LangGraph
A framework built on LangChain for creating stateful, multi-step agent workflows as directed graphs. LangGraph gives developers fine-grained control over agent state, branching logic, and cycle handling.
LangGraph models agent workflows as graphs where nodes represent actions or decisions and edges represent transitions between them. Unlike simpler agent loops, LangGraph supports complex control flow including conditional branching, parallel execution, cycles, and human-in-the-loop interruptions. State is explicitly managed and persisted, enabling long-running workflows that can pause and resume.
For engineering teams building production agent systems, LangGraph provides the control and observability that simpler frameworks lack. You can define exactly when an agent should loop, branch, or wait for human input. The graph structure makes workflows visual and testable. LangGraph also integrates with LangSmith for tracing and debugging. The tradeoff is complexity: defining graphs requires more upfront design than a simple ReAct loop. Use LangGraph when your workflow has non-trivial control flow, needs persistent state across sessions, or requires deterministic routing between agent steps.
Related Terms
Model Context Protocol (MCP)
An open standard that defines how AI models connect to external tools, data sources, and services through a unified interface. MCP enables agents to dynamically discover and invoke capabilities without hardcoded integrations.
Tool Use
The ability of an AI model to invoke external functions, APIs, or services during a conversation to perform actions beyond text generation. Tool use transforms language models from passive responders into active problem solvers.
Function Calling
A model capability where the AI generates structured JSON arguments for predefined functions rather than free-form text. Function calling provides a reliable bridge between natural language understanding and programmatic execution.
Agentic Workflow
A multi-step process where an AI agent autonomously plans, executes, and iterates on tasks using tools, reasoning, and feedback loops. Agentic workflows go beyond single-turn interactions to accomplish complex goals.
ReAct Pattern
An agent architecture that interleaves Reasoning and Acting steps, where the model thinks about what to do next, takes an action, observes the result, and repeats. ReAct combines chain-of-thought reasoning with tool use in a unified loop.
Chain of Thought
A prompting technique that instructs the model to break down complex problems into sequential reasoning steps before producing a final answer. Chain of thought significantly improves accuracy on math, logic, and multi-step tasks.