Add-to-cart behavior shifts quickly, and the merchant only notices it once the weekly report is already out of date. In this case, the immediate task is to monitor changes in add-to-cart rates. The workflow should produce conversion alert rules and diagnostic next steps, each one calibrated to the volumes and baselines in the merchant'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 monitor changes in add-to-cart rates.
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 add-to-cart numerator with its session deduplication rule, the chosen denominator applied everywhere, the baseline window, the segments to watch including device, channel and collection, and the merchant's stated minimum event counts].
Compare each segment's current rate with its baseline value and raise an alert only where the segment clears the stated minimum counts and the movement holds for the consecutive periods the merchant names, checking first whether a change in the denominator or in the products on sale explains the movement.
Return conversion alert rules and diagnostic next steps with every threshold 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.
Define the add-to-cart numerator with the rule that decides whether one session adding several products counts once or several times, define the denominator as product views or sessions and apply it everywhere, then record the baseline window, the segments to watch such as device, channel and collection, and the merchant's stated minimum event counts.
Compare each segment's current rate with its baseline value and raise an alert only where the segment clears the stated minimum counts and the movement holds for the consecutive periods the merchant names, checking first whether a change in the denominator or in the products on sale explains the movement.
Deliver conversion alert rules and diagnostic next steps with the baseline, the gates and the segment recorded for each, then replay them against the supplied add-to-cart and view counts and report which alerts would have fired, which were suppressed by a gate, and what each would have asked the merchant to check.
Cover decision rules, frequent misunderstandings, and required inputs so the team aligns on prerequisites before execution.
The merchant's stated rule decides it, and the same rule is applied to the baseline and to the current period. Counting one event per session measures how many visitors engaged, while counting per product measures how much was added; mixing the two across periods produces a movement that exists only in the arithmetic.
Before an alert is raised, the denominator is checked for a change in definition or coverage and the merchant's records are checked for products that went out of stock or changed price in the window. A rate that moved because the denominator changed is not a behavioural alert; those cases are reported as a definition issue.
The baseline is refreshed at the cadence the merchant sets and always after a change to the catalog, the tracking or the segment definitions, with the old value kept for comparison. Refreshing without keeping the record makes earlier alerts impossible to reproduce; refreshing too rarely lets a slow drift read as a sudden alert.
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.