Step 1
Pull each product's current description, the verified attribute record, and the list of factual claims such as measurements, materials and compatibility statements that must survive the rewrite unchanged.
Descriptions were written at different times and read unevenly, but the product facts in them are correct. In this case, the immediate task is to rewrite existing descriptions without changing product facts. The workflow should produce before and after copy with a note on material changes, rechecked against the verified attributes.
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 rewrite existing descriptions without changing 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: [current descriptions, verified attribute records, and the protected factual claims list per product]. Rewrite only the wording, structure and tone while carrying every protected claim over verbatim, and mark any passage whose meaning is ambiguous enough that two honest rewrites would state it differently.
Return before and after copy with a note on material changes, rechecked against the verified attributes 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.
Pull each product's current description, the verified attribute record, and the list of factual claims such as measurements, materials and compatibility statements that must survive the rewrite unchanged.
Rewrite only the wording, structure and tone while carrying every protected claim over verbatim, and mark any passage whose meaning is ambiguous enough that two honest rewrites would state it differently.
Deliver before-and-after copy side by side with a material-changes note, then verify each after-text by extracting its factual claims and matching them one-to-one against the protected list from the original.
Cover decision rules, frequent misunderstandings, and required inputs so the team aligns on prerequisites before execution.
Any difference that alters meaning, ordering of facts or the presence of a claim, as opposed to pure wording; the note exists so a reviewer can approve the rewrite without re-reading both texts in full.
Comparing claim lists catches silent omissions that proofreading misses, since a rewrite that drops one compatibility sentence still reads smoothly; a one-to-one match against the protected list is the evidence nothing was lost.
They are marked for the merchant rather than smoothed over, because a rewrite that resolves ambiguity by choosing an interpretation is effectively adding a product fact nobody verified.
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.