01
Step 1
Gather net sales and order records for the spike window with line-level detail, the promotion calendar, the recorded traffic sources and the order status filter in use.
Back to topic
Spark playbook scenarios · Spark: AI Store Assistant
Investigate unexpected sales increases
A strong day is treated as growth before anyone checks what produced it. In this case, the immediate task is to investigate unexpected sales increases. The workflow should produce sales and order alert rules with example messages, using the merchant's sales and order records for the period, promotion calendar and traffic sources.
Topic
Sales and Order Alerts
Target keyword
shopify sales spike 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 investigate unexpected sales increases.
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: [net sales and order records with line-level detail for the spike window, the promotion calendar, the recorded traffic sources, and the order status filter in use]. Attribute the rise before calling it demand growth by checking whether it comes from a scheduled promotion, from one or a few large orders, from a traffic source that changed, or from duplicated and test orders, and classify the spike as explained, partly explained or unexplained with the evidence for each candidate.
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
Attribute the rise before calling it demand growth by checking whether it comes from a scheduled promotion, from one or a few large orders, from a traffic source that changed, or from duplicated and test orders, and classify the spike as explained, partly explained or unexplained with the evidence for each candidate.
03
Step 3
Deliver the alert rules with the comparison window, the attribution steps, the recipients and an example message per rule, then verify each past spike against the supplied records by restating the total with the explained portion removed.
FAQ
Common questions when running this scenario
Cover decision rules, frequent misunderstandings, and required inputs so the team aligns on prerequisites before execution.
Should a spike be reported as growth?
Only after attribution. A promotion, a single large order or a tracking change can each raise recorded sales without any change in underlying demand, so the alert reports the rise and its candidate causes, and the growth claim waits until the unexplained part is known.
What if the rise comes from one order?
Report it as concentration risk rather than as demand. The rule restates the total with that order removed and shows the underlying level, so a purchasing or staffing decision is not taken on a single buyer whose order may not repeat.
Who should receive a spike alert?
Whoever can act on it: the merchandiser for the demand read, and whoever owns fulfilment and inbound stock for the capacity check. A spike can strain fulfilment before it is understood, so one recipient who can only read the number is not enough.
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.