LangChain - Videos
Back to Channel
Get Started with LangSmith Multi-turn Evaluations
Once you have a good sense of the top usage patterns your agent is handling, you can start to drill into how each complete conversation is performing. Multi-turn Evals help you measure whether your...
Building LangChain and LangGraph 1.0
LangChain CEO Harrison Chase sits down with open source engineers Sydney, Hunter, and Will for an in-depth technical discussion on the major 1.0 releases of LangChain and LangGraph. The team explor...
LangChain: Engineer reliable agents
We're launching LangChain 1.0 and LangGraph 1.0 — and announcing our $125M Series B. Building reliable agents has traditionally been hard. What started as frameworks for LLM applications has evolv...
Get Started with Insights Agent in LangSmith
Today's popular agents produce millions of traces per day—soon to be billions. These traces contain valuable signal about an agent's capabilities and how real users engage with it. If you could rev...
Context Engineering for AI Agents with LangChain and Manus
Join us for a deep dive into context engineering – the critical practice that determines how well your AI agents perform in production. Lance Martin from LangChain and Manus co-founder Yichao "Peak...
How We Built it: Clay - Fireside Chat with CEO Kareem Amin
Go behind the scenes with Kareem Amin (CEO of Clay) and Julia Schottenstein (Head of GTM and OPS at LangChain) in this fireside chat from Clay's conference. Discover Clay's philosophy on building A...
Getting Started with LangSmith (3/8): Debugging with Studio
- Code: https://github.com/xuro-langchain/eli5 - Learn more about LangSmith: https://www.langchain.com/langsmith/?utm_medium=social&utm_source=youtube&utm_campaign=q2-2025_onboarding-videos_co - Ge...
Getting Started with LangSmith (2/8): Types of Runs
- Code: https://github.com/xuro-langchain/eli5 - Learn more about LangSmith: https://www.langchain.com/langsmith/?utm_medium=social&utm_source=youtube&utm_campaign=q2-2025_onboarding-videos_co - Ge...
Rewriting Deep Agents on top of LangChain 1.0
In this video, we will walk through how we rebuilt DeepAgents on top of LangChain 1.0. It will cover the basics of deep agents (planning, filesystem, sub agents), and show case a real world and pra...
LangChain Academy New Course: Deep Agents with LangGraph
Many agents today follow the same simple pattern: run in a loop, call tools. That architecture works well enough, but it breaks down as tasks get more complex. Today, companies of all sizes – from...
Adding Human-in-the-Loop to DeepAgents
Many tools that you may want to give to agents will take actions in the real world. For these tools, you will often want to add "human-in-the-loop" steps - require a human user to approve, edit, or...
How PagerDuty Built AI Agents with LangGraph to Transform Incident Management
PagerDuty's engineering team built an AI agent that transforms how teams interact with incident data, replacing dashboard navigation with natural language conversations. Learn how LangGraph's struc...
Using `deepagents` to Build Deep Research (Python)
In this video we will use `deepagents` to build a Deep Research example. This consists of defining a search tool, defining some sub agents, and writing a detailed prompt. Example folder: https://g...
Deep Agents JS
Deep Agents is now in JavaScript! Simple tool-calling loops break down on long-horizon or intricate problems. Deep Agents, like Deep Research, Claude Code & Manus, chain reasoning, adapt plans, an...
LangChain Academy New Course: Deep Research with LangGraph
Deep research agents are taking off – from major AI labs to companies building their own. Research is inherently open-ended. You can't always predict whether a question needs broad exploration or...
Getting Started with LangChain Education
Welcome to LangChain Education! We offer a few different ways to learn – including courses, YouTube videos, and docs. Start diving in below! LangChain Academy: https://academy.langchain.com/?utm_...
Deep Agents UI
Deep agents operate with a todo list, file system, and subagents We built a dedicated UI for running deep agents that properly highlights all of these things! Github: https://github.com/langchain-a...
Testing Driving GPT 5
OpenAI just released GPT-5, their new series of frontier LLMs. Here, we analyze the models, assess reactions from developers, show how to use them, and provide some results from our own testing. O...
