A batch of product and page copy is due, and the drafts so far mix supported wording with claims nothing backs. In this case, the immediate task is to generate a coordinated batch of store content. The output should fill only the destination fields supplied and leave unsupported fields clearly marked.
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 generate a coordinated batch of store content.
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 source material behind the batch, the templates and their field lists, the destination fields per content type, the requested batch size, the merchant's terminology and review rules, and the fields refusing generated text].
Draft each piece so it fills only destination fields that were supplied and stays inside the length each destination accepts, leaving unsupported fields visibly flagged instead of filled with inferred values, and assigning one intended topic per piece so two drafts never chase the same search.
Return a content workflow and sample output batch verifying each draft 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 source material behind the batch, the templates and their field lists, the destination fields to fill per content type, the batch size requested, the merchant's terminology and review rules, and the fields the merchant refuses generated text for.
Draft each piece so it fills only destination fields that were supplied and stays inside the length each destination accepts, leaving unsupported fields visibly flagged instead of filled with inferred values, and assigning one intended topic per piece so two drafts never chase the same search.
Deliver the sample output batch alongside the workflow, with every row naming the fields filled, the fields flagged and the source behind each claim, verify that the row count matches the requested batch size, and list any piece held waiting for merchant input.
Cover decision rules, frequent misunderstandings, and required inputs so the team aligns on prerequisites before execution.
Into the merchant's review path, since the routing rule rather than the generator decides what publishes. Every piece therefore leaves the batch carrying a stated next status and the reviewer responsible for clearing it before anything reaches the store.
The field stays flagged and empty, because an invented value cannot be traced to anything and later reads as authoritative. The batch records which source records were missing that value, so the gap can be closed before the next scheduled run.
Each draft receives a distinct destination and topic before generation starts and is then checked against pages already published. Two pieces built from the same template otherwise end up competing with each other for one search.
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.