An engineer wants to enable watsonx Assistant to answer unstructured questions by searching a connected Elasticsearch index of company documents. Which watsonx Assistant feature should the engineer configure?

watsonx Assistant's Conversational Search feature connects to supported search back-ends including Elasticsearch, Watson Discovery, and Milvus. Once configured through the Integrations panel the assistant automatically retrieves passages and synthesises a grounded response using a foundation model — no custom webhook code is required for the retrieval step itself. The correct answer, "Enable Conversational Search and point it at the Elasticsearch data source through the Integrations panel", directly satisfies the scenario because it aligns with watsonx Assistant's design principles and the specific capability being tested. The incorrect options ("Create a custom action that calls the Elasticsearch REST API via a webhook on every user turn", "Import the Elasticsearch OpenAPI spec as a dialog skill and map intents to index queries", "Configure a pre-message webhook that rewrites every user query as an Elasticsearch DSL JSON body") may appear relevant but each misses a key requirement or introduces a step that is either unnecessary or belongs to a different workflow. 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.