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 separates your agent's core architecture from its runtime configuration. This video demonstrates how to create multiple specialized agents from a single codebase, enabling rapid deployment and experimentation without constant code changes.

In this video, you'll discover how to transform static agents into flexible, configurable systems that can be customized for different use cases, teams, and requirements. We'll cover the complete workflow from local development to production deployment, including visual configuration management and programmatic assistant creation.

Chapters:
00:00: Introduction: Configuration & Assistants
03:25: Converting Static Agents to Configurable Agents
07:16: Visual Configuration with LangSmith Studio
10:15: Advanced Node-Level Configuration
12:36: Deployed Assistants on LangSmith Deployment
14:35: Versioning & Assistant Management 
15:30: Programmatic Assistant Management
19:19: Outro

Documentation & Resources:
• Repo Used in Video: https://github.com/victorm-lc/assistants-demo
• LangGraph: https://langchain-ai.github.io/langgraph/
• LangSmith Deployment: https://langchain-ai.github.io/langgraph/concepts/langgraph_platform/
• LangSmith Studio: https://langchain-ai.github.io/langgraph/concepts/langgraph_studio/
• Configuration Guide: https://langchain-ai.github.io/langgraph/how-tos/graph-api/#add-runtime-configuration
• Rebuilding Graphs at Runtime: https://langchain-ai.github.io/langgraph/cloud/deployment/graph_rebuild/
• Node-Level Configuration: https://langchain-ai.github.io/langgraph/cloud/how-tos/iterate_graph_studio/#direct-node-editing

#LangGraph #LangChain #AIAgents #LLM #MachineLearning #AIEngineering