Explanation

This scenario describes Retrieval-Augmented Generation (RAG), which is a contextual prompting approach. Here's why:

Key Characteristics of RAG:

• External Knowledge Retrieval: The system retrieves relevant information from an external source (S3 bucket containing company handbook)
• Context Integration: Retrieved policy paragraphs are included in the prompt before generating the answer
• Dynamic Context: The model uses up-to-date, specific information rather than relying solely on its pre-trained knowledge

Comparison with Other Options:

• A) Few-shot Prompting: Involves providing examples in the prompt, not retrieving external documents
• C) Zero-shot Prompting: No examples or external context provided - just the question
• D) Chain-of-Thought Prompting: Focuses on step-by-step reasoning, not document retrieval

Why RAG is Ideal for This Use Case:

1. Accuracy: Ensures answers are based on the latest company policies
2. Scalability: Can handle large document repositories
3. Maintainability: Policies can be updated in S3 without retraining the model
4. Transparency: Shows which specific policy sections were used for the answer

This approach is particularly valuable for HR systems where policy accuracy and compliance are critical.