thinkhard.SI

Prompt repository Marketing

Write product page FAQs from the questions that stop shoppers buying

Shoppers ask the same things before they buy, or return items for reasons a clear answer would prevent, and you want an FAQ section for the product page.

Registry no.
MKT-081
Collection
Marketing
Laid out for
Any chat model
Score
10 out of 10
Blanks to fill
6

MarketingAny chat

The prompt

Score 10 of 10, Excellent

Use it when Shoppers ask the same things before they buy, or return items for reasons a clear answer would prevent, and you want an FAQ section for the product page.

  • {{product}}
  • {{question_range}}
  • {{policies}}
  • {{product_facts}}
  • {{presale_questions}}
  • {{return_reasons}}
Full prompt and why it works
Prompt
Write an FAQ section for the product page of {{product}} in our online shop. It is for shoppers who are close to buying but have a doubt, so that they find the answer on the page instead of leaving or buying the wrong thing and sending it back.

How many questions: {{question_range}}
Our policies that apply (shipping times and costs, returns, exchanges, warranty), as written: {{policies}}

Product facts (specs, sizes, materials, what is included, compatibility, care):
"""
{{product_facts}}
"""

Questions shoppers have asked before buying (from chat, email, marketplace questions, sales staff):
"""
{{presale_questions}}
"""

Return and complaint reasons for this product, if we track them:
"""
{{return_reasons}}
"""

Produce:
1. The questions and answers, chosen by how often they come up and how likely they are to stop a sale or cause a return. Phrase each question the way shoppers asked it.
2. Answers of one to three sentences, starting with the direct answer ("Yes", "No", a number or a size), then the detail.
3. A note on any question better answered in the product description itself, such as sizing, with a suggested line for the description.
4. A list of questions you could not answer from our facts, for me to fill in.

Format: Markdown, with each question as a bold line and its answer below it.

A good FAQ answers doubts honestly, including the "no" answers: a shopper who learns before buying that the product will not fit is better for us than a return.

For example, an answer in the right form: "Does it fit a standard [size] shelf? No. It is [measurement] deep, so it needs a shelf at least [measurement] deep." That example shows the form only.

Do not invent specs, compatibility, delivery times or guarantees, and quote policies only as written. Avoid sales language in the answers, and questions nobody asks, such as "Why is this product so great?". Leave out any question about safety or medical use unless our facts answer it, and list it for me instead. If two sources disagree, for example the specs and a policy, flag it with [CHECK] instead of choosing one.

Variables

{{product}}
The product's name, as it appears on the page.
{{question_range}}
How many questions, for example "6 to 10".
{{policies}}
Your shipping, returns, exchange and warranty policies, copied as written.
{{product_facts}}
Every fact about the product: specs, sizes, materials, what is in the box, compatibility, care.
{{presale_questions}}
Real questions shoppers have asked before buying, copied or summarized.
{{return_reasons}}
Why people return or complain about this product. Write "none tracked" if you do not track them.

Why it works

  • Background facts. Questions come from what shoppers really asked and why they returned the product, ranked by how likely each is to stop a sale.
  • What good looks like. Answers start with a direct yes, no, number or size, and honest "no" answers are kept, since a lost sale costs less than a return.
  • If unsure. Questions the facts cannot answer, including safety and medical ones, are listed for you, and conflicting sources are flagged with [CHECK].

How to use it

  1. Press Fill in blanks and type your details into each blank. What you type stays in this browser.
  2. Copy the filled prompt into the AI tool you already use, such as ChatGPT, Claude or Gemini, or open it in the Grader or the Prompt Tester here.
  3. Before you rely on it, try it on three or four real examples. The Prompt Tester runs them all at once and shows which ones go wrong.
  4. When the answer comes back, check it before you use it. The Fact Check List lists every figure, quote and source in the answer worth checking, riskiest first.
Use it from code

Get this prompt as JSON from the free REST API, with your own text in the blanks, or let an AI assistant fetch it through the MCP server. No key.

curl -s https://thinkhard.si/api/v1/prompts/product-page-faqs-from-shopper-questions

With the MCP server added to Claude, ChatGPT, Cursor or VS Code, call get_prompt with {"prompt": "product-page-faqs-from-shopper-questions"}, or just ask for it by name.