The next generation of enterprise AI is not just about answering questions – it is about enabling intelligent agents to interact with real business systems, retrieve contextual information, and trigger meaningful actions. While conversational intelligence creates a compelling user experience, the true value of an AI agent emerges when it can securely connect to external services and operational data sources.
Oracle Fusion AI Agent Studio extends this capability by allowing organizations to integrate AI agents with external tools and services through APIs. Among the available integration patterns, calling an external REST API is one of the most practical and powerful approaches for extending agent functionality beyond the boundaries of Oracle applications.
By invoking external REST endpoints, organizations can enable AI agents to access third-party platforms, retrieve real-time business information, integrate with internal enterprise services, or orchestrate actions across a broader technology landscape. Whether it is fetching customer insights from a CRM system, validating business data from an external platform, or triggering downstream workflows, API connectivity transforms an AI agent from a conversational assistant into an actionable enterprise participant.
The business value is significant. Instead of building isolated AI experiences tied to a single application ecosystem, enterprises can create connected, scalable and reusable AI solutions that operate across systems. This reduces manual effort, accelerates decision-making, and allows businesses to leverage existing digital investments without extensive custom development.
However, enterprise integration is not just about connectivity. It is equally about security, governance and trust. External API consumption in an enterprise AI environment must operate within well-defined security boundaries. Oracle Fusion AI Agent Studio supports controlled API interactions through authenticated connections, managed credentials, and governed configurations, helping organizations maintain compliance, protect sensitive business data and ensure that agent actions remain observable and manageable.
In this blog, we will explore how to call an External REST API from Oracle Fusion AI Agent Studio, walk through the configuration steps involved, and demonstrate how secure API integrations can unlock more intelligent, business-ready AI agent experiences.
For this demonstration, I will be using the Catalitium Jobs & Salary API, to fetch average market salaries based on the Job Title and Country entered by the users. This is a publicly accessible API and does not require authentication. I will be making an HTTP GET request to this endpoint. You may sign up for a free API key if you need to authenticate REST API calls. The endpoints exposed for REST calls are shown below.
For this demonstration, I will use the Salary snaphsot GET endpoint.
Before I begin, I made sure that the API returns the output payload as expected, using Postman.
On a high-level, the steps involved are as follows:
1. Create an External REST API Tool
2. Create an Agent Team
3. Create an Agent
4. Publish AI Agents
So let us crack on!!!
Create Tools
To create the Tool, login to Oracle Fusion instance and navigate to Tools > AI Agent Studio. From the navigation-pane at the bottom, click on Tools.
Click on Add.
From the dropdown list, select Tool Type as ‘External REST’.
Type in a Tool Name. Tool Code should auto-populate from the tool name you enter. Enter a Description. Select the Product Family and Product. For this example, I’ll select HCM and Compensation respectively.
In the Authorization section, we will need to add the authentication details for the REST API. Click Add.
Enter the Instance URL. The instance URL will be the base domain for making the REST call. It is important to note that when entering the base domain of the external API, you should not include any paths, parameters, or trailing slashes. In out case this will be:
https://www.catalitium.com
Enter the Instance URL.
Under Authentication, define how your agents will authenticate with the external system. You can choose from the available list of authentication methods supported by the external API you are using. However, in our case, no authentication is required, so I would select None.
Next we need to configure the endpoint. To do that, navigate to the Functions sub-tab.
In the Add Endpoint page, enter the Name of the endpoint. Enter the Operation Type. In our case, we will be using HTTP GET operation. Under Resource Path, specify the relative resource path to be appended to the Instance URL. Don’t include the protocol or base domain. In our case, it will be:
/v1/salary?title={title}&country={country}
Add a Description.
Next we will be adding the input parameters. Scroll-down to the parameter section, and click on Add.
For the endpoint we are using, we need to add two parameters – Job Title and country. We add the first parameter and Save.
We add the second parameter and Save.
