01
Step 1
Set each product's baseline from its own history in the merchant's records, and collect product-level sales, sessions and stock availability for the period under review, using one reporting window on both sides of the comparison.
Back to topic
Spark playbook scenarios · Spark: AI Store Assistant
Detect unusual product performance changes
Weekly swings get noticed late, usually once somebody opens the dashboard and spots a dip nobody can explain. In this case, the immediate task is to detect unusual product performance changes. The workflow should produce an alert list comparing each product against its own baseline, carrying the likely driver and a suggested check.
Topic
Product Performance Analytics
Target keyword
shopify product performance alerts
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 detect unusual product performance changes.
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: [per-product baseline history, product-level sales, sessions, stock availability, and the shared reporting window].
Compare each product against its own baseline, marking movements beyond the range its own history shows, and separate expected seasonal and stock-driven effects before naming a shift as genuine.
Return an alert list with the likely driver and suggested check, confirmed against the supplied 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
Compare each product against its own baseline, marking movements beyond the range its own history shows, and separate expected seasonal and stock-driven effects before naming a shift as genuine.
03
Step 3
Deliver an alert list with each flagged product, its baseline range, the likely driver and a suggested check against the records, then confirm each alert survives the availability check before it is sent.
FAQ
Common questions when running this scenario
Cover decision rules, frequent misunderstandings, and required inputs so the team aligns on prerequisites before execution.
What counts as an unusual change?
A movement beyond the range that product's own recorded history shows, not any fixed threshold. High-variance products get wider bands and steady sellers tighter ones, so every alert is judged against its own baseline.
Should alerts fire on every movement?
No. Alerting on ordinary noise buries the real signals, so the trigger reflects what the merchant would actually act on. Every alert that fires carries a driver and a suggested check, keeping the list actionable.
Can stock changes explain a performance alert?
Often yes, because sold-out days cut sales without any demand shift. Availability records are checked first, and alerts whose timing matches an out-of-stock window are attributed to stock rather than demand.
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.
Measure traffic reaching individual product pages
Rank products by a stated sales measure
Identify underperforming products and plausible constraints
Compare conversion performance across product pages
Measure each product's contribution to revenue
Report product sales using consistent product identifiers
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.