Generative AI Leader Fundamentals of Generative AI Practice Question

Which TWO of the following are best practices for prompt engineering?

Answer choices

Why each option matters

Answer the question above first, then reveal the full breakdown to understand why each option is right or wrong.

Correct answer & explanation

✓

Provide context and examples in the prompt

Option A is correct because supplying relevant context and few-shot examples in the prompt grounds the model, clarifies the expected format and intent, and measurably improves output relevance and accuracy. Option C is correct because clear, specific instructions reduce ambiguity, constrain the model's response space, and yield more predictable, on-target results. Together, these two practices are widely recommended in prompt engineering guidance for both large language models and generative AI services. Option B does not belong because adding random noise degrades coherence and reliability rather than improving genuine creativity. Option D does not belong because maximizing token count wastes context window and cost without improving quality; concise, purposeful prompts are preferred. Option E does not belong because negative prompts are a feature specific to certain image-generation tools and are not a general best practice for prompt engineering across LLMs.

Answer analysis

Option-by-option breakdown

For each option: why learners choose it and why it is or isn't the right answer here.

✓
Provide context and examples in the prompt
Why this is correct
Supplying context and few-shot examples steers the model toward the desired output format and domain, reducing ambiguity. It satisfies the best-practise criterion by grounding responses in relevant information rather than relying on the model's parametric memory alone.
✗
Append random noise to prompts to improve creativity
Why it's wrong here
Random noise degrades prompt clarity and makes outputs non-reproducible, directly harming the precision prompt engineering requires. It is tempting because sampling temperature and top-p genuinely inject controlled randomness for creative tasks, so noise appears to serve the same goal; however, that mechanism belongs in decoding parameters, not the prompt text itself.
✓
Use clear and specific instructions
Why this is correct
Clear, specific instructions constrain the model's output space, reducing ambiguity that otherwise invites plausible but irrelevant completions. This satisfies the stem's demand for a best practise by directly improving response relevance and accuracy, since the model cannot infer unstated intent, format, or scope from vague phrasing.
✗
Always use the maximum possible number of tokens
Why it's wrong here
Padding prompts to the token ceiling wastes context, dilutes salient instructions and raises latency and cost without improving output quality. It is tempting because longer context windows and detailed few-shot examples can improve results, so more tokens looks beneficial; however, effective prompting targets sufficient, relevant tokens rather than the maximum the model accepts.
✗
Use negative prompts to discourage undesired outputs
Why it's wrong here
Negative prompts are not a reliable control mechanism for instruction-tuned LLMs; naming undesired content can prime the model toward it and consumes context. It is tempting because image-generation tools such as Stable Diffusion genuinely use negative prompts to exclude artefacts, so the technique appears transferable; however, that behaviour is specific to those diffusion pipelines, not text LLM prompting.

Go deeper

Generative AI Leader Fundamentals of Generative AI Practice Question

Why each option matters

Option-by-option breakdown

Related to this question