01
Step 1
Gather sales and order records already split by the segments the merchant acts on, with the window, the sales definition, the currency and the order statuses counted.
Back to topic
Spark playbook scenarios · Spark: AI Store Assistant
Explain observed sales trends by segment
A merchant can see the sales line has moved over recent weeks but cannot tell which segment carried the change. In this case, the immediate task is to explain observed sales trends by segment. The workflow should produce a segment-level reading that ties each movement to order counts, order value or mix in the merchant's own records.
Topic
Sales and Store Analytics
Target keyword
shopify sales trend analysis
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 explain observed sales trends by segment.
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: [sales and order records already split by the segments the merchant acts on, the window, the sales definition, the currency, and the order statuses counted]. Trace each segment's movement to its order count, its average order value or its share of the mix by restating the total with that segment held at the comparison-period level, and keep the measured movement separate from candidate explanations until every segment's contribution has been computed.
Return a segment-level sales report with definitions and the figure behind each movement 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
Trace each segment's movement to its order count, its average order value or its share of the mix by restating the total with that segment held at the comparison-period level, and keep the measured movement separate from candidate explanations until every segment's contribution has been computed.
03
Step 3
Deliver the segment reading with each contribution, the mix effect and the unexplained residual, alongside a separate list of candidate causes the records support, then verify that the sum of the segment contributions plus the residual equals the observed total change.
FAQ
Common questions when running this scenario
Cover decision rules, frequent misunderstandings, and required inputs so the team aligns on prerequisites before execution.
Which segments are worth analysing?
The ones the merchant acts on, such as product category, channel or customer type. Splitting by a dimension nobody can influence produces a finding with no owner, and each extra dimension also thins the records behind every cell until the movement is mostly noise.
Should the cause be given with the movement?
No. The report states the measured movement per segment first, then lists the candidate explanations the records support, keeping the two apart. Merging them lets a plausible story outlive the data that contradicted it.
Why use more than two periods?
Two points show movement without direction. Several periods show whether a change is a sustained shift or ordinary variation, and they reveal a trend that began earlier than the comparison window the merchant had in mind.
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.