AI BriefingLangChain Blog news
The latest AI and developer news from LangChain Blog, with short summaries.
Visit website →LangSmith LLM Gateway: Runtime Governance Integrated into the Agent Lifecycle
LangChain has unveiled LangSmith LLM Gateway, a runtime governance layer that manages agents' cost limits and data security.
Deep Agents v0.7 Released
Deep Agents v0.7 reduces default input tokens by 65% through context engineering optimization without sacrificing performance.
How Similarweb Evaluates Agent Reports Using LangSmith
Similarweb explains how it uses LangSmith to evaluate long-form agentic research reports through rubrics, faithfulness checks, traces, and more.
How LangChain Built an 'Agent-First' Data Stack
LangChain redesigned its existing BI-centric data stack into a structure that lets agents understand business context and perform analysis on their own.
Own the Intelligence: The Key to Sustainable AI Competitiveness
Beyond simply using generic AI, companies must control and own business-specific intelligence to secure differentiated competitiveness.
LangChain July 2026 Newsletter — NemoClaw Blueprint, OpenWiki Brains, and More
LangChain announced major updates including the NVIDIA NemoClaw Blueprint, the OpenWiki Brains memory layer, and a free trial of LangSmith Sandboxes.
Deep Agents Benchmark Methodology
LangChain has released a benchmark framework for its open-source agent harness, Deep Agents.
Eval Engineering Skill: Building Evals with Repository Context and Traces
LangChain has released the 'Eval Engineering Skill,' which automatically generates agent evaluations (evals) by analyzing repository structure and execution traces.
Three Years of Graph Engineering with LangGraph
Drawing on three years of operating LangGraph, LangChain shared its design principles for modeling agents as graphs.
How Apollo Leverages Deep Agents and LangSmith for GTM AI
Apollo adopted Deep Agents and LangSmith to automate complex GTM workflows, improving development efficiency by over 80%.
Tracing Voice Agents in LangSmith
LangSmith has launched a feature that provides visibility into voice agents, supporting major frameworks such as Pipecat and LiveKit.
IssueBench - Method for Evaluating Engine Performance
LangChain built IssueBench, a synthetic benchmark for evaluating LangSmith Engine's ability to identify and categorize issues.
Building Governance-Based Agents: A Framework for Cost, Control, and Compliance
As enterprise AI agents proliferate, the importance of LLM gateways for managing cost, control, and compliance is being emphasized.
PickOpen Source Data Extraction Service
LangChain has released a hosted service that automatically extracts structured data from unstructured documents.
PickOpenWiki 0.2 Adopts OKF for Codebase Documentation
OpenWiki 0.2 now supports Google Cloud's OKF standard, improving the structuring of codebase documentation.
Fleet's New Feature: Deploy AI Agents to Slack in One Click
LangChain's Fleet has launched a feature that lets you build custom AI agents using natural language, with no code required, and deploy them instantly to Slack.
Agents Need Their Own Computers Too: How to Safely Provide Environments
AI agents should be given sandbox-based computer environments so they can safely perform tasks in isolated settings, just like human developers.
How to Debug Coding Agents Using LangSmith Traces
LangSmith visualizes the execution process of various coding agents as standardized Traces, helping with debugging and performance improvement.
OpenWiki Brains: Proactive Memory for AI Agents
OpenWiki Brains converts various sources like Gmail, Notion, and Git into a local wiki to provide AI agents with proactive memory.
LangChain and NVIDIA Launch NemoClaw Deep Agents Blueprint
LangChain and NVIDIA have launched the NemoClaw blueprint for building high-performance agents for enterprises.