Traffic has grown while orders have stayed flat, and the merchant cannot see what those extra sessions are doing. In this case, the immediate task is to diagnose why substantial store traffic produces few sales. The workflow should produce a conversion diagnosis and experiment backlog, contrasting landing pages with the merchant's order 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 diagnose why substantial store traffic produces few sales.
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: [sessions and landing pages split by source for the defined window and a comparable earlier window, product views, add-to-cart events, orders with line items and currency, the page type of each landing page, and the merchant's stated minimum visit count].
Compare the composition of traffic with the composition of orders by source and by landing page, marking as non-product traffic those sessions whose records show no product view, and treating a source or page as a suspect only where its visit count is above the merchant's stated minimum and its orders still fail to appear in the order export.
Return a conversion diagnosis and experiment backlog with the gap verified against the merchant's 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.
Pull, for one merchant-defined window and for a comparable earlier window the merchant names, sessions and landing pages split by source, product views, add-to-cart events and orders with their line items and currency, marking each landing page as a product, collection or content page and recording the products each order actually contained.
Compare the composition of traffic with the composition of orders by source and by landing page, marking as non-product traffic those sessions whose records show no product view, and treating a source or page as a suspect only where its visit count is above the merchant's stated minimum and its orders still fail to appear in the order export.
Deliver a conversion diagnosis and an experiment backlog naming each suspect source or landing page with its visits, product views, add-to-carts and orders, then reconcile the order total with the merchant's order export for the same window and currency, and report separately any page whose view count falls below the merchant's stated minimum.
Cover decision rules, frequent misunderstandings, and required inputs so the team aligns on prerequisites before execution.
A session is counted as not reaching a product when its event records contain no product view anywhere in the window, so landing on a blog post and leaving counts as well. This keeps the diagnosis on the merchant's records rather than on figures from another tool; sessions with incomplete event records are listed as unmeasured.
Yes. Each source is read with its own landing pages and order count, because sending many visits to a content page is not the same job as sending few visits to a product page, and a weak rate is then read in context. Sources below the merchant's stated minimum visit count are reported with raw counts only.
The comparison window should be one the merchant can reproduce from the same records, and it is recorded alongside the result. If the traffic growth is recent, the earlier window is taken from before that growth so the change is not averaged away; where no comparable window exists, the finding is reported as a single-window observation and flagged as unconfirmed.
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.