A product can draw strong interest and still fail on cost once delivery is included. In this case, the immediate task is to shortlist products with evidence of demand and viable margins. The workflow should produce a ranked shortlist with reasons and stated uncertainty, checked against the cost and demand records supplied.
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 shortlist products with evidence of demand and viable margins.
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: [candidate product list, dated demand evidence with sources, competitor selling prices by destination market, supplier cost quotes, freight and duty inputs, delivery terms, the merchant's stated minimum margin, and per-figure uncertainty notes]. Screen every candidate on two tests, demand evidence that holds across the window and landed margin computed from the quoted inputs against the stated minimum, keeping only candidates that clear both and marking any that pass one test on estimated rather than confirmed figures.
Return a ranked shortlist with reasons and stated uncertainty, checked against the supplied cost 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.
Assemble the candidate products with dated demand evidence and its source, competitor selling prices in the destination market, supplier quoted cost, freight and duty inputs, delivery terms, the merchant's stated minimum margin, and the uncertainty each figure carries.
Screen every candidate on two tests, demand evidence that holds across the window and landed margin computed from the quoted inputs against the stated minimum, keeping only candidates that clear both and marking any that pass one test on estimated rather than confirmed figures.
Deliver a ranked shortlist stating for each survivor the deciding evidence, its margin basis and its largest uncertainty, then reconcile each quoted cost and price back to the supplier quotes and competitor listings supplied before the list is used for ordering.
Cover decision rules, frequent misunderstandings, and required inputs so the team aligns on prerequisites before execution.
A landed cost that leaves the selling price below the stated minimum margin once freight, duty and fulfilment are counted, supply the merchant cannot secure reliably, or delivery terms the store cannot meet; demand alone never carries a candidate, and each disqualification is recorded with the failing input so it can be revisited.
Small enough that every entry can be put through a real validation test within the next buying cycle, because the list exists to focus testing rather than to store ideas; candidates that miss the cut stay on the research record with the failed test named, not on the shortlist.
Each survivor's margin line is traced back to the supplier quote and the competitor price it was built from, and any figure that came from an estimate instead of a confirmed quote is labelled; the check matters because one unconfirmed freight input can silently move a candidate across the margin bar.
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.