01
Step 1
Collect dated sales history with units and net sales, availability records, the promotion calendar, any seasonal profile already established, and the lead times and horizon the purchasing decision requires.
Back to topic
Spark playbook scenarios · Spark: AI Store Assistant
Estimate future product demand with uncertainty ranges
Purchases are committed before the season, but the history is shaped by promotions and stockouts. In this case, the immediate task is to estimate future product demand with uncertainty ranges. The workflow should produce a demand forecast with assumptions, ranges and review dates from the merchant's dated sales, availability records and promotion calendar.
Topic
Sales and Demand Forecasting
Target keyword
shopify demand forecasting
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 estimate future product demand with uncertainty ranges.
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 with units and net sales, availability records, the promotion calendar, any seasonal profile already established, and the lead times and horizon the purchasing decision requires].
Build the baseline only from periods free of stockouts, promotions and tracking gaps, carry it forward with the seasonal profile where one is established, and express the result as a range bounded below by the baseline held flat and above by the baseline continued at its observed trend.
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
Build the baseline only from periods free of stockouts, promotions and tracking gaps, carry it forward with the seasonal profile where one is established, and express the result as a range bounded below by the baseline held flat and above by the baseline continued at its observed trend.
03
Step 3
Deliver the forecast with the assumption list, the range per product, the excluded periods and the review dates, then verify the baseline against the supplied records and flag every product whose range rests on fewer periods than the merchant requires for a defensible read.
FAQ
Common questions when running this scenario
Cover decision rules, frequent misunderstandings, and required inputs so the team aligns on prerequisites before execution.
How are stockout periods treated?
They are flagged and either excluded or adjusted, because recorded sales during a stockout understate the demand that existed. Where most of a history is stockout-affected, the product is reported as insufficient rather than forecast, since no adjustment recovers demand that was never observable.
Why report a range instead of one number?
A single figure implies a precision the history does not support, while a range shows the downside and upside at the moment stock is committed. The range is bounded by explicit alternatives, not by an unexplained margin added to a point estimate.
When should the forecast be reviewed?
Set review dates from the horizon and lead times, then compare actual demand with the range at each date. If actuals fall outside the range repeatedly, revise the assumption list first, before changing the method itself.
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.