Support answers the same product questions by hand every week, and the replies differ depending on who writes them. In this case, the immediate task is to generate answers to recurring product questions. The workflow should produce one direct answer per question with a source note on each line, refusing any claim the merchant's records do not support.
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 answers to recurring product questions.
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 buyer questions recorded for the product with how often each one arrives, the support replies already sent, the product specifications and policy statements on file, and the merchant own wording for terms and conditions].
Draft one direct answer per question from those records, keep the merchant wording wherever a policy or a specification is quoted, and mark a question unresolved where the records state nothing instead of answering from general product knowledge.
Return the answer set with a source note per line 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 the buyer questions recorded for the product together with how often each one arrives, the support replies already sent, the product specifications and policy statements on file, and the merchant own wording for anything involving terms or conditions.
Draft one direct answer per question from those records, keep the merchant wording wherever a policy or a specification is quoted, and mark a question unresolved where the records state nothing instead of answering from general product knowledge.
Deliver the answer set with a source note on every line, then verify each claim against the supplied records and list the questions still needing a merchant answer, so the set carries no unsupported statement.
Cover decision rules, frequent misunderstandings, and required inputs so the team aligns on prerequisites before execution.
Every statement traces to a record the merchant supplied and carries its source note. An answer that is plausible but unsourced should stay unresolved, because publishing it commits the store to something nobody has confirmed.
Only those the merchant expects, added and marked as anticipated. Filling the set with guessed questions buries the recurring ones support actually handles and adds copy nobody has asked to maintain.
Draft both from the same records and keep one version per question, so the page and the reply read alike. Separate drafting is what produced the drift in the first place and will reproduce it.
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.