Step 1
Collect the candidate products with the change proposed for each, the record cited as its evidence, the fields the merchant allows to change, and the value currently stored in each of those fields.
A catalog review produced a long list of possible improvements, only some backed by records the merchant holds. In this case, the immediate task is to prepare a batch of evidence-based catalog improvements. The output should be a ranked change preview that keeps the supported improvements and drops the rest, verified against the merchant's own records.
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 prepare a batch of evidence-based catalog improvements.
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 candidate products with their proposed changes, the record cited as evidence for each, the fields the merchant allows to change, and the current value stored in each of those fields]. Keep a change only where the cited record shows a concrete defect such as a missing attribute, a value contradicting another record or an internal inconsistency, and drop every improvement resting on a belief about what performs better.
Return a bulk change preview and exception report verifying each improvement against the merchant's records 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.
Collect the candidate products with the change proposed for each, the record cited as its evidence, the fields the merchant allows to change, and the value currently stored in each of those fields.
Keep a change only where the cited record shows a concrete defect such as a missing attribute, a value contradicting another record or an internal inconsistency, and drop every improvement resting on a belief about what performs better.
Deliver the ranked preview with the supporting record named for each change and the dropped items listed with their reason, confirm each proposed value against the current record, and flag fields the export does not contain at all.
Cover decision rules, frequent misunderstandings, and required inputs so the team aligns on prerequisites before execution.
An evidence-based change points to a record showing a defect, such as a blank required attribute or two records disagreeing; a preference says a field should read differently with no record behind it.
By how firmly the records support a change and how many products it touches, so defects visible in the data are cleared before cosmetic rewrites that no record actually requires.
They are listed with the reason they were dropped, usually the absence of a supporting record, so the merchant can supply the missing data and rerun the pass instead of losing the idea.
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.