langgraph-fundamentals

Build and orchestrate agent workflows with LangGraph directed graphs and reducers.

1|Updated Mar 15, 2026

Search Tags:#langgraph #state-management #graph #parallel-processing #agent-workflows #conditional-edges

Ready to run

npx skills add https://github.com/kegbi/monica-companion --skill langgraph-fundamentals-kegbi

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: langgraph-fundamentals
Source: https://github.com/kegbi/monica-companion/tree/main/.agents/skills/langgraph-fundamentals
Command: npx skills add https://github.com/kegbi/monica-companion --skill langgraph-fundamentals-kegbi

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

LangGraph fundamentals provide a structured approach to building and orchestrating agent workflows as directed graphs, including state management, node definitions, edge routing, and runtime execution semantics.

Core Features & Use Cases

Graph modeling with StateGraph, Nodes, Edges, START/END.
State management with reducers and partial updates to support complex workflows.
Advanced routing: conditional edges, Command for combined updates and routing, Send for parallel tasks.
Compile-before-run and streaming capabilities for real-time insights and safe execution.
Use cases include building chat-guided assistants, automation pipelines, and multi-step decision workflows.

Quick Start

Instantiate and compile a two-node graph that processes input and returns an uppercase result.

Frequently Asked Questions about langgraph-fundamentals

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I build agent workflows with conditional routing and parallel processing?▼

You build agent workflows by defining a StateGraph with nodes and edges, using conditional edges for routing logic and Send tasks for parallel processing. This approach enforces compile-before-run execution and partial-state updates to ensure safe workflow orchestration.

What is the best way to manage state in complex LangGraph agent workflows?▼

State management in LangGraph uses reducers and partial-state updates within a directed graph. This enables complex workflows to maintain runtime context effectively and apply targeted updates without overwriting the entire state object.

How do I route execution dynamically in a LangGraph directed graph?▼

Dynamic routing in a LangGraph directed graph is handled using conditional edges and the Command object. These mechanisms combine state updates with routing decisions to direct execution flow between nodes based on runtime data.

Can I execute parallel tasks simultaneously in LangGraph?▼

Yes, you can execute parallel tasks in LangGraph using the Send workload feature. This allows the directed graph to dispatch multiple node executions concurrently, enabling multi-step decision workflows and automation pipelines to process branches in parallel.

How does LangGraph prevent infinite loops during agent workflow execution?▼

LangGraph prevents infinite loops through compile-before-run guarantees and robust error handling. Compiling the graph before execution validates the routing logic, while partial-state updates and runtime context tracking ensure safe agent execution.

When do I need to use reducers in a LangGraph state graph?▼

Reducers are needed in a LangGraph state graph when workflows require complex state management. They process partial-state updates from parallel node executions, ensuring that concurrent branches merge state changes correctly without data loss.