Sessions fall between one report and the next, and the merchant cannot tell whether demand weakened, tracking broke or a channel stopped. In this case, the immediate task is to identify significant traffic declines. The workflow should produce a traffic anomaly report and investigation rules that rank each decline by how far the series support it.
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 identify significant traffic declines.
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 daily and weekly session series, the channel, device and landing page splits, the dates of any tracking, theme or tag change, the promotion calendar covering the window, and a baseline period matched on promotion and seasonal conditions]. Measure the decline against that baseline, then test the competing explanations in order by checking whether the drop appears across every channel and device at once and coincides with a recorded tag change, whether it is confined to one channel or campaign, and whether the baseline period's promotion calendar accounts for it, marking each explanation as supported or not supported by the records.
Return a traffic anomaly report and investigation rules, ranking the declines the records support 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 the daily and weekly session series, the channel, device and landing page splits, the dates of any tracking, theme or tag change, the promotion calendar covering the window and a baseline period chosen to match its promotion and seasonal conditions.
Measure the decline against that baseline, then test the competing explanations in order by checking whether the drop appears across every channel and device at once and coincides with a recorded tag change, whether it is confined to one channel or campaign, and whether the baseline period's promotion calendar accounts for it, marking each explanation as supported or not supported by the records.
Deliver a traffic anomaly report and investigation rules ranking each decline by how far the records support it, then reconcile the session count for the window against the store's own session and order records and re-run the comparison after any tracking fix so the same decline is not counted twice.
Cover decision rules, frequent misunderstandings, and required inputs so the team aligns on prerequisites before execution.
A break tends to appear across all channels, devices and landing pages at once and starts on a date with a recorded tag or theme change, while weaker demand usually concentrates in one channel or landing page. Where the drop is uniform and dated to a change, tracking is ranked first and confirmed by re-running the window afterwards.
One with a comparable promotion calendar and the same weekday composition, because promotional and weekend traffic distort a comparison on their own. The report names the baseline and the reason for choosing it, so a reviewer can see whether the conclusion would change under a different window instead of accepting the number as given.
When it sits inside the variation the series already shows between comparable periods, so it cannot be separated from normal movement. Those are still recorded with the measured size and the baseline used, and they are ranked below declines that exceed that variation and carry a dated, checkable cause.
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.