Answer: Context enrichment

## Explanation **Context enrichment** is the correct answer because: 1. **Definition**: Context enrichment involves adding relevant information or context to prompts to improve the AI model's understanding and generate more accurate responses. 2. **Application in this scenario**: The developer is including excerpts from the company's policy document directly in the prompts. This provides the AI model with specific, relevant information it needs to answer policy-related questions consistently and accurately. 3. **Why other options are incorrect**: - **A) Zero-shot prompting**: This refers to asking the model to perform tasks without providing any examples. The developer is actually providing context, so this isn't zero-shot. - **C) Negative prompting**: This involves telling the model what NOT to do, which isn't what's happening here. - **D) Temperature adjustment**: This refers to adjusting the randomness/creativity of responses, not adding contextual information. 4. **Best practice**: By enriching prompts with relevant context (policy document excerpts), the developer ensures the AI model has the specific information needed to provide consistent, accurate answers to policy-related questions, which is a key best practice in prompt engineering.

Author: Ritesh Yadav