GENERATIVE-AI-LEADER · Question #21
A marketing team wants to use a generative AI model to create product descriptions for their new line of eco-friendly water bottles. They provide a brief prompt stating, "Write a product description…
The correct answer is B. Add details to the prompt about the audience, tone, and keywords. The model generated a generic description because the prompt was too vague-it lacked audience context, brand tone, and key differentiating keywords. Prompt engineering by adding specifics (e.g., target audience: eco-conscious consumers; tone: inspiring and urgent; keywords…
Question
A marketing team wants to use a generative AI model to create product descriptions for their new line of eco-friendly water bottles. They provide a brief prompt stating, "Write a product description for our new water bottle." The model generates a generic, lackluster description that is factually accurate but lacks engaging language and doesn't highlight the environmental benefits that are key to their brand. What should the marketing team do to overcome this limitation of the generated product description?
Options
- ATrain the model on a dataset of marketing materials from other eco-friendly brands.
- BAdd details to the prompt about the audience, tone, and keywords.
- CIncrease the token count for the model to allow for longer descriptions.
- DLower the temperature setting of the model to produce more consistent results.
How the community answered
(30 responses)- A10% (3)
- B80% (24)
- C3% (1)
- D7% (2)
Explanation
The model generated a generic description because the prompt was too vague-it lacked audience context, brand tone, and key differentiating keywords. Prompt engineering by adding specifics (e.g., target audience: eco-conscious consumers; tone: inspiring and urgent; keywords: sustainable, BPA-free, ocean-bound plastic) directly guides the model to produce relevant, engaging output. Option A (fine-tuning on other brands' data) is expensive, slow, and raises IP concerns-overkill for a prompt issue. Option C (increasing token count) only affects response length, not quality or relevance. Option D (lowering temperature) makes output more conservative and deterministic, which would likely make descriptions even more generic, not more compelling.
Topics
Community Discussion
No community discussion yet for this question.