In the Sample Queries subtab, list example user queries that should trigger this tool. Click Add.
Add the sample user query and Save.
In the Headers subtab, specify any required metadata and security credentials for the external server. In our case, we need to specify the API-Key to authenticate the REST API request, according to the instructions you receive upon registration. Click Add.
Enter the API-Key and click Save.
That completes configuring the Endpoint. Click Add.
Click Create to complete the External REST Tool setup.
The External REST tool we created will be listed in the Tools Library.
Create Agent Team
Next step is to create the AI Agent Team. To create the AI Agent Team, navigate to the Agent Teams tab.
Click on the Add(+) button.
Under the Details tab, provide a Name for your Agent Team. Agent Team Code should auto-populate. Under Family, select the pillar in which you want to create the Agent in. Select the Product. For this demonstration, I have used HCM and Compensation for the Family and Product respectively. Since we are creating a supervisor agent, I will select the agent Type as Supervisor. Add a Description.
Under the LLM tab, you can select the Large Language Model you want to use for NLP. You can chose to use the default model(GPT-4.1 Mini). Note that this model is free to use.
Or you can chose from the list of other available LLMs. Note that there might be additional charges to use these models. I would highly recommend checking with your Oracle CSM on the usage costs, in case you want to use any of these models.
If you are using one of the paid models, you have the flexibility to restrict the usage.
Under the Security tab, you can specify who should have access to use this Agent Team. If you want to make this Agent Team available for all employees, make sure you enable ‘For all employees’ option.
Click on Create to create your Agent Team.
Add Agent to the Agent Team
Once you have created the Agent Team, next step would be to create the Agent. From the tools panel on the left, click on Agents, as highlighted in the screenshot below. Then click on New Worker Agent, as we want to create a worker agent for this demo. Based on your requirement, you can also chose to add a Supervisor Agent.
The Agent creation panel pops up. Enter the Agent Name, Agent Code, Family and Product. Enter a Description for the Agent.
Use the Agent Persona and Role to set the character profile(tone, style, attitude, and behavioral patterns) of the agent.
Use Prompt section to instruct the agent about its tasks, roles and responsibilities. Add guidelines for agent responses.
I will leave default values for remainder of the tabs and click on Create. This will create the Agent. Note that we are yet to add our tool to the agent.
To add the tool, select Tools. From the left-hand pane, search for the tool that you created earlier, and add the tool. Click Add.
The tools window pops up. Click Add. Repeat these steps if you want to add more tools to the agent.
Notice that our tool has been added.
Next step is to publish the agent team. However, before publishing the agent team and making it available for business users, make sure to test the agent team using the Debug button.
Publish Agent Team
To publish the agent team, click on the Publish button on the top-right-hand corner.
You should be able to verify the status from the Agent Teams page. Note that since we have created the Agent Teams from scratch, it has been tagged as a Custom Agent Team.
There you go, we have successfully created a custom AI Agent that calls an External REST API using Oracle AI Agent Studio.
Few Gotchas (Postman vs, Oracle AI Agent Studio)
Every Postman setting has a direct equivalent in Oracle AI Agent Studio. I want to call out each of these mappings in the table below. Please keep these in mind when configuring the External REST Tool in Oracle AI Agent Studio.
| Component | Postman | Oracle AI Agent Studio |
| URL | Enter full URL in the address bar | Split into two: i. Authorization subtab: Base URL ii. Function: Resource Path |
| Method | Select from Method Dropdown | Operation dropdown inside Function |
| Authorization | Setup in Auth tab | Setup in the Authorization sub-tab under Tools. |
| Headers | Setup under Headers | Setup in the Headers tab under Functions sub-tab under Tools. |
| Parameters | Under Params | Parameters sub-tab when configuring the Endpoint. |
| Send | You can inspect the JSON response | The LLMs parses the JSON response. |
Hope this was helpful. Happy Learning.
References
Leave a Reply