​
What is the Agent Graph System?

The Agent Graph System (AGS) lets you define hierarchical constraints for your AI agents, controlling which operations they can use and in what order.

While agents can see all available operations, they must follow the workflow you define. This balances autonomy with predictable behavior.

​
Core Concepts

An agent graph consists of three simple components:

  1. Nodes - Individual operations (tools) your agent can use
  2. Connections - Define which operations must happen before others
  3. Hierarchical levels - Group operations by their position in the workflow

​
Example Agent Workflow that requires AGS

Let’s explore a practical example using a LinkedIn researcher agent to demonstrate why AGS is valuable: Users might ask:

“Find Person X on LinkedIn” And the agent should follow this specific sequence:

  1. First, use Tavily to search the internet for profile information
  2. Once profiles are found, use LinkedIn’s /search-people endpoint to get basic profile data
  3. Finally, retrieve full profile details using either:
    • /get-profile-data-by-url
    • Get Profile Data by Username and ID

Without AGS constraints, the agent attempted to skip the initial web search step by directly calling “LinkedInProfileServiceSearchProfilesByCriteria”, finding the wrong person. With AGS we can design a graph that enforces the correct sequence of operations without limiting the agent’s ability to make decisions.

We can see that the agent indeed attempted to skip the initial web search step by directly calling “LinkedInProfileServiceSearchProfilesByCriteria”. The xpander.ai platform detected this violation of the intended workflow and prevented the operation.

The agent then correctly used the Tavily operation to perform the required web search first:

This example shows how AGS enforces the correct sequence of operations, ensuring data is gathered methodically and reliably.

​
Implementation Methods

You can create agent graphs using either the visual UI or programmatically with the SDK.

The xpander.ai UI provides a drag-and-drop interface for creating agent graphs:

1

Access the Graph Builder

Navigate to your agent in the xpander.ai dashboard and select the “Graph” tab

2

Add Operations

Drag operations from the sidebar into your graph workspace

3

Create Connections

Draw lines between operations to establish dependencies

4

Test Your Graph

Use the interface options to test your agent with different invocation methods

5

Deploy

Save changes to deploy your updated graph

The visual builder gives you all the power of AGS without writing code, making it accessible to both developers and non-developers.

​
Troubleshooting & Best Practices

​
Next Steps

Now that you understand the Agent Graph System, you might want to explore: