01
Step 1
Pull product and variant identifiers with sales, sessions, stock availability and in-sale dates for the merchant's stated comparison period, recording for each product the days it was actually purchasable.
Back to topic
Spark playbook scenarios · Spark: AI Store Assistant
Rank products by a stated sales measure
Ranking lists tend to get built from whichever number is easiest to export, so exposure masquerades as demand. In this case, the immediate task is to rank products by a stated sales measure. The workflow should produce a ranked report explaining the drivers behind each position, with products of limited exposure separated out.
Topic
Product Performance Analytics
Target keyword
shopify best selling products report
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 rank products by a stated sales measure.
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: [product and variant identifiers, sales, sessions, stock availability, in-sale dates for the stated comparison period, and the merchant's stated ranking measure]. Rank by the merchant's stated measure applied identically to every row, and separate products whose availability or exposure was too limited for the measure to indicate demand, reporting them with raw counts instead of a rank position.
Return a ranked report with the drivers behind each position and the next test, checked against the 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.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
Rank by the merchant's stated measure applied identically to every row, and separate products whose availability or exposure was too limited for the measure to indicate demand, reporting them with raw counts instead of a rank position.
03
Step 3
Deliver the ranked report with the measure and period stated, the driver behind each top position, the separately listed limited-exposure products and a proposed next test, then reconcile the ranked totals with the sales records.
FAQ
Common questions when running this scenario
Cover decision rules, frequent misunderstandings, and required inputs so the team aligns on prerequisites before execution.
Which measure should define a best seller?
The merchant's stated measure, whether units, revenue or margin, applied identically across the whole period. Mixing measures between rows, such as units for some products and revenue for others, makes the ranking impossible to read or defend.
Why might a strong product rank low?
Limited exposure, restricted stock or a short in-sale window suppress sales without any demand problem, which is why purchasable days are recorded per product. Such items are listed separately with raw counts rather than given a misleading position.
Should variants be ranked with products?
Report both levels, since a strong variant can hide inside a mediocre parent product. The variant view keeps the parent total intact while showing which options actually sell.
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.
Identify underperforming products and plausible constraints
Report product sales using consistent product identifiers
Measure traffic reaching individual product pages
Detect unusual product performance changes
Measure each product's contribution to revenue
Compare conversion performance across product pages
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.