Tag
LangChain introduced Managed Deep Agents at the Interrupt NYC conference, bundling the agent harness with infrastructure to simplify authentication, memory, and channel integrations, while adding a pre-built web search tool, Harbor evaluation integration, and Parallel tool integration — allowing teams to focus on business logic.
LangChain 分享 Snyk 如何将内部支持助手 Snyk Assist 打造为客户产品功能：基于 LangChain + LangGraph 构建，LangSmith 负责可观测性与评估，已处理 6 万次查询、85% 会话无需人工工单解决。
LangChain 展示了一款名为 Restock 的办公室耗材采购智能体应用，可在 Slack 中运行，支持查找商品、准备订单并通过 Stripe Link 代理钱包完成支付，且每笔订单都需人工批准。
LangChain 将在伦敦 Outernet 举办 Interrupt Agent Conference（2026年10月13日），OVO Energy 等企业将分享如何构建飞轮来改进客服 AI 智能体。
LangChain announces Managed Deep Agents v0.9, adding a Schedules SDK that lets agents create their own reminders and recurring tasks, per-run configuration for models/skills/MCP servers/sandboxes, and Slack Reactions to signal run starts.
LangChain shared a video by Sydney Runkle on building a model router into a coding agent harness, demonstrating how to cut costs by 64% without reducing quality by matching tasks to appropriately-sized models.
LangChain announced a webinar on the agentic operating model, covering how enterprise teams should structure ownership, standardization, governance, and infrastructure for scaling production AI agents.
LangChain announces that p0 is sponsoring Interrupt London, featuring a live demo of web infrastructure enabling AI search, extraction, monitoring, and reasoning.
LangChain's Managed Deep Agents now supports user-level memory out of the box, letting agent memory be scoped to individual users or entire teams, configured with a single file and deployed with one command.
LangChain spotlights Corridor, which uses LangSmith to build agentic security evaluations, trace inference pipelines, and manage memory graphs while securing AI coding agents as they write code. Trusted by security teams at companies like Etsy, ElevenLabs, Lovable, and Mercor.
LangChain's official "Agents From Scratch" guide offers a hands-on, four-step roadmap for building an email agent with long-term memory and human-machine collaboration, covering LangGraph workflows, LLM-as-Judge testing, human-in-the-loop confirmation, and LangGraph Store memory integration, with notebooks and source code included.
LangChain shares a practical guide on building a model router inside the agent harness—covering task understanding, model selection, and outcome tracking—claiming a 64% reduction in median cost per thread with no quality loss.
LangChain shares how they built a model router inside the agent harness for their open source coding agent Open SWE, cutting median cost per thread by 64% with no measurable quality change by routing tasks to cheaper models where frontier intelligence isn't needed.
LangChain 发布 LangSmith Fine-Tuning 和 smithtune CLI，让开发者可以直接把 Agent 的运行轨迹转换为微调数据，无需手动搭建训练流水线。
Sydney Runkle introduces a new LangGraph feature: interrupts with typed response schemas, allowing human responses to be validated before being passed back to the agent and enabling real response forms in UIs instead of raw JSON input.
LangChain introduces an Engine that learns how your agent works by reading traces and repositories, then tests for agent-specific weaknesses such as hallucinations and system prompt violations, returning a list of verified issues to fix before they impact users.
LangChain has introduced a new terminal interface for Managed Deep Agents, allowing developers to test agents locally via the `mda chat` command for lightweight development.
LangChain and Box announce an integration that combines agentic orchestration with governed content, enabling structured extraction, auditable logic, and human approval in a single flow.
LangChain is hosting a workshop on agent engineering for life sciences, focusing on creating accurate, observable, and reliable research workflows.
Open-source maintainers are adapting to AI-generated contributions by focusing on issue discussion and co-authoring, while LangChain outlines a tiered agent framework including LangGraph and Deep Agents for complex autonomous tasks.