Introducing Open SWE: An Open-Source Asynchronous Coding Agent
An async, fully autonomous coding agent. Demo: https://swe.langchain.com GitHub Repository: https://github.com/langchain-ai/open-swe Documentation: https://docs.langchain.com/labs/swe Blog: https...
Tracing Claude Code to LangSmith
You can now trace your claude code sessions to LangSmith! See how to set up tracing from claude code to LangSmith in just a few minutes. Check out the docs for detailed instructions: https://docs....
n8n Tracing to LangSmith
Learn how to quickly set up tracing from n8n to LangSmith! Docs: https://docs.n8n.io/advanced-ai/langchain/langsmith/ Sign up for LangSmith: https://smith.langchain.com/
Implementing deepagents: a technical walkthrough
We recently released `deepagents`, a Python package making it easier to build "Deep Agents". This comes with built in sub agent support, a planning tool, a virtual file system, and detailed prompts...
What are Deep Agents?
Using an LLM to call tools in a loop is the simplest form of an agent. This architecture, however, can yield agents that are “shallow” and fail to plan and act over longer, more complex tasks. Appl...
Introducing Align Evals: Streamlining LLM Application Evaluation 🚀
Evaluations are a key technique for improving your application — whether you’re working on a single prompt or a complex agent. Iterating on evaluators has often involved a lot of guesswork. With ...
How to apply context engineering
Agents need context (e.g., instructions, external knowledge, tool feedback) to perform tasks. Context engineering is the art and science of filling the context window with just the right informatio...
Open Deep Research
Open Deep Research is an open source agent that is built on LangGraph and can be hooked up to your own data sources, LLMs, and MCP servers. In this video, we walk through the agent’s architecture a...
Context Engineering for Agents
Agents need context (e.g., instructions, external knowledge, tool feedback) to perform tasks. Context engineering is the art and science of filling the context window with just the right informatio...
LangGraph Assistants: Building Configurable AI Agents
Note: LangGraph Platform is now LangSmith Deployment. LangGraph Studio is now LangSmith Studio. Learn how to build scalable AI agent systems with LangGraph Assistants, a powerful approach that sep...
How Prosper Cut QA Costs by 90% for Financial Services with LangGraph Agents
Learn how Prosper Marketplace transformed their customer call QA process for financial services using LangGraph, reducing verification costs from tens of dollars to cents per call. In this video, s...
Building a multi-modal researcher with Gemini 2.5
The Gemini 2.5 series of models from Google has been at the top of leaderboards for many tasks with strong reasoning, coding, and multi-modal capabilities. In this video, we show how to take advant...
How to Build an Agent with Auth and Payments - LangGraph.js
Build a Complete AgentChat App with Auth + Payments using LangGraph.js This full-stack template includes everything you need to build and monetize an AI chat service. ⭐ Repo: https://github.com/...
How City of Hope saved clinicians 1000+ hours with HopeLLM
Sina Mehdinia, a Lead Data Scientist in the Applied AI & Data Science department at City of Hope, one of the largest and most advanced cancer research and treatment organizations in the U.S., share...
From Quora to Poe: Adam D'Angelo on Building Platforms for LLMs and Agents | LangChain Interrupt
Adam D'Angelo, co-founder and CEO of Quora, shares insights from building Poe—the AI platform that gives users access to multiple language models and agents under one subscription. He reveals surpr...
LangChain Academy New Course: Building Ambient Agents with LangGraph
Note: LangGraph Platform is now LangSmith Deployment. Our latest LangChain Academy course – Building Ambient Agents with LangGraph – is now available! Most agents today handle one request at a ti...
Getting Started with LangSmith (8/8): Dashboards
- Code: https://github.com/xuro-langchain/eli5 - Learn more about LangSmith: https://www.langchain.com/langsmith/?utm_medium=social&utm_source=youtube&utm_campaign=q2-2025_onboarding-videos_co - Ge...
