Verified against Claude · 2026-07-25
Turn raw FAQ content into schema and copy AI engines can cite
Turns rough Q&A content into answer-first visible copy and valid FAQPage JSON-LD, structured for AI engines that still parse FAQ schema even after Google retired FAQ rich results.
The prompt
Ready to copy — highlighted parts are example details you can swap.
You are an AEO (answer-engine-optimization) editor. Google retired FAQPage rich results on 7 May 2026, but AI answer engines (ChatGPT, Claude, Perplexity, Google AI Overviews) still parse FAQPage JSON-LD and still quote well-structured Q&A prose directly. Your job is to make this content easy for both to lift.
PAGE TOPIC: Return and refund policy for a DTC skincare brand
RAW Q&A:
Q: Can I return an opened product? A: Yes within 30 days if... Q: How long do refunds take? A: 5-7 business days...
TARGET ANSWER LENGTH: 300 characters (if blank, keep each answer under roughly 300 characters)
RULES FOR EACH ANSWER
- The first sentence is the complete direct answer — no "Great question," no throat-clearing.
- One claim per answer. If the raw content bundles two ideas, split it into two Q&A pairs.
- The answer must be understandable on its own, with no pronoun referring back to the question ("it," "this," "that") — restate the subject.
- Keep any numbers, timeframes, or conditions from the source content exactly as given — never invent or round them.
OUTPUT
1. The cleaned Q&A as answer-first visible copy (what a human reads on the page).
2. The equivalent schema.org FAQPage JSON-LD block, one Question/acceptedAnswer pair per Q&A, ready to paste inside a <script type="application/ld+json"> tag.Customize the highlighted detailsoptional — the prompt above already works
Why this works
An answer engine that retrieves a chunk of text and quotes it can only quote what stands alone — a chunk that opens with "It depends on..." with no restated subject is unusable out of context, which is why answer-first, pronoun-free single-claim answers are the retrievable unit, not a style preference. FAQPage schema still matters even though Google retired the FAQ rich result on 7 May 2026, because AI engines parse structured data independently of whether Google renders it as a visual snippet — it removes any ambiguity about what kind of content the block is. The never-invent-numbers rule matters because a rewrite optimized to "sound more specific" is otherwise a direct incentive to fabricate a figure that was never in the source.
What you get back
Q: Can I return an opened product? A: Yes — opened skincare products can be returned within 30 days of delivery for a full refund. Q: How long do refunds take to process? A: Refunds are issued within 5-7 business days of the returned item reaching our warehouse. ```json { "@context": "https://schema.org", "@type": "FAQPage", "mainEntity": [ { "@type": "Question", "name": "Can I return an opened product?", "acceptedAnswer": { "@type": "Answer", "text": "Yes — opened skincare products can be returned within 30 days of delivery for a full refund." } } ] } ```
Verified against
Claude Claude Sonnet 4.5 · 2026-07-25
Google AI Overviews Gemini 3.0 grounding · 2026-07-25
Changelog
- 2026-07-25 — Initial publish, dated to Google's 7 May 2026 FAQ rich-result retirement so the prompt explains why FAQ schema still matters instead of assuming it earns a visual Google rich result.
Building this for real?
This is a free starting point. If you'd rather have SEO built and running for your business, that's Scult's day job.
EXPLORE SEO
