01
Step 1
Gather dated sales history in units with the availability log, promotion dates, product launch dates and the supplier lead times that constrain the response.
Back to topic
Spark playbook scenarios · Spark: AI Store Assistant
Identify seasonal patterns in the sales history
Peaks appear in the history every year, but nobody has checked whether they repeat or happened only once. In this case, the immediate task is to identify seasonal patterns in the sales history. The workflow should produce a demand forecast with assumptions, ranges and review dates, using the merchant's dated sales, availability records and promotion dates.
Topic
Sales and Demand Forecasting
Target keyword
shopify seasonal sales 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 identify seasonal patterns in the sales history.
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: [dated sales history in units with the availability log, promotion dates, product launch dates, and the supplier lead times that constrain the response]. Align the same calendar windows across every year available, mark a peak as recurring only when it appears in the same window across enough years to separate a pattern from a coincidence, and mark windows distorted by stockouts, campaigns or a launch as unusable rather than averaging them in.
Return a demand forecast with assumptions, ranges and review dates 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
Align the same calendar windows across every year available, mark a peak as recurring only when it appears in the same window across enough years to separate a pattern from a coincidence, and mark windows distorted by stockouts, campaigns or a launch as unusable rather than averaging them in.
03
Step 3
Deliver a seasonal profile giving the peak and trough windows per product, the value range observed in each and the purchasing deadline implied by the lead time, then verify the profile against the raw dated history and list every window excluded with the reason.
FAQ
Common questions when running this scenario
Cover decision rules, frequent misunderstandings, and required inputs so the team aligns on prerequisites before execution.
How many cycles make a peak credible?
A peak is marked recurring only when it appears in the same window across enough years to separate a pattern from a coincidence. With a single cycle the finding stays provisional and is labelled as such, so nobody commits stock to a one-off event.
What if the peak moves earlier each year?
Record the shifting dates instead of averaging them, because a moving season changes the correct purchasing deadline. Averaging places the peak between years where no peak occurs, and stock then arrives after demand has already passed.
Which products can be assessed?
Only products with enough dated history to judge. New products and products whose history is largely stockout-distorted get no seasonal claim and are listed as insufficient, with the earliest date at which a defensible read becomes possible.
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.