AI BriefingLangChain Blog news
The latest AI and developer news from LangChain Blog, with short summaries.
Visit website →How to Run Deep Agents Code on NVIDIA NemoClaw
NVIDIA NemoClaw enables running Deep Agents code in a security-hardened environment.
How Schneider Electric Built Its LLMOps Foundation with LangSmith
Schneider Electric leveraged LangSmith to build an LLMOps system for managing observability, evaluation, and deployment of large-scale AI agents.
Improving agents is a data mining problem
LangChain explains how to analyze agent traces to find failures, fine-tune low-cost models, and optimize performance.
If Your Coding Agent Costs Have Doubled, Here's How to Fix It
It presents ways to track and manage usage costs across various coding agents like Claude Code and Cursor.
PickOpenWiki: An Open-Source Repository Documentation Tool for Coding Agents
OpenWiki is an open-source tool that automatically generates and maintains documentation so coding agents can better understand codebases.
How to Use RLM in Deep Agents
Deep Agents introduced RLM and dynamic subagents to improve performance in handling large-scale context.
How Pendo Uses LangSmith to Trace Novus from User Behavior Data to Code Fixes
Pendo uses LangSmith to debug, evaluate, and monitor its AI agent Novus.
How Deep Agents Run Untrusted Code Without a Sandbox
LangChain unveiled a technology that safely executes agent code in an isolated environment by leveraging WebAssembly and QuickJS.
Deep Agents Introduces Dynamic Subagents
Deep Agents has launched Dynamic Subagents, which build complex agent pipelines through code-based programmatic orchestration.
Prompt Caching with Deep Agents
Deep Agents automates prompt caching strategies that differ across model providers, reducing the operating costs of AI agents.
June 2026: LangChain Newsletter — Fleet On-Call Copilot, Deep Agents Rubrics, and Other Updates
LangChain unveiled new features for LangSmith and open-source tools for Deep Agents.
How SmithDB Builds Inverted Indexes for Full-Text Search
SmithDB built an inverted index using JSON Tape and String Interning technologies for high-performance full-text search based on object storage.
Why the Best AI Agents Should Be Simple: An Interview with Sierra's Zack Reneau-Wedeen
Instead of multi-agent complexity, Sierra creates real business value through a single-agent model and outcome-based pricing.
How Klarna's AI Assistant Redefined Large-Scale Customer Support for 85 Million Active Users
Klarna leveraged LangGraph and LangSmith to build a high-performance AI agent that replaces the work of 700 employees.
How to Meet EU AI Act Regulatory Requirements with LangSmith and LangChain OSS
LangChain supports compliance with the EU AI Act's regulations on high-risk AI systems through LangSmith and open-source tools.
How to Build Memory for AI Agents
This covers a methodology for designing memory systems that allow AI agents to learn from past experiences and correct their behavior.
How Factory Used LangSmith to Automate Feedback Loops and Double Iteration Speed
Factory adopted LangSmith to gain observability into its LLM pipelines and automate feedback loops, doubling its product iteration speed.
LangSmith: Product Homepage Redesign and Introduction of Tagging Feature for Resource Management
LangSmith has redesigned its homepage and enhanced resource management features to optimize developer workflows.
The Art of Loop Engineering
This introduces the loop engineering strategy of stacking loops hierarchically to increase the reliability of AI agents.
Why Fleet Offers Both General-Purpose Chat and Specialized Agents
Fleet distinguishes between general-purpose chat for one-off tasks and specialized agents that automate recurring work.