Step 1
Collect product view counts and cart addition counts for one period together with the breakdown by device, page and variant that the supplied records carry, counting one view per page per session and one addition per variant per session.
Product pages get traffic but carts stay empty, and view and addition counts by device, page and variant are available for one period. In this case, the immediate task is to locate losses between product views and cart additions. The workflow should return loss points ranked by size, with the evidence behind each drop.
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 locate losses between product views and cart additions.
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: [product views counted once per page per session, cart additions counted once per variant per session, and the breakdown by device, page and variant for the period]. Compute the step rate between views and additions for every segment and rank the segments by the number of sessions lost rather than by the lowest rate, then test each large loss against stock status, variant selection and page faults and mark any loss that no available record explains as unexplained rather than attributing it to a cause.
Return the funnel analysis with each loss point ranked and its evidence from 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.
Collect product view counts and cart addition counts for one period together with the breakdown by device, page and variant that the supplied records carry, counting one view per page per session and one addition per variant per session.
Compute the step rate between views and additions for every segment and rank the segments by the number of sessions lost rather than by the lowest rate, then test each large loss against stock status, variant selection and page faults and mark any loss that no available record explains as unexplained rather than attributing it to a cause.
Deliver the funnel analysis with each loss point ranked by size and the evidence behind it, then verify it by confirming that the sessions across all segments sum to the period total and that no session is counted in two segments.
Cover decision rules, frequent misunderstandings, and required inputs so the team aligns on prerequisites before execution.
By the number of sessions lost, because a steep rate on a small segment can hide a shallow rate on a large one that costs far more sessions. Both figures are shown side by side so the ranking reflects size while the rate keeps the comparison fair across segments.
One view per page per session and one addition per variant per session, so reloading a page or tapping the control twice does not inflate either step. Without that rule a slow-loading page looks like strong interest and a double tap looks like two shoppers.
It is reported as unexplained with the segment and the size of the gap, and the additional record needed to decide is named. Inventing a cause to fill the row leads the operator to change a page that was never the problem.
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.