01
Step 1
Collect, for the same merchant-defined period, each product's units sold and orders placed, its refunded units and refunded orders, and the refund dates, all at the level, product or variant, that the merchant's records support.
Back to topic
Spark playbook scenarios · Spark: AI Store Assistant
Compare refund rates by product with consistent denominators
Products with very different order volumes are being compared on raw refund totals, which makes the ranking unreliable. In this case, the immediate task is to compare refund rates by product with consistent denominators. The workflow should produce a refund breakdown and evidence-based action list, using the merchant's units, orders and refund dates.
Topic
Refund Analysis and Alerts
Target keyword
shopify refund rate by product
Copyable AI prompt
A prompt you can drop directly into Spark
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.
ai-prompt.txt
Act as a Shopify operations specialist.
Help me compare refund rates by product with consistent denominators.
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: [each product's units sold and orders placed, refunded units and refunded orders, and refund dates for the same defined period, at the recorded product or variant level]. Compute every product's refund rate with a single declared denominator, orders or units, applied identically across the catalog, and mark products below the merchant's stated minimum order count as low-volume, reporting them with raw counts instead of a ranked rate.
Return a refund breakdown and evidence-based action list 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.How to solve
A recommended resolution workflow
Split the work into input, judgment, and deliverable phases. Verify each step's output before moving to the next.
02
Step 2
Compute every product's refund rate with a single declared denominator, orders or units, applied identically across the catalog, and mark products below the merchant's stated minimum order count as low-volume, reporting them with raw counts instead of a ranked rate.
03
Step 3
Deliver the refund breakdown and evidence-based action list, verify each rate by recomputing it from the raw counts, and note which denominator the ranking uses and where low-volume products were excluded from comparison.
FAQ
Common questions when running this scenario
Cover decision rules, frequent misunderstandings, and required inputs so the team aligns on prerequisites before execution.
How is the ranking protected from mixed denominators?
One denominator, orders or units, is declared in the report and applied to every product alike. Mixed bases make the ranking meaningless because products are not being divided by the same thing. A product whose denominator cannot be computed stays unranked with its raw counts shown.
What does verification of a rate involve?
Each published rate is recomputed from its raw counts and matched against the reported figure. This catches assembly and rounding errors before the list drives decisions. A mismatch sends the product back rather than letting the ranking ship.
What happens if the denominator is switched later?
The whole period is recomputed from raw counts under the new basis, since rates cannot be rescaled product by product. A rescaled mix would quietly keep fragments of the old denominator. The report states which basis each published ranking used.
Related scenarios
Continue with adjacent or same-topic scenarios
Start with scenarios under the same topic, then expand into cross-topic matches suggested by similarity.
Next step
Want these AI scenarios embedded directly into daily operations?
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.