Tag
LangChain and Fireworks are hosting a hands-on workshop on August 25th to teach participants how to train custom evaluation models for AI systems, followed by a happy hour. The workshop focuses on building reliable eval models to optimize agent performance in LangSmith.
LATAM Airlines and other CX teams are improving AI customer experience agents by analyzing production conversations, reducing out-of-scope messages and enhancing performance with tools like LangSmith.
LangChain has been featured as one of Lenny Rachitsky's top 100 companies for talent density and ambition, and they are actively hiring.
Toyota builds manufacturing agents using LangChain and utilizes LangSmith to monitor and fix issues like failed tool calls and broken pipelines, ensuring smooth production operations.
LangChain is hosting an event in San Francisco on September 2nd focused on continual learning, featuring technical talks and networking opportunities.
LangChain is hosting a webinar on automating evaluation and environment engineering for AI agents, featuring discussions on using repository context and production traces for building and testing evals.
LangChain is hosting an Agent Conference named Interrupt NYC on September 24th in New York City, featuring Erik Bernhardsson as a headliner among other industry leaders.
LangChain is hiring open-source developers focused on AI agents, detailing their operating principles and directing to career opportunities.
Join LangChain, AWS, and MongoDB at the AWS Agentic AI Partner Showcase Extended in San Francisco to learn about building production-ready agentic AI systems with live demos and technical insights.
LangChain has launched LangSmith Tuned Evaluators, a tool that automatically adds quality feedback to production traces for AI agents, using a tuned model and managed infrastructure to score behavior like Perceived Error.
Unify GTM reduced AI model costs by 90-95% through architectural optimization and prompt caching, emphasizing the importance of adversarial judging models for scalable sales AI agents.
monday.com rebuilt their AI copilot Sidekick by evolving from a single general-purpose agent to a system with specialized subagents and LangSmith Sandboxes, enhancing its capability to handle complex, iterative work in production.
LangChain and AWS have partnered to release AgentCore Payments middleware, allowing AI agents to automatically handle payments for API usage through the x402 protocol, with integrated budgeting and tracking in LangSmith.
LangChain's official Agents From Scratch tutorial provides a detailed guide on how to build an AI agent from scratch with human-in-the-loop and memory capabilities, covering four parts: basic setup, evaluation system, human-in-the-loop (HITL), and long-term memory.
LangChain introduces Managed Deep Agents (MDA), a simplified way to build and deploy production AI agents with managed infrastructure and a deep agent harness.
A 17-minute video run-through by BraceSproul explains OpenWiki, an open-source self-maintaining wiki, covering its core ideas, functionality, and why documentation for AI agents differs from human docs.
LangChain announces updates including support for OpenAI's 3.0 SDK and Gemini 3.7 Flash, along with various reliability fixes contributed by the community.
LangChain has rebuilt Dashboards in LangSmith to improve investigation and reporting, featuring KPIs next to trends, metric comparison, breakdowns by model or user, notes, and freely arrangeable layouts.
LangChain announces that LinkedIn's Tanvi Motwani will speak at Interrupt NYC on Sept 24, sharing the Agentic Eval Playbook behind LinkedIn's Hiring Assistant, covering agent traces, LLM-as-a-Judge systems, and monitoring for production agents.
LangChain tested NVIDIA's open-source router Switchyard with Deep Agents, showing that routing between models can cut costs by ~70% while retaining ~90% accuracy, and introduced new middleware integration for NVIDIA models.