LangChain - Videos
Back to Channel
LangChain Live Stream
Interrupt 2026 Keynotes
Hear from LangChain co-founder, Harrison Chase, on what's coming next for AI agents. Learn what's working in production today, where agents are headed, and get a first look at new product drops.
Should You Use a Sandbox for Your Agent? | Max Agency #aidesign #aiinfrastructure
Florian Juengermann, Co-Founder and CTO of Listen Labs, on why sandboxes made for local dev break down fast when you add an agent. If your API key lives in the environment, one rogue prompt is all ...
Great Agent Builders Share These 2 Traits | Max Agency #podcast #agenticai
There are two types of engineers who tend to build great agents. The first has taste — they know what LLMs can and can't do, and they feel it when something's off. The second is a product engineer ...
Your AI Agent Can Ask for Feedback on Itself | Max Agency #podcast #agenticai
What if your AI could review its own work before you even see it? Listen Labs Co-Founder & CTO Florian Juengermann explained how this works to LangChain Co-Founder & CEO Harrison Chase in this clip...
AI Agents That Build Their Own Data Tables | Max Agency #podcast #agenticai
@ListenLabsAI Co-Founder + CTO Florian Juengermann goes behind the scenes of his agents that analyze data by building their own tables — adding columns like "user sentiment," filling in values aut...
How Listen builds AI Agents that review their own work | Florian Juengermann, CTO
Florian Juengermann is the co-founder and CTO of Listen, an AI startup that turns qualitative research across hundreds of interviews, surveys, and focus groups into structured, traceable insights. ...
Make Your LangSmith Deployment Multi-Tenant
When you deploy an agent on LangSmith, you get a full agent server with 30+ API endpoints out of the box — threads, runs, assistants, a built-in store, A2A and MCP protocol support. But by default,...
How to monitor production AI agents: A simple breakdown
Learn more about monitoring production agents in our LangChain Academy course. Enroll for free ➡️ https://academy.langchain.com/courses/production-monitoring/?utm_medium=social&utm_source=youtube&u...
How Hex Builds AI Agents: Making Agents Reason Like Human Data Analysts | Izzy Miller, AI Engineer
Izzy Miller is an AI engineer at Hex, an AI analytics platform that was one of the first companies to ship data agents to real paying users. Today, Hex runs a multi-agent system with nearly 100K to...
Deploy Agents with A2A on LangSmith Deployment
Every LangSmith Deployment comes with built-in A2A (Agent-to-Agent) support, no extra configuration needed! In this video, we walk through how your deployed agents automatically get A2A-compatible ...
7,500+ Arcade.dev tools now available in LangSmith Fleet
Arcade's library of 7,500+ agent-optimized MCP tools is now available in LangSmith Fleet. In this demo, we show how to connect Arcade's MCP Gateway to Fleet and start building agents that work acro...
LangChain Academy New Course: Monitoring Production Agents
Enroll for free ➡️ https://academy.langchain.com/courses/production-monitoring/?utm_medium=social&utm_source=youtube&utm_campaign=q1-2026_monitoring-academy-lauch_aw Shipping agents to production ...
Deep Dive: How to Monitor AI Agents in Production
You don’t know what your agent will do until it’s in production. In this technical deep dive, learn why production monitoring for AI agents requires a new approach to observability. When you ship...
Skills in LangSmith Fleet
Fleet now supports shareable skills, so you equip agents across your team with knowledge for specialized tasks. Create them from a prompt or manually, start from templates, or import from GitHub....
Webhooks for LangSmith Deployment: Notify Slack When Your Agent Run Finishes
Learn how to set up webhook alerts for your LangSmith Deployment so you get notified in Slack as soon as your agent run completes. In this video, Hari from LangChain walks through: 00:00 - Intro 0...
Introducing LangSmith Fleet
Introducing LangSmith Fleet. Agents for event team. → Build agents with natural language → Share and control over who can edit, run, or clone each agent → Manage authentication with agent identity ...
LangSmith Fleet: Agents for the whole company
Agent Builder is now Fleet. Give every team the ability to build, use, and manage AI agents with the security your org requires. Try it free: https://www.langchain.com/langsmith/fleet
Polly AI Assistant now generally available in LangSmith
In most debugging sessions, you're clicking through traces, switching pages, and losing your place. Polly is the AI assistant built into LangSmith to keep up with you. In this video, see Polly in ...
Open Models, Open Runtime, Open Harness - Building your own AI agent with LangChain and Nvidia
Claude Code, OpenClaw, Manus and other agents all use the same architecture under the hood. They consist of a model, a runtime (environment), and a harness. In this video, we show how to create a c...
Introducing: LangSmith Sandboxes (Now in Private Preview)
Agents get a lot more useful when they can execute code. But letting an LLM run arbitrary code without isolation from your infrastructure is risky. Sandboxes give you ephemeral, locked-down envir...
Deploy CLI: The Easiest Way to Deploy Agents from Your Terminal
Learn how to go from zero to a production-ready AI agent using langgraph deploy, all from your terminal. In this tutorial, we walk through the full CLI workflow: scaffolding a new agent with langgr...
How to Debug, Evaluate, and Ship Reliable AI Agents with LangSmith
Learn the foundations for understanding, improving, and confidently deploying AI agents. Get practical steps on how to debug non-deterministic agent behavior, iterate on performance, and ship reli...
Introducing Support for Multimodal Evaluators in LangSmith
In this video, we walk through LangSmith’s new multi-modal evaluator support in the UI. Learn how to evaluate interactions that include attachments and base64 multi-modal content, with flexible map...
