01
Step 1
Collect daily or weekly net sales with the seasonality and weekday patterns, the comparison window the merchant accepts as valid, the minimum move that counts as a decline, and the reporting completeness checks available.
Back to topic
Spark playbook scenarios · Spark: AI Store Assistant
Detect sustained sales declines against a relevant baseline
Sales fall for a week and the cause is only discussed at the next monthly review. In this case, the immediate task is to detect sustained sales declines against a relevant baseline. The workflow should produce sales and order alert rules with example messages, using the merchant's daily or weekly sales, seasonality and comparison window.
Topic
Sales and Order Alerts
Target keyword
shopify sales drop 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 sustained sales declines against a relevant baseline.
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: [daily or weekly net sales with the seasonality and weekday patterns, the comparison window the merchant accepts as valid, the minimum move that counts as a decline, and the reporting completeness checks available].
Compare each interval with a matched baseline of the same weekday and season, require the shortfall to persist across consecutive intervals and to exceed the merchant's stated minimum move, and suppress the alert when orders are missing, still importing, or when the store's own timezone has not closed the interval yet.
Return sales and order alert rules with example messages 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 interval with a matched baseline of the same weekday and season, require the shortfall to persist across consecutive intervals and to exceed the merchant's stated minimum move, and suppress the alert when orders are missing, still importing, or when the store's own timezone has not closed the interval yet.
03
Step 3
Deliver the alert rules with the baseline definition, the persistence requirement, the suppression checks and an example message per rule, then verify them by replaying recent periods and listing each decline that would have fired together with the cause later established.
FAQ
Common questions when running this scenario
Cover decision rules, frequent misunderstandings, and required inputs so the team aligns on prerequisites before execution.
How long must a decline last before alerting?
Require the shortfall across several consecutive intervals against a matched baseline, so one slow day never fires an alert. The boundary is completeness: if orders are still importing or the timezone day has not closed, the alert is suppressed rather than sent early.
What baseline should the decline compare to?
A period matched on weekday and season with similar promotion activity, since an unmatched baseline turns ordinary seasonality into a false alarm. The message names the comparison window it used, so the reader can reproduce the number being reported.
Can a tracking change look like a decline?
Yes. A theme change, a consent change or a broken checkout can cut recorded sales with no change in demand, so the rule checks data collection before firing. Where recorded sessions also fall, the alert is routed to whoever owns tracking.
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.