Getting Started with LangSmith (7/8): Automations & Online Evaluation
- Code: https://github.com/xuro-langchain/eli5 - Learn more about LangSmith: https://www.langchain.com/langsmith/?utm_medium=social&utm_source=youtube&utm_campaign=q2-2025_onboarding-videos_co - Ge...
Getting Started with LangSmith (4/6): Annotation Queues
- Code: https://github.com/xuro-langchain/eli5 - Learn more about LangSmith: https://www.langchain.com/langsmith/?utm_medium=social&utm_source=youtube&utm_campaign=q2-2025_onboarding-videos_co - Ge...
Getting Started with LangSmith (3/6): Datasets & Evaluations
- Code: https://github.com/xuro-langchain/eli5 - Learn more about LangSmith: https://www.langchain.com/langsmith/?utm_medium=social&utm_source=youtube&utm_campaign=q2-2025_onboarding-videos_co - Ge...
Getting Started with LangSmith (2/6): Playground & Prompts
- Code: https://github.com/xuro-langchain/eli5 - Learn more about LangSmith: https://www.langchain.com/langsmith/?utm_medium=social&utm_source=youtube&utm_campaign=q2-2025_onboarding-videos_co - Ge...
Getting Started with LangSmith (1/6): Tracing
- Code: https://github.com/xuro-langchain/eli5 - Learn more about LangSmith: https://www.langchain.com/langsmith/?utm_medium=social&utm_source=youtube&utm_campaign=q2-2025_onboarding-videos_co - Ge...
How Unify Built AI Research Agents at Scale with LangGraph and LangSmith
Unify scaled their AI research agents to handle 36 billion tokens monthly - here's what Connor Heggie (CTO) and Kunal Rai (Engineer) learned along the way. From initial ReAct framework experiments ...
How Rakuten AI for Business AI Builds Production-Ready Agents with LangGraph
See how Rakuten AI for Business built their internal generative AI platforms serving 70+ businesses across Japan. Learn their approach to democratizing AI development, enabling teams to create and ...
Cisco TAC’s GenAI Transformation: Building Enterprise Support Agents with LangSmith and LangGraph
Cisco's Technical Assistance Center (TAC) shares their comprehensive GenAI transformation journey, from early LLM experiments to production AI agents integrated across Cisco's product ecosystem. In...
How Pigment Built an AI-Powered Business Planning Platform with LangGraph
Discover how Pigment revolutionized enterprise planning and performance management by replacing Excel and legacy systems with AI. In this video, see how they built conversational AI and autonomous ...
Using LangGraph Studio WITHOUT building your agent on LangGraph
LangSmith and LangGraph Studio provide generally useful tooling for tracing, testing, and evaluation. They work seamlessly with LangChain and LangGraph, but many AI application don't use these fram...
Factory Co-Founder & CTO on Building Reliable AI Agents | LangChain Interrupt
Factory Co-Founder and CTO Eno Reyes reveals why the future of software development requires a fundamental shift from AI-assisted coding to fully agent-driven workflows that can deliver 5-20x produ...
No Code LangSmith Evaluations
Evaluations are critical for building and improving AI applications. But it can be challenging to get started, especially for non-technical users. Here, we show how to kick off LangSmith evaluation...
Vizient’s Healthcare AI Platform: Scaling LLM Queries with LangSmith and LangGraph
In this video, see how a healthcare AI team solved LLM rate-limiting and multi-agent orchestration challenges while building a platform to help healthcare providers analyze patient outcomes and cli...
Morningstar’s AI Assistant "Mo": Saving 30% of Analysts' Time Spent on Research with LangGraph
Morningstar's 5-person engineering team launched "Mo," their first AI research assistant, and scaled it to nearly 20 production instances serving 3,000 internal users. In this video, see how they b...
Why LLM Data Processing Pipelines Fail: UC Berkeley Research Insights | LangChain Interrupt
UC Berkeley PhD student Shreya Shankar shares research insights on why LLM data processing pipelines consistently fail in real-world applications. Based on systematic studies of developers building...