Sessions climb at hours when real customers are asleep, and the source and device splits look machine-generated. In this case, the immediate task is to assess evidence of suspicious automated traffic. The workflow should produce a traffic anomaly report and investigation rules that label each pattern as suspected or confirmed from the store's own 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 assess evidence of suspicious automated traffic.
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 session series by hour, the source and device breakdowns, the engagement signals recorded per session, the orders placed in the same window, the campaign and tag change log, and any internal or partner traffic the merchant has declared].
Compare the affected segments against a baseline period, label a pattern confirmed only where several automation signals agree and no campaign or partner record on those dates explains it, label it suspected where one signal stands alone or a declared campaign overlaps the window, and set aside traffic the merchant has identified as its own before judging.
Return a traffic anomaly report and investigation rules, labelling each pattern as suspected or confirmed 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.
Pull the session series by hour, the source and device breakdowns, the engagement signals recorded per session such as page depth and events, the orders placed in the same window, the campaign and tag change log and any internal or partner traffic the merchant has declared.
Compare the affected segments against a baseline period, label a pattern confirmed only where several automation signals agree and no campaign or partner record on those dates explains it, label it suspected where one signal stands alone or a declared campaign overlaps the window, and set aside traffic the merchant has identified as its own before judging.
Deliver a traffic anomaly report and investigation rules labelling each pattern suspected or confirmed with the signals behind that label, then re-run the same window with the flagged segments excluded so the merchant can see how much of the conversion reporting the pattern was moving.
Cover decision rules, frequent misunderstandings, and required inputs so the team aligns on prerequisites before execution.
When several independent signals agree, such as extreme session counts from one source alongside requests with no engagement, and no campaign, partner or tagging record on those dates accounts for it. A single signal, however strong, stays suspected, because a legitimate placement or a feed can produce the same shape for a while.
Report the window both with and without the flagged segments instead of deleting anything, so the effect on conversion measures stays visible and reversible. Removal also hides later changes in the same segment, so the excluded figures are recorded alongside the reason and the dates for the exclusion.
Yes. A single placement or an email send can produce a burst from one source at unusual hours with shallow engagement, which is why the campaign and tag log is checked before any label is applied. Where a dated campaign matches the window, the pattern is attributed to it and kept out of the automated category.
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.