AI engineering glossary · Agents tools MCP
What is state graph?
State graph (also called Agent graph): A way to build an agent as nodes, which are steps such as model calls or tool runs, connected by edges that decide what comes next, with a shared state passed along. It gives explicit control over loops, branches and pauses.
State graph: an example
A graph has nodes 'plan', 'search' and 'write'; an edge from 'search' loops back to itself until enough sources are found.
Related terms
More Agents tools MCP terms
- stdio transport
- Stop condition
- Streamable HTTP
- Subagent
- Supervisor agent
- Task success rate
- Thought-action-observation
- Tool argument validation
Where you learn it
State graph is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.