An alert fires on a segment the merchant has never examined, and those visits behave unlike the store's usual shoppers. In this case, the immediate task is to investigate unusual traffic patterns. The workflow should produce a traffic anomaly report and investigation rules tying each pattern to the promotion or conversion record behind 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 investigate unusual traffic patterns.
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 alert windows with the thresholds that triggered them, the affected segments with their source, device and landing page definitions, the engagement and conversion behaviour inside those segments, the promotion and content calendar for the same dates, and any recorded tag changes]. Classify each pattern as a behaviour change where a dated promotion or post on the merchant's calendar accounts for it, a measurement artefact where a segment definition or tag change on those dates reclassified existing visits, or traffic with no purchase intent where sessions rise while engagement and orders stay flat, and mark it unclassified where the records support none of these.
Return a traffic anomaly report and investigation rules, with each pattern tied to the evidence supporting it 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.
Gather the alert windows with the thresholds that triggered them, the segments involved with their source, device and landing page definitions, the engagement and conversion behaviour inside those segments, the promotion and content calendar for the same dates and any tag changes recorded.
Classify each pattern as a behaviour change where a dated promotion or post on the merchant's calendar accounts for it, a measurement artefact where a segment definition or tag change on those dates reclassified existing visits, or traffic with no purchase intent where sessions rise while engagement and orders stay flat, and mark it unclassified where the records support none of these.
Deliver a traffic anomaly report and investigation rules tying each pattern to the promotion or conversion record behind it, then confirm that the segment definition is unchanged across the window and list one-off movements separately with the date and the segment affected.
Cover decision rules, frequent misunderstandings, and required inputs so the team aligns on prerequisites before execution.
Yes. A change to tagging, to a channel rule or to a segment definition can move visits between labels while the store's totals hold steady, which reads as an anomaly in one segment. The check compares the segment definition before and after the window and reconciles it against the store total before calling the movement real.
With the date, the segment and the measures observed, and left unclassified unless the same pattern reappears in a later window. Assigning a cause to a single occurrence puts a guess in the report, so the entry stays an observation with the checks already attempted named against it for the next review.
No. Until the engagement and conversion records move in the same direction, the pattern is reported as unconfirmed together with the measures that stayed flat, because a session change on its own is not a business outcome. It ranks below explained patterns and is revisited only when the quality measures confirm it.
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.