01
Step 1
Collect per product, at the level the merchant tracks stock, the sales history with its period, current stock, inbound quantities, supplier lead times, and pack or minimum order constraints.
Back to topic
Spark playbook scenarios · Spark: AI Store Assistant
Build a replenishment plan by product
A buying cycle is about to start and each product needs its own coverage figure before anything can be committed. In this case, the immediate task is to build a replenishment plan by product. The workflow should produce a replenishment plan with timing and quantity rationale from the merchant's per-product sales history and pack or minimum constraints.
Topic
Replenishment and Inventory Planning
Target keyword
shopify replenishment planning
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 build a replenishment plan by product.
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 its period, current stock, inbound quantities, supplier lead times, and pack or minimum order constraints at the tracked stock level]. Work product by product through projected coverage using the stated demand basis, round each proposed quantity up to the recorded pack or case size, and flag any line whose sales history is shorter than the merchant's stated minimum history or covers a known distortion.
Return a replenishment plan with timing and quantity rationale 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
Work product by product through projected coverage using the stated demand basis, round each proposed quantity up to the recorded pack or case size, and flag any line whose sales history is shorter than the merchant's stated minimum history or covers a known distortion.
03
Step 3
Deliver the replenishment plan with quantity rationale plus the extra coverage each pack rounding introduced, then verify the row count equals the tracked products and reconcile every line against the stock and inbound records.
FAQ
Common questions when running this scenario
Cover decision rules, frequent misunderstandings, and required inputs so the team aligns on prerequisites before execution.
Why does rounding up to pack size change coverage?
The calculated quantity rarely lands on a whole pack, so it is rounded up to the recorded pack or case size and the extra units add coverage beyond the target. The rationale notes the extra days each rounding introduced. Rounding down is not used, because a short pack would breach the supplier's own constraint anyway.
What marks a line as thin data?
A line is flagged when its sales history is shorter than the merchant's stated minimum history, or its period includes a known distortion such as a long stockout. Flagged lines carry the merchant's stated assumption instead of a computed figure. They are never filled with an invented demand value, since the plan's credibility rests on traceable numbers.
How is the plan level kept consistent with stock tracking?
Every line is built at the level the merchant actually tracks stock, and results are rolled up only after the per-unit lines are complete. Planning at a coarser level than the tracked one hides gaps that exist where counts actually happen. The roll-up is for review, while ordering happens at the tracked level.
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.