LangChain

638 videos207.0K subscribers

LangChain enables every company to own their intelligence. LangChain's open, model-agnostic harnesses give teams choice and control over how they build their agent architecture. LangSmith brings testing, deployment, and monitoring together so teams can continuously improve their agents, compound intelligence, and govern them at scale. More than 7,000 customers, including Nvidia, Bridgewater, LinkedIn, Workday, Harvey, and Rippling trust LangSmith to improve their agents across the Agent Development Lifecycle.

Ask across these videos

LangChain

Recent Videos (50 of 639)

What building Tesla's autopilot chips taught Cognition's President about AI

What Is Human in the Loop?

Build, Test, Deploy, Monitor: The Agent Development Lifecycle Explained

HTTP Channels for Managed Deep Agents

This Is Why Your Main Agent Shouldn't Read Every Trace

Evaluating Agents in Production: Traces, LLM-as-Judge, and Prompt Management at Wonder

What Happens Inside an AI Right Before It Cheats

We Built a Slack-to-GitHub PR Agent in a Few Lines of Code

How to go from your agent's traces to a fine-tuned model in one workflow

Introducing LangSmith Trajectories: A readable view of every agent session

Introducing LangSmith Engine v2: Detect and ship fixes to agents faster

Introducing LangSmith Custom Apps: Build custom interfaces around your agent data

Schedules for Managed Deep Agents: Cron jobs, prompts, and Slack delivery

What Is LangChain, Actually?

How To Build A Harness With Jev | A LangChain x TypeSafe Conversation

LangSmith explained in 5 minutes

Jev Explained | System 1 vs System 2, for AI models

Ship a GitHub PR From a Slack Message with Managed Deep Agents

The Self-Driving Eval Trick No AI Benchmark Beats

Building a Harness with Jev

How Jev detects PII vs LLMs, explained in under 20 seconds

The 3 Things Clay Measures on Every AI Agent

How Do Agents Remember Anything Between Runs?

What are Deep Agents? Explained fast

Middleware for Managed Deep Agents

How Lyft Increased Its Agent Resolution Rate by 16% with LangSmith and LangGraph

How Do I Get Started Building Agents?

Share your Managed Deep Agent with your team using Slack

The One-Line Integration That Got Clay's Agents Into LangSmith

What is an agent harness? Explained fast

Catch Agent Regressions Before You Ship: Evals for Managed Deep Agents

Why Sierra uses one agent per brand instead of multi-agent systems

Build an Online LLM-as-a-Judge with the LangSmith CLI and a Coding Agent

How Clay Monitors Millions of Agent Runs

How to manage shared and user credentials with Managed Deep Agents Connections

Turn Flagged Traces Into a Dataset in 3 Minutes with the LangSmith CLI

dcode Essentials | New LangChain Academy Course

The "Whack-a-Mole" Problem Every AI Team Hits

The LangSmith Feature Built for Multi-Step Agents

How Unify Cut AI Costs 95% Two Weeks Before Launch

LangSmith Essentials | New LangChain Academy Course

Podium Built Their Own AI Agent Runtime. Then Ditched It.

MCP Explained: The USB-C Cable for AI Agents

Why Clay's Finance Team Loves LangSmith

Inside Clay's Eval Stack: 300M Agent Runs, One LangSmith Pipeline

How Podium Traces Every AI Agent Decision

How Morningstar Stopped Flying Blind on Production Agents with LangSmith

The most common Deep Agents use cases

Accelerate agent improvement with LangSmith Engine

How Do You Actually Evaluate an AI Agent?