A merchant about to submit product pages to richer search formats wants to know whether the schema would pass muster first. In this case, the immediate task is to check page schema against visible product facts. The workflow should verify required properties in the merchant's markup against on-page facts, noting which checks pass and which fixes need review.
First replace every [bracketed] placeholder with real store scope and constraints, then add any actual records or data you have, and paste it into your preferred AI assistant or Spark agent. Spark will follow this page's workflow to produce structured output and verification steps.
Act as a Shopify operations specialist.
Help me check page schema against visible product facts.
My store context is [describe the business, products and target audience].
My scope is [specify the affected products, pages, customers or reporting period]. Use these inputs: [the rendered page source for each URL, the structured-data types and properties extracted from it, and the visible product facts including variant, price with currency and availability at that URL].
Check each declared type for its required properties, confirm the values match those visible facts rather than only parsing, and mark a property that is present but empty as missing rather than correct.
Return a structured-data issue report and correction draft for the specified task.
Show the relevant evidence or before-and-after examples and explain how I can verify the result.
If essential data is missing, ask for it and mark unsupported conclusions as unknown.
Do not invent metrics, product claims or customer facts.
For any publication, message, account or store change, use only connected tools within my explicitly authorized scope and report success only after verification; otherwise provide the draft or proposed steps.Split the work into input, judgment, and deliverable phases. Verify each step's output before moving to the next.
Read the rendered page source, extract the structured-data blocks with the type each declares, and set beside them the product facts the page shows, including the variant, the price with its currency and the availability state visible at that URL.
Check each declared type for its required properties, confirm the values match those visible facts rather than only parsing, and mark a property that is present but empty as missing rather than correct.
Deliver a per-URL result listing passed checks, properties to correct and the draft replacement values, then re-extract the markup after correction and confirm the previously failing property now matches the page.
Cover decision rules, frequent misunderstandings, and required inputs so the team aligns on prerequisites before execution.
No. A block can parse and still describe the wrong product or a price the page never shows, so every value has to be read against the visible page before that check is called passed.
After any theme or template change, on the rendered page rather than the editor preview, because templates decide which properties are emitted and how each one is filled.
A variant page can show a different price or availability from the parent, so markup written only at product level may describe something a shopper at that URL cannot actually buy.
Start with scenarios under the same topic, then expand into cross-topic matches suggested by similarity.
Ciwi Spark builds Shopify-native AI tools and agents around the workflows merchants actually run: research, ads, translation, and customer support. Stop rewriting the same prompts by hand.