LOCAL

Local FAQ from real customer questions

Use when you want FAQ content for a location page based on what customers actually ask rather than invented questions.

local-faq-from-real-questions.md

Download .md

Build an FAQ section for a local business page.

Business and service: {{BUSINESS_AND_SERVICE}}
Area: {{AREA}}
Questions customers actually ask us, pasted raw: {{REAL_QUESTIONS}}
Facts I can confirm (pricing, lead times, coverage, parking, access, guarantees, callout charges): {{CONFIRMED_FACTS}}

Produce twelve FAQs.

Sourcing rule: at least eight must come directly from my raw question list, rewritten into the phrasing a person would type or say. The remaining four may be gaps you identify, and you must label those [GAP] so I know they are your suggestions.

For each FAQ give:
- The question, in the customer's words, under 12 words
- An answer of 40 to 70 words that gives the actual answer in the first sentence
- A confidence line: Confirmed if it rests only on facts I supplied, or [NEEDS INPUT: exactly what to find out] if it does not

Constraints:
- Never answer a pricing, timing or coverage question with an invented figure. If I have not given the number, mark it needs input.
- Do not write questions whose only purpose is to repeat the service name and the area name together.
- Answer directly. Do not open with "Great question" or restate the question before answering.
- No em dashes. No summary paragraph at the end.

Then rank the twelve by how likely each is to affect an enquiry decision, and tell me which three to put at the top of the page.

Fill in before running

Replace each placeholder with your own detail. The more specific you are, the less the model invents.

{{BUSINESS_AND_SERVICE}}
{{AREA}}
{{REAL_QUESTIONS}}
{{CONFIRMED_FACTS}}

Getting a better result

Pull the raw questions from your inbox, call notes or live chat rather than guessing what people ask.
Answer-first phrasing is what gets pulled into search results, so do not let the model bury the answer in sentence two.
Only mark up as FAQ schema the questions that genuinely appear on the page.

Questions about this prompt

When should I use this rather than generating FAQs from a keyword tool?

Whenever you have real questions to work from. FAQ blocks invented from search volume answer things nobody asks and read like it. This enforces the difference: at least eight of the twelve must come from {{REAL_QUESTIONS}}, and anything the model adds itself is labelled [GAP] so you can tell them apart.

What do I need before running it?

Raw questions pulled from your inbox, call notes or live chat and pasted unedited, plus {{CONFIRMED_FACTS}} covering pricing, lead times, coverage, parking, access, guarantees and callout charges. Any figure you do not supply comes back marked [NEEDS INPUT] rather than invented, which is the behaviour you want on price and timing.

What does it produce?

Twelve FAQs, each with a question under 12 words, a 40 to 70 word answer that gives the answer in the first sentence, and a confidence line. Then a ranking by likely effect on an enquiry decision and three to put at the top of the page. Act on that ranking.

What is the mistake specific to this one?

Letting the answer drift into sentence two while tidying the copy. Answer first phrasing is what gets pulled into search results and it is the first thing an editor undoes. The other one is marking up all twelve as FAQ schema when only the three you promoted actually appear on the page.