AI BriefingLangChain Blog news
The latest AI and developer news from LangChain Blog, with short summaries.
Visit website →Your Harness, Your Memory
The agent harness is the core of memory management, so securing memory sovereignty requires using an open harness.
Interrupt 2026 Preview: Agents at Enterprise Scale
Interrupt 2026 will address enterprise-scale expansion of agents on May 13-14 in San Francisco.
Human Judgment in the Agent Improvement Loop
To maximize the performance of AI agents, an improvement loop that integrates domain experts' tacit knowledge into workflow and tool design is essential.
Deep Agents Deploy: An Open Alternative to Claude Managed Agents
Deep Agents Deploy is an open source agent deployment approach that lets you own your models and memory directly.
Human Judgment Needed in Agent Improvement Loops
Agents get better fast only when expert judgment is built into evaluation and verification loops.
Better Harness: Hill-Climbing the Harness with Evals
It presents a method for iteratively improving agent harnesses by using evals as a training signal.
Deep Agents v0.5 Released
Deep Agents v0.5 adds async subagent and multimodal file support.
Arcade.dev tools added to LangSmith Fleet
LangSmith Fleet has integrated with Arcade.dev, enabling secure use of 7,500+ tools.
How Agents Self-Heal in Production
Right after deployment, the system detects and judges regressions, and an agent automatically fixes them via a PR.
Open Models Have Crossed the Threshold
GLM-5 and MiniMax M2.7 delivered closed-model-level performance on core agentic tasks.
LangChain Newsletter, March 2026
A roundup of March updates including LangSmith Fleet, Polly GA, NVIDIA integration, and Open SWE.
LangChain and MongoDB Announce Partnership: An AI Agent Stack Running on a Database You Already Trust
An AI agent stack combining vector search, state persistence, Text-to-MQL, and observability on top of MongoDB Atlas has arrived.
A Checklist for Preparing Agent Evals
It provides a key checklist of steps to take before building evaluation infrastructure in order to successfully build AI agents.
Agent Evaluation Readiness Checklist
It presents a step-by-step checklist for effectively evaluating AI Agent performance and deploying it reliably.
Kensho Solves Reliable Financial Data Retrieval with LangGraph-Based Multi-Agent Framework
Kensho built a trustworthy search environment by unifying fragmented financial data through 'Grounding,' a LangGraph-based multi-agent framework.
How to Build Evals for Deep Agents
It covers strategies for designing and managing Targeted Evals to accurately measure an agent's actual behavior in production.
How to Build Evals for Deep Agents
To improve an agent's accuracy and reliability, you need to build targeted evaluation systems that reflect real production behavior.
How to Customize Agent Harnesses Using Middleware
Agent middleware allows you to customize the core loop of an agent harness and inject business logic.
LangSmith Fleet Supports Skills Feature
LangSmith Fleet has launched a 'Skills' feature that gives agents domain knowledge and allows it to be shared within teams.
How Moda Built a Production-Grade AI Design Agent Using Deep Agents
Moda used Deep Agents and LangSmith to build a production-grade multi-agent system that performs complex visual design.