ZEN INVESTING
LangChain Reveals Deep Agents Eval Framework for AI Accuracy
LangChain open-sources evaluation methodology for Deep Agents, emphasizing targeted testing over volume to improve AI agent reliability in production.
LangChain Unveils Agent Middleware for Custom AI Harness Development
LangChain introduces AgentMiddleware system enabling developers to customize AI agent behavior with hooks for PII detection, dynamic tool selection, and production-ready features.
LangChain Launches Shareable Skills for AI Agent Teams in LangSmith Fleet
LangSmith Fleet now lets teams create and share reusable AI agent skills, codifying company knowledge for specialized tasks across workspaces.
Moda Deploys Multi-Agent AI System for Professional Design Automation
Moda's Deep Agents-powered platform enables non-designers to create production-grade visuals through a three-agent architecture with custom DSL for layout reasoning.
LangChain Splits AI Agents Into Two Security Classes With Fleet Update
LangSmith Fleet introduces Assistants and Claws agent types, solving a critical authorization problem for enterprise AI deployments.
LangChain Launches LangSmith Fleet for Enterprise AI Agent Management
LangChain rebrands Agent Builder as Fleet, adding enterprise controls for permissions, credentials, and multi-agent oversight across organizations.
NVIDIA AI-Q Blueprint Gets LangChain Integration for Enterprise AI Agents
NVIDIA releases detailed tutorial for building enterprise search agents with AI-Q and LangChain, cutting query costs 50% while topping accuracy benchmarks.
LangChain Expands Polly AI Assistant Across LangSmith Platform
LangChain's Polly AI debugging assistant now available platform-wide in LangSmith, adding persistent memory and automated actions for AI agent developers.
LangChain Releases Open SWE Framework for Enterprise AI Coding Agents
LangChain open-sources Open SWE, a framework mirroring coding agent architectures deployed at Stripe, Coinbase, and Ramp. Built on Deep Agents and LangGraph.
LangChain Launches LangSmith Sandboxes for Secure AI Agent Code Execution
LangChain unveils LangSmith Sandboxes in Private Preview, offering microVM-isolated environments for AI agents to safely execute untrusted code.