Shoppers face a catalogue where the right choice depends on the use case, but nothing on the page helps them narrow it. In this case, the immediate task is to guide product selection through relevant questions. The workflow should produce a comparison table and guided selection explanation, tested against the merchant's own product 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 guide product selection through relevant 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 candidate products, each candidate's recorded attribute answers, the permitted questions and their answer options, the merchant's stated priorities, and the current availability of each candidate]. Order the questions from the broadest discriminator to the narrowest, recording how many candidates remain after each answer, retiring any question that leaves the set unchanged, and attaching to every surviving product the reason it fits, while flagging paths whose answers leave nothing or leave only products not currently offered for sale.
Return a comparison table and guided selection explanation 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, the answers each one supports in the merchant's own records, the questions to be asked with their permitted answer options, and the priorities that should drive a recommendation, including the attributes marking a product as a match.
Order the questions from the broadest discriminator to the narrowest, recording how many candidates remain after each answer, retiring any question that leaves the set unchanged, and attaching to every surviving product the reason it fits, while flagging paths whose answers leave nothing or leave only products not currently offered for sale.
Deliver the question flow with its decision rules and a guided note naming the shortlist and the reasoning behind it, then replay every answer path against the merchant's product records so the recommended set is the one those records support, and list each path that ends without a recommendation.
Cover decision rules, frequent misunderstandings, and required inputs so the team aligns on prerequisites before execution.
Once no remaining question would change the outcome, normally when further answers no longer split the candidate set. Questions kept for completeness only add friction without information; one earns its place by moving some shoppers to a different shortlist than they would otherwise have reached.
Say plainly that no product fits the answers and show the nearest alternatives together with the attribute each failed on, rather than promoting a poor substitute. A forced recommendation is worse than an empty result because it looks authoritative, and the same rule applies to paths whose only match is unavailable for sale.
Replay each answer path against the merchant's own product records and check that the returned products are exactly those whose recorded attributes satisfy every answer given. Paths are re-run after any catalog or answer change, because a recommendation is only ever as sound as the records standing behind 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.