AI BriefingLangChain Blog news
The latest AI and developer news from LangChain Blog, with short summaries.
Visit website →Structured Tools
LangChain introduces Structured Tools supporting complex inputs and a new agent class.
Using Skills in Deep Agents
LangChain has added Anthropic's agent skills feature to Deep Agents.
LangSmith Engine Doubles Agent Issue Detection Performance
LangSmith Engine has improved agent issue detection performance by more than 2x and fix performance by 25%.
Building Self-Correcting Memory in OpenWiki
LangChain has introduced self-correcting memory to OpenWiki, enabling it to detect code changes and automatically update documentation.
How to Build Agent Environments and Tasks
LangChain has released a two-stage pipeline that automatically generates environments and tasks for agent evaluation.
Toyota Expands Enterprise AI with Deep Agents and LangSmith
Toyota North America is leveraging Deep Agents and LangSmith to maximize AI development efficiency and pursue eight-figure cost savings.
Test Agent Changes with LangSmith Preview Builds
LangSmith now provides PR-based temporary deployment environments, enabling testing of agent changes before production.
LangSmith Tuned Evaluators Released
LangChain has released **LangSmith Tuned Evaluators**, enabling AI agent evaluation with low cost and high performance.
AgentCore Payments Middleware for LangChain Agents
AgentCore Payments middleware has been released to enable LangChain agents to directly pay for paid APIs.
Why Managed Agents Are the Next Generation Core of Agent Building
Managed agents simplify production deployment through standardized tools and managed infrastructure.
LangSmith BYOC Now Generally Available on AWS
LangSmith BYOC has launched as a generally available service running within customers' AWS accounts and VPCs.
What Percentage of Agent Calls Actually Require a Frontier Model?
Switchyard handled 93% of agent calls with a 30B model, reducing costs by 74%.
Managed Deep Agents: The Fastest Way to Launch Deep Agents for Production
LangSmith has released Managed Deep Agents, which handles the deployment and operation of Deep Agents.
Managed Deep Agents Launches in Public Beta
LangSmith has launched a managed execution environment for Deep Agents in public beta.
Comparison of Deep Agents, LangChain, and LangGraph
The three frameworks divide control levels and abstraction across different layers of the agent stack.
How to Build an Autonomous SRE Agent for Kubernetes
LangChain built an autonomous SRE agent that diagnoses Kubernetes failures and suggests fixes.
How to Evaluate Voice Agents with LangSmith
LangSmith supports evaluating voice agents in terms of execution, outcome, and user experience.
Production CX Agents: Lessons from Lyft, Vodafone, and LATAM Airlines
Lyft, Vodafone, and LATAM Airlines have systematized evaluation, routing, and improvement while operating CX agents.
How Stripe Built Kai with Deep Agents in a Week
Stripe built Kai, a company-wide AI agent, in just one week using Deep Agents.
Evaluating Code Review Agents with ReviewBench
The LangSmith team built ReviewBench, a benchmark for evaluating code review agents based on real PR reviews.