSmith Insights: Group Traces and Schedule Recurring Jobs
By
–
🔎 Use LangSmith Insights to group traces and find emergent usage patterns of your agents
— LangChain (@LangChain) 17 février 2026
Now with the ability to set a schedule and run recurring jobs!
Docs 👉 https://t.co/IjrWYOCsri pic.twitter.com/8hgZFJ7qNlUse LangSmith Insights to group traces and find emergent usage patterns of your agents Now with the ability to set a schedule and run recurring jobs! Docs https://
docs.langchain.com/langsmith/insi
ghts
…