01
Step 1
Assemble product identifiers, sales, sessions, stock availability and launch dates, plus comparison periods long enough to cover a full buying cycle for the category and equal in length on both sides.
Back to topic
Spark playbook scenarios · Spark: AI Store Assistant
Identify underperforming products and plausible constraints
Low sales do not by themselves show whether the cause is demand, exposure or stock. In this case, the immediate task is to identify underperforming products and plausible constraints. The workflow should produce a ranked list of underperformers, each with the most plausible constraint, checked against the supplied sales, session and stock records.
Topic
Product Performance Analytics
Target keyword
shopify underperforming 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 identify underperforming products and plausible constraints.
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 identifiers, sales, sessions, stock availability, launch dates, and equal-length comparison periods covering a full category buying cycle]. For each weak result, test in turn whether low exposure, stock gaps, a recent launch or genuine demand explains it, naming a cause only where the records support it and marking the rest unresolved.
Return a ranked list of underperformers with the most plausible constraint for each, 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
For each weak result, test in turn whether low exposure, stock gaps, a recent launch or genuine demand explains it, naming a cause only where the records support it and marking the rest unresolved.
03
Step 3
Deliver a ranked list of underperformers with the most plausible constraint for each, the evidence behind it, unresolved cases flagged with a proposed next test, then verify the figures against the sales, session and stock records supplied.
FAQ
Common questions when running this scenario
Cover decision rules, frequent misunderstandings, and required inputs so the team aligns on prerequisites before execution.
Is a low seller always a weak product?
No. Limited exposure, stock gaps or a recent launch can produce the same number, so those conditions are tested before any cause is ranked. A product with strong per-session sales and little traffic has an exposure problem, not a demand one.
How far back should the comparison window go?
Long enough to cover a full buying cycle for the category, with both periods equal in length. Windows shorter than the cycle compare different phases of the same pattern and mislabel normal variation as decline.
What if the constraint cannot be identified?
Record the case as unresolved, list the explanations already ruled out, and propose the next test. An honest unknown can be acted on, while an assumed cause sends the fix to the wrong lever.
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.