01
Step 1
Collect each source's identifier and last successful update timestamp, the refresh window the merchant expects for it, the availability definitions applied to its quantities, and the owning team named for each source.
Back to topic
Spark playbook scenarios · Spark: AI Store Assistant
Monitor inventory freshness and availability
Replenishment runs off a periodic export that sometimes lands late or does not arrive at all. In this case, the immediate task is to monitor inventory freshness and availability. The workflow should produce an inventory visibility report and refresh requirements based on the merchant's actual update records.
Topic
Inventory Management and Visibility
Target keyword
shopify inventory monitoring
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 monitor inventory freshness and availability.
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: [each source's identifier and last successful update timestamp, its expected refresh window, the availability definitions applied to its quantities, and the owning team per source]. Measure every snapshot against its own expected window, mark a figure stale once it is older than that window and missing when the expected refresh never arrived, and block those quantities from replenishment or availability decisions until the source refreshes or an owner records why it cannot.
Return an inventory visibility report and refresh requirements 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
Measure every snapshot against its own expected window, mark a figure stale once it is older than that window and missing when the expected refresh never arrived, and block those quantities from replenishment or availability decisions until the source refreshes or an owner records why it cannot.
03
Step 3
Deliver an inventory visibility report with a freshness panel per source showing the expected window, the actual age and the status, add refresh requirements naming the owning team, and reconcile the number of stale sources with the alerts raised before the cycle is signed off.
FAQ
Common questions when running this scenario
Cover decision rules, frequent misunderstandings, and required inputs so the team aligns on prerequisites before execution.
When is a stock figure too old to use?
Once it is older than the source's expected refresh window, because orders, receipts and adjustments since then have moved the real position. Age is measured per source rather than against one store-wide rule, since a warehouse feed and a nightly export cannot be held to the same interval.
Should a stale quantity be hidden?
No, it is displayed with its age and status marked, because replacing it with a blank or a zero makes the view look complete while a real stockout risk sits behind it. If the source cannot refresh, the owner records why and the figure stays flagged.
Who fixes a source that failed to refresh?
The team named in advance as owning that system; alerts are addressed to them rather than to a shared inbox, and a monitoring cycle is not signed off while a stale source has no named owner. An alert nobody can act on is the same as no alert.
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.