Candidates look profitable on a supplier quote until freight, duty and destination pricing are counted in the same figure. In this case, the immediate task is to screen candidate products for attractive landed margins. The workflow should produce a shortlist ranked by margin evidence, flagging the figures that rest on estimates rather than confirmed quotes.
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 screen candidate products for attractive landed 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: [supplier cost quotes, freight and duty inputs, payment and fulfilment costs, intended selling prices by destination market, recorded discount and return rates, and the confirmed-versus-estimated status of each figure]. Compute landed margin per candidate as selling price minus all counted cost lines, discounting expected returns where records exist, and label every figure built on an estimate rather than a confirmed quote so the ranking shows its own weakest inputs.
Return a shortlist ranked by margin evidence with the validation test each candidate needs 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.
Gather each candidate's supplier quoted cost, freight and duty inputs, payment and fulfilment costs the merchant will bear, the intended selling price in the destination market, and any recorded discount and return rates for comparable products.
Compute landed margin per candidate as selling price minus all counted cost lines, discounting expected returns where records exist, and label every figure built on an estimate rather than a confirmed quote so the ranking shows its own weakest inputs.
Deliver a shortlist ranked by margin evidence with each candidate's cost breakdown, the confirmed-versus-estimated status of every line, and the validation test needed to confirm its estimates, then reconcile the cost lines back to the supplied quotes.
Cover decision rules, frequent misunderstandings, and required inputs so the team aligns on prerequisites before execution.
Supplier price, freight, duty, payment fees and the fulfilment costs the merchant expects to bear, each shown as its own line; omitting any line overstates what a sale returns, and the breakdown makes an omitted cost visible at review.
Where the merchant's records hold discount or return rates for comparable products, the margin is computed on the expected net price rather than full price; without such records the margin is labelled as assuming full-price, zero-return sales, a condition the records may not support.
Because margin depends on the gap between price and the actual cost lines, not on the price tag alone; a low-priced candidate with proportionally low fixed costs can clear the stated bar, so the check reads the breakdown instead of the selling price.
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.