Answering a stock question means opening several screens, so nobody trusts the number they quote to a customer. In this case, the immediate task is to build an inventory visibility dashboard. The workflow should produce an inventory visibility report and refresh requirements grounded in the merchant's own stock snapshots.
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 build an inventory visibility dashboard.
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: [the trusted stock snapshots, their SKU and location identifiers, the availability definitions in use, each source's refresh interval, and the questions the dashboard must answer]. Lay out one default view answering those questions with physical, committed and sellable quantities side by side and the age of each figure, push location detail into a drill-down rather than the main view, and route SKUs with missing or stale readings to a separate exception panel instead of showing them as zero.
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.
Take the stock snapshots the merchant already trusts, the SKU and location identifiers they carry, the availability definitions in use, the refresh interval of each underlying source, and the questions the dashboard must answer without opening another screen.
Lay out one default view answering those questions with physical, committed and sellable quantities side by side and the age of each figure, push location detail into a drill-down rather than the main view, and route SKUs with missing or stale readings to a separate exception panel instead of showing them as zero.
Deliver an inventory visibility report describing each panel with its field and source, add refresh requirements giving the interval and owner per source, and verify the dashboard figures against the source snapshot for a sample of SKUs before handover.
Cover decision rules, frequent misunderstandings, and required inputs so the team aligns on prerequisites before execution.
Physical, committed and sellable quantities side by side with the age of each figure, because a single number invites the reader to treat held stock as instantly available. Anything needed only occasionally, such as location splits or movement history, belongs in a drill-down so the main view stays answerable at a glance.
In an exception panel, never as zero, because a blank reading rendered as zero hides a real stockout risk behind a confident number. Those SKUs carry a missing or stale label with the last successful refresh, and the panel is the first thing the team works through each day.
Before handover its figures are checked against the source snapshot for a sample of SKUs, and every panel names the source and refresh interval behind it. A panel without a named source or interval is not published, since nobody could then tell how old its numbers are.
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.