AI BriefingLangChain Blog news
The latest AI and developer news from LangChain Blog, with short summaries.
Visit website →Join LangChain at Google Cloud Next 2026
LangChain is participating in Google Cloud Next 2026, unveiling the latest technology for agent development and LangSmith updates.
Two Types of Agent Authorization Methods
LangSmith Fleet has introduced two agent authorization models: the on-behalf-of-user method and the dedicated-credentials method.
Introducing LangSmith Fleet
LangChain has launched LangSmith Fleet, an enterprise workspace that supports agent creation through management.
LangSmith Officially Launches 'Polly,' an AI Assistant Usable Across All Work Environments
LangSmith has officially launched **Polly**, an AI assistant that supports trace analysis and prompt editing across all work environments.
The Structure of Agent Harnesses
An agent Harness is the system infrastructure around a model, providing filesystem, tools, memory, and orchestration.
How LangChain Built Its GTM Agent
LangChain built a GTM agent based on Deep Agents to automate its sales process, increasing lead conversion rates by 250%.
Technical Evaluation Methodology
To effectively measure the performance of AI agents, an iterative evaluation process is needed that defines tasks, sets performance metrics, and leverages LangSmith.
monday Service + LangSmith: A Code-Centric Evaluation Strategy Built from Day One
monday Service leveraged LangSmith to build a code-centric evaluation framework that verifies agent quality from the early stages of development.
On Agent Frameworks and Agent Observability
As LLMs advance, agent frameworks are evolving from simple chaining to autonomous workflow orchestration.
January 2026: LangChain Newsletter
LangChain unveiled its major January updates, including the GA of LangSmith Agent Builder and a new experiment comparison feature.
Context Management for Deep Agents
LangChain has released the Deep Agents SDK, equipped with context compression techniques for AI agents performing complex, long-running tasks.
Agent Engineering: A New Discipline
Agent engineering is a new field that combines product thinking, engineering, and data science to build reliable LLM systems.
Evaluating Deep Agents: What We Learned
LangChain has unveiled 5 core evaluation patterns for effectively validating Deep Agents.
PickLangSmith Introduces No-Code Agent Builder
LangChain has launched LangSmith Agent Builder, which allows not only developers but also general business users to easily build agents.
How to Turn Claude Code into a Domain-Specific Coding Agent
Combining Claude.md and MCP—high-quality, condensed information—is the key to maximizing a coding agent's performance.
Monte Carlo: Building a Data + AI Observability Agent with LangGraph and LangSmith
Monte Carlo built an AI agent using LangGraph that investigates and resolves data pipeline issues in parallel.
Building LangGraph: Designing an Agent Runtime from First Principles
The LangChain team has unveiled LangGraph, a low-level agent framework optimized for production environments.
Introducing Open SWE: An Open-Source Asynchronous Coding Agent
LangChain has released Open SWE, an open-source asynchronous coding agent that connects directly to GitHub to autonomously write and test code.
How and When You Should Build Multi-Agent Systems
Building a successful multi-agent system hinges on sophisticated Context Engineering and design tailored to the nature of the task.
Interrupt 2025: A Summary of LangChain's AI Agent Conference
LangChain officially launched the LangGraph Platform at Interrupt 2025 while emphasizing the importance of agent engineering.