A Generative AI extension system prompt says 'You are a helpful insurance agent. Only answer insurance coverage questions.' What is the effect?
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 — the model is instructed to constrain its responses to insurance topics; steering away from off-topic answers is your go-to move. System prompts provide the model with persistent role and scope instructions. This is a classic Domain 4: Integrate with watsonx concept you'll want locked in before exam day.'
Full explanation below image
Full Explanation
System prompts provide the model with persistent role and scope instructions. The model will attempt to stay on topic and decline or redirect off-topic questions. The system prompt does not gate intent detection; does not reject messages at the API level; and does not auto-generate documents. The correct answer, "The model is instructed to constrain its responses to insurance topics; steering away from off-topic answers", directly satisfies the scenario because it aligns with watsonx Assistant's design principles and the specific capability being tested. The incorrect options ("The extension only fires on insurance-related intents", "The extension rejects messages without the word insurance", "The model auto-generates insurance policy documents") 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.