Design agents with control
Add human oversight and create stateful, scalable workflows with AI agents.
Stay in the driver's seat. Build copilots that write first drafts for review, act on your behalf, or wait for approval before execution.
Customize your agent runtime with LangGraph
LangGraph provides control for custom agent and multi-agent workflows, seamless human-in-the-loop interactions, and native streaming support for enhanced agent reliability and execution.
About LangGraph
001
Force call a tool
002
Wait for human-in-the-loop approval
003
Multiple agents collaborating on a common goal
004
Stream intermediate steps as they happen
Build the right cognitive architecture for your application
Identify and implement the best prompting strategies and architectures so that your LLMs perform as intended.
Plan-and-execute
001
Multi-agent
002
Go to Docs
Critique Revise
003
ReAct
004
Self-ask
005
Autonomous, but well‑behaved
Go to Docs
Debugging agents got you down? LangSmith can help.
LangSmith gives you the explainability to understand why your agents go off track and how to get them humming again.
Explore LangSmith
001
End-to-end trace observability
002
Tool selection visibility
003
Playground with prompt, model, and tool definition variability
004
Cost, latency, and error tracking
005
LLM evaluators for agent runs
Resources for Agents
Introduction to LangGraph
LangChain Academy Course
data Report
State of AI Agents (2024)
use cases
Breakout Agentic Apps
Ready to start shipping reliable agents faster?
Get started with tools from the LangChain product suite for every step of the agent development lifecycle.
Products
Resources
Company
Sign up for our newsletter to stay up to date
