01
Step 1
Gather sales history by SKU in units, the dated periods each SKU was unavailable, the promotions run, the on-hand and on-order quantities, and the horizon the plan must cover.
Back to topic
Spark playbook scenarios · Spark: AI Store Assistant
Forecast inventory demand from adjusted history
History shows weeks when the item was unavailable or discounted, treated as normal demand. In this case, the immediate task is to forecast inventory demand from adjusted history. The workflow should produce a demand forecast with assumptions, ranges and review dates from the merchant's per-SKU history, unavailable periods and promotion list.
Topic
Sales and Demand Forecasting
Target keyword
shopify inventory forecasting app
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 inventory demand from adjusted 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: [sales history by SKU in units, the dated periods each SKU was unavailable, the promotions run, on-hand and on-order quantities, and the horizon the plan must cover]. Adjust the affected intervals before projecting, scaling stockout intervals up to the demand level observed either side of them and scaling promotional intervals down to the surrounding baseline, then confirm the adjusted series still shows the weekday and trend shape present in the observed record.
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
Adjust the affected intervals before projecting, scaling stockout intervals up to the demand level observed either side of them and scaling promotional intervals down to the surrounding baseline, then confirm the adjusted series still shows the weekday and trend shape present in the observed record.
03
Step 3
Deliver the demand estimate per SKU with the adjustment log, the coverage it implies against on-hand and on-order stock and review dates set from the longest lead time, and verify the adjusted history by adding every recorded adjustment back onto the original units.
FAQ
Common questions when running this scenario
Cover decision rules, frequent misunderstandings, and required inputs so the team aligns on prerequisites before execution.
Can the raw sales history be used as is?
No. Intervals when an item was unavailable or discounted understate or overstate real demand, so each affected interval is adjusted and logged first. The boundary is a SKU whose history is mostly distorted: its projection is marked low-confidence rather than silently accepted.
How far ahead should the horizon run?
Set it from the longest supplier lead time plus one review cycle, so the output covers the purchasing decision that must actually be made. A shorter horizon produces a number nobody can act on, and a longer one rests on assumptions nobody reviewed.
Should fast and slow movers share one method?
Use one method but review the two groups separately, because error behaves differently when volume is low or intermittent. Slow movers are listed with their intermittent demand pattern named, and their estimates carry a wider range than fast movers built from the same history.
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.