An engineer needs to connect watsonx Assistant to IBM watsonx.ai so the assistant can invoke a foundation model for generating responses. Which configuration step is required inside the watsonx Assistant interface?
Select an answer to reveal the explanation.
Short Explanation
Todd Lammle: When you need watsonx Assistant to call a foundation model in IBM watsonx.ai, you'll create a custom extension from the watsonx.ai OpenAPI specification and supply the API key and project ID. That's the required setup inside the assistant, not a connector, toggle, or proxy.
Full Explanation
Connecting watsonx Assistant to IBM watsonx.ai requires adding a custom extension built from the watsonx.ai REST API's OpenAPI specification. During setup, the engineer provides an IAM API key and the watsonx.ai project ID so the assistant can authenticate and invoke foundation models. There is no built-in toggle or App Connect pathway that replaces this step. Creating a custom extension using the watsonx.ai OpenAPI specification and supplying the API key and project ID directly satisfies the scenario because it aligns with watsonx Assistant's design principles and the specific capability being tested. Installing the watsonx.ai connector from the IBM App Connect Enterprise catalog is wrong because it introduces a different integration workflow and does not represent the required configuration inside watsonx Assistant. Enabling a Foundation Model toggle in the dialog skill's advanced settings panel to skip authentication is wrong because no such toggle replaces the required OpenAPI extension and authentication details. Deploying a webhook endpoint that proxies all requests to the watsonx.ai REST API is wrong because it adds an unnecessary external proxy layer rather than configuring the assistant's native custom extension. Mastering the distinction between these approaches is essential for effective watsonx Assistant implementations and is a core focus of the Domain 4: Integrate with watsonx section of the certification exam.