01
Step 1
Pull, for each location, the stock snapshot with its SKU and location identifiers, the definitions the merchant uses for physical, committed and sellable quantities, and the update timestamp recorded on each snapshot.
Back to topic
Spark playbook scenarios · Spark: AI Store Assistant
Review stock availability across multiple locations
Two warehouses ship the same catalogue, yet availability is only ever reported as one blended total. In this case, the immediate task is to review stock availability across multiple locations. The workflow should produce an inventory visibility report and refresh requirements checked against the merchant's per-location records.
Topic
Inventory Management and Visibility
Target keyword
shopify multi location inventory management
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 review stock availability across multiple locations.
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-location stock snapshots with SKU and location identifiers, the merchant's definitions of physical, committed and sellable quantities, and each snapshot's update timestamp]. Report quantities per location rather than as one blended total, deriving sellable stock as physical less committed inside each location, and exclude from every availability figure a transfer the receiving location has not confirmed, listing those units as in transit instead.
Return an inventory visibility report and refresh requirements, with each quantity verified against the supplied records 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
Report quantities per location rather than as one blended total, deriving sellable stock as physical less committed inside each location, and exclude from every availability figure a transfer the receiving location has not confirmed, listing those units as in transit instead.
03
Step 3
Deliver an inventory visibility report with per-location rows and a store-level view that sums only confirmed sellable quantities, add refresh requirements per location, then verify each quantity against that location's own snapshot and reconcile the summed total with the per-location rows before publishing.
FAQ
Common questions when running this scenario
Cover decision rules, frequent misunderstandings, and required inputs so the team aligns on prerequisites before execution.
Which figure should a storefront promise against?
The sellable quantity of the location that will fulfil the order, not the sum across all locations, because stock sitting in a distant warehouse may not reach the shopper inside the promised window. Where the fulfilling location is chosen later, the report shows each location's sellable figure separately.
Does a transfer between locations raise availability?
Only once the receiving location confirms it. Until then the units are shown as in transit and excluded from both locations' sellable figures, since counting them twice oversells the SKU while counting them nowhere hides stock the merchant has already paid for.
How is a SKU with conflicting location records reported?
Both readings are kept, the newer timestamp is labelled, and the conflict is resolved from the source of record before any total is published. Where it stays unresolved the SKU appears with both values and no summed line, so a wrong total never reaches a decision.
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.