After a round of configuration changes and imports, the merchant wants one honest picture of how the store runs now. In this case, the immediate task is to review the store's current operational health. The workflow should snapshot the catalog, order and fulfillment records and flag every place where behaviour departs from the intended setup.
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 review the store's current operational health.
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 current catalog state, order and fulfillment statuses in force, inventory quantities published per channel, and the configuration changes and imports applied in the named period].
Compare what the snapshot shows against the setup the merchant intends, recording each departure with the area, the records affected, the change most likely to have caused it and whether customers can currently see it, and treating a departure explained by a recent import as still open until the correction is verified.
Return a health summary with current status and watch items 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.
Snapshot the current catalog state, the order and fulfillment statuses in force, the inventory quantities published per channel, and the configuration changes and imports applied in the period the merchant names, capturing the snapshot time alongside the records.
Compare what the snapshot shows against the setup the merchant intends, recording each departure with the area, the records affected, the change most likely to have caused it and whether customers can currently see it, and treating a departure explained by a recent import as still open until the correction is verified.
Deliver a health summary listing current status per area in scope, the deviations found and the watch items that sit inside tolerance but are worth re-checking, state plainly which areas were not reviewed because no records were supplied, and reconcile the deviating records listed against the counts in the snapshot.
Cover decision rules, frequent misunderstandings, and required inputs so the team aligns on prerequisites before execution.
Any place where observed behaviour departs from the setup the merchant intends, recorded with the area, the affected records and the likely cause. A difference that is intentional, meaning a setting the merchant changed on purpose, is noted as expected rather than a deviation.
No, it means no departure was found among the checks performed on the records supplied at the snapshot time. Areas with no records supplied are listed as not reviewed rather than assumed sound, and behaviour can change with the next import.
Because a recent configuration edit or import usually explains a newly appearing deviation and points straight at the correction, while without it the team must re-derive the cause. Where no change lines up, the deviation is flagged as unexplained and needs its own investigation.
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.