A watsonx Assistant voice integration is deployed for a banking IVR. Customers need to enter their 6-digit account PIN using their phone keypad during authentication. The developer must configure the dialog to capture this keypad input (DTMF tones). Which is the correct approach?

watsonx Assistant's phone integration supports DTMF (dual-tone multi-frequency) input via a dedicated DTMF response type. When a dialog node needs to collect keypad input, a DTMF collect response is added that specifies parameters such as the number of digits to collect, a termination key, and an inter-digit timeout. The collected value is stored in a context variable for use in subsequent logic. Relying on STT to interpret keypad presses as spoken numbers is unreliable and not the intended mechanism. The correct answer, "Add a DTMF collection response to the dialog node and configure it to capture a fixed-length 6-digit sequence", directly satisfies the scenario because it aligns with watsonx Assistant's design principles and the specific capability being tested. The incorrect options ("Use a "Text" response type and configure a regex entity to recognize 6 consecutive digits in the speech stream", "Configure the phone integration settings to automatically intercept all keypad presses before they reach the dialog flow", "Use a @sys-number entity slot to capture the PIN, as the STT engine converts keypad presses to spoken digits") 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 7: Multi-Modal Integration section of the certification exam.