🌐 Managed Deep Agents can now use a browser Your agent can:
– Take actions on sites with no API, like booking a reservation
– Test an application end to end through its UI
– Hand you the browser to sign in, then pick up where it left off Docs ➡️ https://
docs.langchain.com/langsmith/pyth
on/managed-deep-agents-browser-use
…
@langchain
-
Managed Deep Agents Adds Browser Actions Testing and Human Sign In Handoffs
By
–
-
Newer Claude Model Lets LangChain Simplify Design Agent Rules
By
–
one of the biggest things i learned building @LangChain
’s internal design agent is that most of the rules i wrote actually made it worse… they were there to compensate for the model’s intelligence at the time but when Opus 5.5 came out i deleted most of them, and the work got -
OpenWiki Evidence Graph Lets Agents Trace Knowledge to Supporting Sources
By
–
we've been exploring how to make the knowledge openwiki produces more useful to agents. our latest experiment pairs the wiki with a lightweight evidence graph, letting agents follow relationships and trace information back to supporting evidence. on complex, domain-specific
-
Loop Engineering Becomes a DeepLearningAI Course
By
–
"the art of loop engineering" is now a @DeepLearningAI course! https://
deeplearning.ai/courses/loop-e
ngineering-with-langchain-deep-agents
… -
Loop Engineering Course Teaches Agents to Handle Complexity and Improve
By
–
great to work w/ @AndrewYNg and @EAGar123 on this loop engineering course!
— Sydney Runkle (@sydneyrunkle) 28 octobre 2026
this course focuses on how to build agents that can a) handle complex tasks and b) improve over time with deepagents! https://t.co/UsieIulsoHgreat to work w/ @AndrewYNg and @EAGar123 on this loop engineering course! this course focuses on how to build agents that can a) handle complex tasks and b) improve over time with deepagents!
-
Managed Deep Agents Reports Strong Adoption of Dynamic Scheduling
By
–
You’re an mda init and mda deploy away from distributing a proactive agent in your org. Since launching dynamic scheduling for Managed Deep Agents in September, over 70% of MDA runs on LangSmith come from schedules vs human typing a message.
-
Loop Engineering Course Covers Reliable Long Running AI Agents
By
–
Build reliable agents for long-running tasks.
— DeepLearning.AI (@DeepLearningAI) 28 octobre 2026
Loop Engineering with @LangChain Deep Agents: add loops that check output, trigger runs on events, and improve the harness from traces across runs. Taught by @sydneyrunkle and @EAGar123.
Enroll for free: https://t.co/VaNUdjXNkk pic.twitter.com/ivJngyRj2nBuild reliable agents for long-running tasks. Loop Engineering with @LangChain Deep Agents: add loops that check output, trigger runs on events, and improve the harness from traces across runs. Taught by @sydneyrunkle and @EAGar123
. Enroll for free: https://
bit.ly/4kfDJxR -
Brief Guide Explains LangChain’s Framework and Company
By
–
The company? The framework?
— LangChain (@LangChain) 28 octobre 2026
LangChain explained in 2 minutes. pic.twitter.com/S9S0dZ2ZJrThe company? The framework? LangChain explained in 2 minutes.
-
LangSmith Tracks Agent Cache Hit Rates by Thread and Over Time
By
–
LangSmith now tracks cache hit rates for your agents 🦜
— LangChain (@LangChain) 27 octobre 2026
Cached LLM calls are cheaper and faster, so it's worth knowing how often your agent actually gets a hit.
📊 View your agent's overall hit rate as a single stat
🧵 Break it down thread by thread
📈 Chart it over time with… pic.twitter.com/G5SSW5rYbmLangSmith now tracks cache hit rates for your agents 🦜 Cached LLM calls are cheaper and faster, so it's worth knowing how often your agent actually gets a hit. 📊 View your agent's overall hit rate as a single stat
🧵 Break it down thread by thread
📈 Chart it over time with -
Company Agent Harnesses Let Teams Share Domain Knowledge Across Departments
By
–
Company harnesses break down knowledge silos Three in four requests to Content Studio come from people outside marketing. This usage pattern is why I'm so bullish on company harnesses: they allow everyone to get involved in domains they had no business in before. We've encoded