01
Step 1
Collect per-product sales history with units and net sales in one currency, the reporting period and the horizon the merchant needs, the promotion calendar covering that horizon and any decided pricing or assortment change.
Back to topic
Spark playbook scenarios · Spark: AI Store Assistant
Forecast product sales with explicit assumptions
Next quarter's numbers are needed, yet the assumptions behind them are never written down. In this case, the immediate task is to forecast product sales with explicit assumptions. The workflow should produce a demand forecast with assumptions, ranges and review dates from the merchant's per-product history, upcoming promotions and pricing changes.
Topic
Sales and Demand Forecasting
Target keyword
shopify product sales 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 forecast product sales with explicit assumptions.
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: [per-product sales history with units and net sales in one currency, the reporting period and the horizon the merchant needs, the promotion calendar covering that horizon, and any decided pricing or assortment change].
Build the estimate product by product from a baseline of undistorted periods, applying every stated assumption explicitly and recording the adjustment made for each promotion, stockout or price change, then express the result as a range and show how it shifts when a named assumption fails to hold.
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 estimate product by product from a baseline of undistorted periods, applying every stated assumption explicitly and recording the adjustment made for each promotion, stockout or price change, then express the result as a range and show how it shifts when a named assumption fails to hold.
03
Step 3
Deliver the forecast with the assumption list, a range per product and review dates set from the horizon and the longest supplier lead time, and verify that the sum of the product estimates reconciles with the store-level history for the same baseline periods.
FAQ
Common questions when running this scenario
Cover decision rules, frequent misunderstandings, and required inputs so the team aligns on prerequisites before execution.
Which assumptions must be written down?
The baseline periods used, how promotions and stockouts were treated, and any decided pricing or assortment change. Each assumption is written next to the product it affects, so the estimate can be traced back and revised individually when one assumption later fails.
Should promoted periods feed the baseline?
Include them only as adjusted and labelled periods, because promotional volume does not represent baseline demand afterwards. The boundary is a product promoted continuously: for those the promotional level is the baseline, and that choice is stated rather than assumed.
How is the range set and later judged?
The range spans the estimate under the stated assumptions and the estimate under the named alternative, not a band invented from thin history. At each review date compare actual results with the range and record the error, so the method can be tightened next cycle.
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.