Question 32
Domain 3: Applications of Foundation ModelsAn education provider is building a question and answer application that uses a generative AI model to explain complex concepts. The education provider wants to automatically change the style of the model response depending on who is asking the question. The education provider will give the model the age range of the user who has asked the question. Which solution meets these requirements with the LEAST implementation effort?
Correct answer: B
Explanation
Prompt engineering is “the practice of crafting the text inputs sent to a model,” and a prompt can include “an instruction” and “context.” Adding a role description that states the user’s age range changes the response style without retraining the model, so it meets the requirement with the least implementation effort.
Why each option is right or wrong
A. Fine-tune the model by using additional training data that is representative of the various age ranges
Fine-tuning adjusts model weights on domain-specific data and is used when prompt changes are insufficient.
B. Add a role description to the prompt context that instructs the model of the age range that the response
Prompt engineering is the relevant mechanism here because the provider is only changing the instruction/context sent at inference time, not the model weights. Under the GenAI guidance, a prompt can include an instruction and context, and adding a role description that states the user’s age range is the least-effort way to steer style without fine-tuning or retraining, which would require additional data preparation and model customization overhead.
C. Use chain-of-thought reasoning to deduce the correct style and complexity for a response suitable for
Chain-of-thought is a reasoning technique, not a mechanism for selecting audience-appropriate style.
D. Summarize the response text depending on the age of the user so that younger users receive shorter
Summarization changes length, not necessarily tone, reading level, or audience-specific style.