Step 1
Collect the affected product pages, the viewport widths reported, the device and browser models, the touch interactions described, and the view-to-addition counts split by device for the same period.
Mobile visitors add to cart less often than desktop visitors, and the pages, viewports, touch interactions and funnel counts are on record. In this case, the immediate task is to check the usability of the add-to-cart control on mobile. The workflow should return a diagnosis of the small-screen state and a retest path per device.
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 check the usability of the add-to-cart control on mobile.
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 affected product pages, the reported viewport widths, the device and browser models, the described touch interactions, and the view-to-addition counts split by device for the same period]. Inspect the control in its small-viewport state for target size, spacing from neighbouring controls, position after scrolling and overlap with sticky headers, banners or cart bars, classifying each finding as blocking when the control is unreachable or covered and as friction when it is visible but hard to hit.
Return an add-to-cart diagnosis and verification checklist, with the reported path retested on each supplied device 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 the affected product pages, the viewport widths reported, the device and browser models, the touch interactions described, and the view-to-addition counts split by device for the same period.
Inspect the control in its small-viewport state for target size, spacing from neighbouring controls, position after scrolling and overlap with sticky headers, banners or cart bars, classifying each finding as blocking when the control is unreachable or covered and as friction when it is visible but hard to hit.
Deliver the diagnosis with the blocking findings first and a retest path per reported device, then verify it by walking the recorded path on each named device and confirming that the control is reachable and that the cart updates without a further obstacle.
Cover decision rules, frequent misunderstandings, and required inputs so the team aligns on prerequisites before execution.
Being unreachable or covered at the moment of the tap, for instance beneath a sticky cart bar or behind a consent banner, is blocking. A control that is merely small or close to its neighbour is friction, and the two are listed separately because only the first stops the purchase outright.
Sticky headers and cart bars shift and overlay the control as the page moves, so a control clear on load can be covered once the shopper reaches the buy area. The retest walks the real path from the product image to confirmation instead of inspecting a static screenshot.
It shows layout and overlap but not touch behaviour, autofill or the mobile keyboard, so emulator findings are confirmed on at least one real device per reported viewport. Where no real device is available, that limitation is written on the finding instead of presenting it as verified.
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.