langchain

LangChain announces that users can connect a Managed Deep Agent to Slack, allowing mentions, DMs, and thread replies to trigger agent runs with responses posted in the same conversation.

The article argues that the key barrier to monetizing AI agent builds is not technical skill but the failure to translate technical achievements into clear business value for non-technical customers.

LangChain's guide explores how organizations like Madrigal Pharma, Abridge, and Vizient are scaling AI agents in healthcare and life sciences to accelerate research and reduce documentation burden, focusing on infrastructure for reliability and compliance.

Adam Łucek discusses LangSmith Engine, an agent for automating agent development using trace data.

LangSmith is PodiumHQ's sanctioned platform for building AI agents, with Walker Ward explaining the benefits of a shared tool over multiple solutions.

LangChain announces Managed Deep Agents with @harborframework, offering container-based evaluations tracked in LangSmith to ensure safe modifications to AI agent skills and models.

A discussion seeking feedback from developers on production-level issues with AI agent frameworks like LangChain and CrewAI, and predictions for future improvements.

The article introduces 'Connections,' a feature in Managed Deep Agents that enables managed credentials and per-caller identity for secure agent actions, supporting both static secrets and OAuth grants.

The article discusses the integration of the open-source Stagehand SDK with Browserbase to provide ready-made browser tools for AI agents in LangChain, enabling easy setup for browser interaction.

A tweet outlines key skills such as LangChain, LangGraph, and OpenAI API needed for a six-figure AI Engineer position, with a link to a project for hands-on learning.

LangChain announces new Connection features in Managed Deep Agents 0.7, providing simple agent authentication with support for agent and user credentials to streamline deployment.

LangChain is hosting Interrupt NYC, an AI agent conference featuring talks from Weber Shandwick and focused.io on building agent factories with LangGraph.

LangChain introduces new connection features in Managed Deep Agents 0.7 to simplify agent authentication via OAuth and token management.

LangChain introduces a new feature in its Deep Agents framework where subagents can now fork the supervisor's full conversation context instead of starting from a blank window.

GetCandidly's state model measures gaps in conversation resolution in real time and improves it by inserting prompts that mirror user wording, as highlighted by LangChain.

LangChain announces Deep Agents Code (dcode), an open source coding agent that works with any model and offers control for teams, alongside a free course on LangChain Academy for enterprise implementation.

LangChain Academy introduces a free course on LangSmith Essentials to teach the essentials of the LangSmith platform for agent engineering, including tracing, debugging, and deployments.

The blog post demonstrates how Nevermined empowers LangChain agents to autonomously purchase services using a credit card with spending limits, enabling agents to operate without human intervention for payments.

LangChain announces updates to its MCP support, including the new stateless MCP spec, to enhance AI framework capabilities.

LangChain offers a free LangSmith Essentials course to teach the agent development lifecycle, enabling teams to build, test, deploy, and monitor AI agents systematically.