Q69 — AWS AIF-C01 Ch.3

Question 69 of 100 | ← Chapter 3

An ML engineer has deployed a foundation model (FM) and wants to adapt the FM’s response format. The ML engineer wants to implement a technique to adapt the FM’s response format. Which technique will most cost-effectively meet these requirements?

• A. Retrieval-Augmented Generation (RAG)
• B. Prompt engineering ✓
• C. Feature engineering
• D. Fine-tuning

Correct Answer: B. Prompt engineering

Explanation

In machine learning, prompt engineering is an effective method for adapting a model’s response format. It focuses on optimizing input prompts to improve model performance and satisfy specific business needs — such as formatting responses — and is typically more cost-effective than retraining or complex feature engineering. Retrieval-Augmented Generation (RAG) enhances content relevance and quality but does not primarily target response formatting. Feature engineering optimizes input features rather than output format. Fine-tuning adjusts model parameters for new tasks or datasets but is generally less cost-effective than prompt engineering for simple response-format adaptation. Therefore, prompt engineering is the most cost-effective technique for meeting the stated requirement.