---
sourceDocument: Australia Enable AI
sourceDocumentLink: https://www.servicenow.com/docs/r/australia/intelligent-experiences

 Release :

    - australia

ft:locale :

    - en-US

ft:publication_title :

    - Australia Enable AI

ft:clusterId :

    - platai

bundleId :

    - platai

workflow :

    - Platform


---

# Knowledge Graph integration with AI agents

# Knowledge Graph integration with AI agents {#ariaid-title1}

Release version: Australia  
Updated March 12, 2026  
![](https://www.servicenow.com/docs/portal-asset/ico-clock) 2 minutes to read
Summarize  
![AI sparkle icon](https://servicenow.com/docs/portal-asset/ai-sparkle-icon) Summarized using AI  
This content was generated using new OpenAI-powered functionality. Results are provided on an as is basis and are not guaranteed to be accurate or complete.  

## Summary of Knowledge Graph integration with AI agents

ServiceNow's Knowledge Graph integration with AI agents enhances live agent productivity by enabling AI to perform tasks and answer user queries more effectively.
The integration leverages user context and task-specific tools, providing personalized and permission-aware responses without requiring extensive manual input.
Show full answer Show less  

## Key Features

* **Integration for User Context:** Utilizes data from the prebuilt User Profile schema to fetch relevant user information such as name, location, contact details, and occupation. This allows AI agents to deliver personalized responses and reduce the need for users to fill in multiple details.
* **Integration as a Tool:** Knowledge Graph functions as a reusable operation within AI agents, enabling task automation without coding. For example, an Asset Manager agent can retrieve and manage assets assigned to users by querying the Knowledge Graph.
* **Knowledge Graph API Output:** AI agents query the Knowledge Graph to retrieve detailed and structured information, including table names, column data, and unique identifiers (sysId), to accurately respond to user queries such as identifying a manager's name.

## Key Outcomes

* Improved AI agent efficiency through contextual, permission-aware data retrieval.
* Streamlined task execution within AI agents by using Knowledge Graph as a tool, reducing the need for custom coding.
* Enhanced user experience with personalized assistance and accurate, data-driven responses from AI agents.  
The prebuilt integrations of Knowledge Graph, improve live agent productivity by assisting AI agents in performing tasks and answering user queries.

In this release, the available prebuilt integrations with AI agents are:

1. Integration with AI agents for User Context: Helps users with personalized responses.
2. Integration with AI agents as a tool: Used to perform specific tasks that are assigned to the AI agents.

{#leverage-knowledge-graph-prebuild-integration-with-agentic-ai__ol_fdm_tvh_cfc}

## Integration with AI agents for User Context {#leverage-knowledge-graph-prebuild-integration-with-agentic-ai__section_k5x_5vh_cfc}

ServiceNow AI agents integrates the context from the prebuilt User Profile schema to fetch relevant data and provide personalized responses.

By using relationships between users, teams, and content, AI agents can fetch relevant, permission-aware user information and provide answers to reduce slot-filing requirement.

Here's an example use case of how Knowledge Graph is used within AI agents for user context.  
* A user needs assistance in writing their resume, so they use ServiceNow AI agents called Resume builder.
* The user ads their task: <kbd class="ph userinput">Build my resume</kbd>.
* AI agents uses Knowledge Graph to fetch the following information from the user profile schema:
  * First name
  * Last name
  * Location
  * Email ID
  * Phone number
  * Occupation
  {#leverage-knowledge-graph-prebuild-integration-with-agentic-ai__ul_nxm_bbj_cfc}
* AI agents reverts with the available information and request for the missing information to proceed building the resume.
* Once the agent as all the required information, it provides user with output.
{#leverage-knowledge-graph-prebuild-integration-with-agentic-ai__ul_ql4_d1j_cfc}

## Integration with AI agents as a tool {#leverage-knowledge-graph-prebuild-integration-with-agentic-ai__section_ljt_5vh_cfc}

Knowledge Graph can now be used as a tool within AI agents. Users can choose Knowledge Graph to perform tasks, while creating an Agent.

You can define the flow action to use Knowledge Graph as a reusable operation in automating the ServiceNow AI Platform features without having to write code.

See [Add a Knowledge Graph to an AI agent](https://www.servicenow.com/docs/leMdG0tc9UbMUgUwe9txWA "Add a Knowledge Graph to an AI agent in AI Agent Studio that uses the structured and unstructured data from different ServiceNow records to enhance the performance of AI agents.") to add Knowledge Graph to an AI agents in AI Agent Studio.
Example use case:

* A user wants to view and retire all the assets assigned to another user. To execute this task, user will use Asset Manager agent.
* Asset Manager uses Knowledge Graph to fetch the asset information related to the user.
* After processing the query, the agent provides the following output:User has the following assets:1.\<asset1\> 2.\<asset2\> 3.\<productID\>- \<asset 3\> \<purchase date\>. The email address for the user is \<emailId\> and username \<username1\>.
* User then proceeds with the task of retiring the assets: <kbd class="ph userinput">Proceed with retiring the assets associated with Username1.</kbd>
* The next tool, used execute this task, will take the table name and sysId displayed in Knowledge Graph output and proceed with the task.
{#leverage-knowledge-graph-prebuild-integration-with-agentic-ai__ul_m5c_tnm_cfc}  

## Knowledge Graph API output in AI agents {#leverage-knowledge-graph-prebuild-integration-with-agentic-ai__example_owp_flq_dfc}

When a user ask a query <kbd class="ph userinput">What is my Manager's name? </kbd>, AI agents reaches out to Knowledge Graph to fetch this information. Here's an example output of the query:

    { 

        "Manager": [ 

            { 

                "sys_user": { 

                    "user_name": { 

                        "value": "abel.tuter", 

                        "displayValue": "abel.tuter" 

                    }, 

                    "sysId": "62826bf03710200044e0bfc8bcbe5df1", 

                    "name": { 

                        "value": "Abel Tuter", 

                        "displayValue": "Abel Tuter" 

                    }, 

                    "first_name": { 

                        "value": "Abel", 

                        "displayValue": "Abel" 

                    }, 

                    "last_name": { 

                        "value": "Tuter", 

                        "displayValue": "Tuter" 

                    } 

                } 

            } 

        ] 

    } 

In this example, the table that is called is `sys_user` and column referred is `user_name`. The output also displays sysId, example: `"sysId":
"62826bf03710200044e0bfc8bcbe5df1"`.