Stock keeps moving through the day while the reported position stays frozen at the last batch figure. In this case, the immediate task is to track stock position with visible update timestamps. The workflow should produce an inventory visibility report and refresh requirements built from the merchant's own event records.
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.
Act as a Shopify operations specialist.
Help me track stock position with visible update timestamps.
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: [movement events with their recorded event time and source, opening stock per SKU and location, the ordering rule across sources, and the merchant's accepted latency tolerance]. Apply events in their recorded event time order rather than their arrival order, rebuild the position by replaying from the last confirmed level, and hold as unapplied any event arriving outside the accepted tolerance or out of sequence so an earlier event cannot overwrite a later state.
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.Split the work into input, judgment, and deliverable phases. Verify each step's output before moving to the next.
Collect each inventory movement event with its recorded event time and source, the opening stock level per SKU and location, the ordering rule applied to events coming from different sources, and the latency tolerance the merchant accepts for operational decisions.
Apply events in their recorded event time order rather than their arrival order, rebuild the position by replaying from the last confirmed level, and hold as unapplied any event arriving outside the accepted tolerance or out of sequence so an earlier event cannot overwrite a later state.
Deliver an inventory visibility report showing the current position with its event timestamp and the count of unapplied events, add refresh requirements with the measured latency per source, and reconcile the replayed position with the last confirmed stock count before publishing.
Cover decision rules, frequent misunderstandings, and required inputs so the team aligns on prerequisites before execution.
Every source carries some delay between the physical movement and the event reaching the report, so what matters is the tolerated latency and a visible timestamp. The page states the measured delay per source and counts events still unapplied instead of claiming an instant view.
They are sorted by recorded event time rather than arrival time and the position is rebuilt by replaying from the last confirmed level, so a late-arriving sale is never wiped out by an earlier receipt. An event whose time is unknown is held unapplied rather than placed by guesswork.
Because a figure without an age cannot be trusted when committing stock to an order or promising a dispatch date. The timestamp lets the operator see whether the position includes the latest movements, and events outside the tolerance are counted so the gap is visible at a glance.
Start with scenarios under the same topic, then expand into cross-topic matches suggested by similarity.
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.