Before buying, shoppers ask about specifications, sizing and compatibility, and the store has no consistent way to answer. In this case, the immediate task is to answer presales questions from verified product facts. The workflow should produce an answer set with the fact behind each reply and the follow-up questions used when a shopper's need is unclear.
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 answer presales questions from verified 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: [verified specifications, size charts with their measurement basis, compatibility rules and exceptions, material and care facts, shipping constraints per destination, and the recurring presales questions]. Answer from those verified fields only, comparing two products solely on attributes present in both records while naming any attribute missing from either side, and asking exactly one targeted follow-up when the shopper's requirement is ambiguous.
Return the answer set with the fact behind each reply checked against the supplied product 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 verified specifications, size charts with the measurement basis behind them, compatibility rules and their exceptions, material and care facts, shipping constraints per destination, and the questions presales contacts repeat most.
Answer from those verified fields only, comparing two products solely on attributes present in both records while naming any attribute missing from either side, and asking exactly one targeted follow-up when the shopper's requirement is ambiguous.
Deliver the answer set quoting the fact and source record behind each reply, then check every answer against the supplied product data and flag any that depends on a field the catalogue leaves empty.
Cover decision rules, frequent misunderstandings, and required inputs so the team aligns on prerequisites before execution.
Yes, provided both records carry the attributes being weighed; where one side lacks a value the gap is stated rather than filled, because a guessed specification is worse for the shopper than an admitted unknown.
It narrows the choice using the needs stated and explains each tradeoff, leaving the decision to the shopper; a single recommendation hides which attributes failed to match and raises the risk of a return.
With one focused follow-up on the attribute that decides the reply, such as size, use case or compatibility, rather than guessing which product is meant, since guessing yields confident advice about the wrong item.
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.