An engineer configuring conversational search wants to control how the LLM synthesizes its final response from retrieved document passages. Specifically, they need to add instructions about response tone and maximum length. Where should these instructions be placed?
Select an answer to reveal the explanation.
Short Explanation and Infographic
Todd Lammle: 'Imagine you're building a chatbot and this exact situation comes up — in the llm prompt configuration within the search integration settings is your go-to move. The LLM prompt configuration, accessible inside the search integration settings for conversational search, is the correct location for customizing how the model uses retrieved passages to generate a response. This is a classic Domain 4: Integrate with watsonx concept you'll want locked in before exam day.'
Full explanation below image
Full Explanation
The LLM prompt configuration, accessible inside the search integration settings for conversational search, is the correct location for customizing how the model uses retrieved passages to generate a response. Instructions placed here—such as tone guidance or length limits—are injected into the prompt at inference time alongside the retrieved content. The correct answer, "In the LLM prompt configuration within the search integration settings", directly satisfies the scenario because it aligns with watsonx Assistant's design principles and the specific capability being tested. The incorrect options ("In the action step's 'Assistant says' response field for each affected action", "In the webhook request body template used by the custom extension", "In the global system prompt under the assistant's profile page") 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.