Shoppers drop off between landing and checkout, yet nobody has walked the pages like a visitor would. In this case, the immediate task is to audit website issues affecting the shopping experience. The workflow should follow the supplied URLs from landing page to cart, recording where a visitor gets blocked, misled or slowed and which pages are affected.
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 audit website issues affecting the shopping experience.
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 URLs the merchant supplies for landing page, collection, product, cart and the first checkout screen, the device and entry path used for each pass, and the repeat-observation record for every page]. Classify each observation as blocking, misleading or merely slow, and set aside anything seen once and never reproduced as unconfirmed rather than as a finding, so the list carries only what a visitor would actually meet.
Return a website issue list with affected pages 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.
Open each URL the merchant supplies in the order a shopper would meet it, from landing page through collection, product, cart and the first checkout screen, recording for every page the device and entry path used, the element that blocks, misleads or slows the visit, and whether the same behaviour repeats on a second pass.
Classify each observation as blocking, misleading or merely slow, and set aside anything seen once and never reproduced as unconfirmed rather than as a finding, so the list carries only what a visitor would actually meet.
Deliver the issue list with the affected URL, the step in the path where it appears, its classification and the page it pushes the shopper to, then re-walk the corrected pages and confirm that the row count matches the URLs supplied and that nothing marked blocking remains open.
Cover decision rules, frequent misunderstandings, and required inputs so the team aligns on prerequisites before execution.
At least two passes on the same device and entry path, with the observation recorded both times. A single pass can catch a transient network stall or a cached state, so repeating the walk separates a stable defect from a moment.
Report it with the observed cause named rather than as a defect by default. Heavy media, third-party scripts and theme settings all produce delay, and the fix differs for each, so the report should say what was seen slowing the page.
Record it as unreachable with the response seen and keep it on the list. Dropping it quietly hides a blocking problem that a shopper would meet at exactly that step of the path.
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.