Tag
Austin Berke, Lead AI Product Engineer at Harmonic, shared how they used LangChain's Deep Agents framework to rebuild Scout, quadrupling user retention from week 1 to week 4. The core approach is to use the file system as shared storage to manage context, connecting agents, frontend, and deterministic processes, allowing the model to build context on demand.
LangChain shares a guide by Sydney Runkle explaining the differences and use cases for Deep Agents, LangChain, and LangGraph, with examples to help developers choose the right package.
LangSmith's LLM Gateway now supports Kimi K3 and other open models via Gateway Credits, letting users call hosted models with just a LangSmith API key without configuring provider secrets.
LangChain Academy announces an update to its free 'Introduction to Deep Agents' course, adding modules on dynamic and async subagents, a course tutor skill, capstone projects, practice exercises, and TypeScript support, along with Deep Agents v0.7 updates.
LangChain announces it has added ISO 27001:2022 certification along with SOC 2, GDPR, and HIPAA compliance, strengthening its enterprise security posture.
A LangChain team member explains that Skills are shareable prompts that help AI agents focus on specific tasks, highlighting their value in agent development.
LangChain announces that Spring Health's Sr. Director of Engineering Marissa Saunders will speak at Interrupt NYC, a conference on AI agents taking place September 24 in New York City.
LangChain's guide examines how Lyft, Fastweb/Vodafone, and LATAM Airlines deploy AI agents for customer experience, covering self-serve platforms, rep copilots, and production feedback loops.
A tweet introducing the eval-engineering skill from langchain-ai/langchain-skills, which uses human feedback to generate aligned environments, harnesses, and tasks for agent evaluation. It explains the workflow and provides installation instructions for the open-source tool.
OpenWiki, a CLI that generates and maintains self-updating wikis for codebases, just received a major upgrade to its code init prompt, producing higher-quality wikis with better codebase coverage and improved eval scores. The tool supports multiple model providers, connectors, and an interactive visualizer.
The author built Agent DevTools, a local debugger for AI agents that inspects prompts, memory, retrieval, and tool calls, with LangChain support and a free Groq demo.
Stripe built an internal Knowledge AI Platform called Kai with Deep Agents in one week, showcasing the potential of internal AI platforms to transform companies.
LangChain is bringing its Interrupt agent conference to London on October 13, featuring a talk by Gregor Beuster of DB Engineering & Consulting about using AI vision agents for railway infrastructure plans.
LangChain Academy launches the first certification for the full Agent Development Lifecycle, offering a 50% discount for the first two months.
A live webinar from Nebius, LangChain, and Tavily demonstrates how to build a production-ready compliance audit AI agent using LangChain Deep Agents, Tavily, and NVIDIA Nemotron 3 Ultra, covering cost/quality tradeoffs and production capabilities.
n8n now officially supports Alibaba Cloud and Qwen models via Bring Your Own API Key, enabling secure enterprise data connections, complex agent orchestration, and automated SaaS decision-making in workflows.
LangChain releases Deep Agents v0.7, a leaner agent harness that cuts base input tokens by 65% through removing the default system prompt, trimming tool descriptions, and making TodoListMiddleware opt-in, with comparable performance validated across multiple models.
LangChain is hosting an Apache DataFusio meetup with Hotdata on August 13th at their San Francisco office, featuring talks on SmithDB and other speakers including Divya Ranganathan and Alexander.
LangChain Academy released a new free course on autonomous agent improvement using LangSmith Engine, covering the agent development lifecycle from identifying issues to monitoring regressions.
The blog argues that as AI generates code faster, understanding the combined execution becomes difficult, and proposes using graph engineering with a compiler to create deterministic orchestrators.