LangChain & LangSmith Skills: Teach Your AI to Build Agents
See how to use LangChain and LangSmith skills to give your coding agent deep expertise in agent development. Watch Claude Code use skills to navigate the full agent development lifecycle, from buil...
LangSmith Agent Builder
LangSmith Agent Builder enables anyone to build agents using natural language: - Describe your goal in your own words. Agent Builder figures out the approach. - It creates detailed instructions,...
LangSmith: Agent observability, evaluation, and deployment
Anyone can build an agent. But is yours actually working? LangSmith is the agent engineering platform built for observability, evaluation, and everything in between — so you can stop guessing and s...
New in LangSmith Agent Builder: all new agent chat, file uploads, and tool registry
New releases in LangSmith Agent Builder: - All new agent chat: One always-available agent with access to all your workspace tools - Chat → Agent: Turn any conversation into a specialized agent with...
Observability and Evals for AI Agents: A Simple Breakdown
- You don't know what your agents will do until you actually run them — which means agent observability is different and more important than software observability - Agents often do complex, open-e...
The Future of Agent UIs: Streaming Subagents in Real Time
Today’s AI agents don’t run in a straight line anymore. They plan, delegate, and spin up multiple subagents in parallel. But most UIs still show… a loading spinner. In this video, Christian Broma...
Building Better AI Agents: Observability and Evaluation
AI agents don't fail like traditional software. When an agent takes hundreds of steps, repeatedly calls tools, updates state, and still produces the wrong result, there is no stack trace to inspect...
The Only Way to Debug AI Agents
When something goes wrong in traditional software, you know what to do: check the error logs, look at the stack trace, find the line of code that failed. But AI agents have changed what we're debu...
The Secret to Scalable AI Agents: Virtual Filesystems with Deep Agents
Your AI agent sees one filesystem. Under the hood? S3, SQLite, and local disk, all working together. In this video, I show how Deep Agents uses virtual filesystems to give your agent a unified int...
What AI Agents Talk About on Moltbook
Wonder what your AI Agents are talking about on Moltbook? With LangSmith Insights Agent you can look at all the posts out there and see different trends and topics! 1. Scrape posts 2. Upload to La...
Introducing: LangSmith Agent Builder
LangSmith Agent Builder enables anyone to build agents using natural language: - Describe your goal in your own words. Agent Builder figures out the approach. - It creates detailed instructions, se...
Introducing /remember: Teaching Agents to Learn from Experience
🧠Shipping /remember in the Deep Agents CLI: a primitive for persistent agent memory How it works: - inject a reflection prompt into your conversation thread - agent analyzes full context + identi...
LangChain Academy New Course: LangSmith Agent Builder
LangSmith Agent Builder enables anyone to build agents for complex daily tasks, without writing code. It’s simple. You start by describing the goal in your own words. Agent Builder determines the ...
LangSmith Agent Builder Technical Highlights
Six technical features central to LangSmith Agent Builder: 1. It's built on the Deep Agents harness 2. The agent is a filesystem 3. Memory is built in 4. Triggers let them act autonomously 5. Super...
3 Hidden Features That Make AI Agents Production-Ready
In this video I walk through 3 less-known features that make agentic apps feel actually production-ready, using real code from the LangGraphJS repository. 📚 What you’ll learn - Render reasoning to...
Building with Subagents: Design Decisions
The subagents multi-agent pattern is straightforward—but the implementation details really matter for performance. In this video we break down the design decisions that determine whether your syst...
Choosing the Right Multi-Agent Architecture
When do you actually need a multi agent system? And how should you decide what architecture to use? In this video we break down 4 architectural patterns (subagents, skills, router, and handoffs) w...
Build Better Agent UX: Streaming Progress, Status, and File Ops with LangChain
Build agent UIs that feel instant: stream **custom events** from LangChain tool calls (progress, status, file operations) straight into React as they happen. In this video we walk through the a dem...
How I built an AI agent to automate my emails with LangSmith Agent Builder
LangSmith Agent Builder is a no-code agent builder. I built an email assistant to monitor and respond to emails, that I've been using for the last ~3 months. Here's what it looks like: 1/ Triggers...
Streaming Typed Agent Messages in LangChain and React
Most “streaming” agent UIs are built around token streams. That works — until you try to build a real UI. In this video, Christian Bromann shows how to stream typed agent messages from a LangChai...
LangSmith Agent Builder: On the street in San Francisco
Join Brace as he finds VCs in South Park, San Francisco and shows them how to build agents to solve their biggest problems using LangSmith Agent Builder. Try LangSmith Agent Builder free: https://...
How Cursor Builds the Future of AI Coding Tools
Harrison Chase and Cursor's Jason Ginsberg discuss the evolution of coding agents, from tab completion to agentic workflows. Learn how Cursor's engineering team ships fast, builds features they use...
Ralph Mode for Deep Agents: Running an Agent Forever
🫡 Ralph Mode for Deep Agents 🫡 What if you could give an AI agent a task and just let it run forever? We built Ralph Mode to test this, built on Deep Agents. Ralph Mode loops an agent with fresh co...
Learning Skills with Deepagents
The biggest gap between AI agents and human intelligence is the ability to learn. There are various emerging approaches to support continual learning for AI agents. Here, we discuss skill-learning ...
Tracing Claude Code to LangSmith
Curious what Claude Code is doing behind the scenes? Or want observability into critical workflows that you’ve set up with Claude Code With our new Claude Code → LangSmith integration, you can vie...
Approaches for Managing Agent Memory
Humans refine their skills and learn preferences through experience. But many AI agents lack this capacity for continual learning. Here, we give an overview of memory in the DeepAgents CLI. Here, w...