An existing page converts below expectations, and the team holds a long list of unrelated ideas for fixing it. In this case, the immediate task is to prioritize improvements to an existing landing page. The workflow should produce a landing-page draft and improvement hypotheses checked against the merchant's own page and behaviour data.
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 prioritize improvements to an existing landing page.
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 live page with its section order and copy, the campaign or traffic source feeding it, the behaviour data held for the review window, the stated conversion goal, and the customer objections on record]. Rank the weaknesses by how directly they sit on the path to the stated action, propose the smallest change that would test each one, drop any idea whose effect cannot be observed with the behaviour data available, and mark hypotheses that depend on traffic the page does not currently receive as untestable for now.
Return the prioritized improvement list with hypotheses checked 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.
Gather the live page with its section order and copy, the campaign or traffic source feeding it, the behaviour data the merchant holds for the review window, the stated conversion goal, and the objections and questions customers have raised about this offer.
Rank the weaknesses by how directly they sit on the path to the stated action, propose the smallest change that would test each one, drop any idea whose effect cannot be observed with the behaviour data available, and mark hypotheses that depend on traffic the page does not currently receive as untestable for now.
Deliver the prioritized improvement list with each item's location on the page, the change proposed, the hypothesis it tests, the metric that would confirm it and the order in which to run them, then confirm every item traces to an observed weakness and list the ideas deferred for lack of data.
Cover decision rules, frequent misunderstandings, and required inputs so the team aligns on prerequisites before execution.
By how close it sits to the action: a mismatch between the campaign promise and the headline outranks a footer change, because the first blocks every visitor while the second affects few; ideas that need traffic or data the page does not have are deferred rather than ranked.
Only when they are independent and each has its own measurable signal; overlapping edits to the promise, proof and button make a result unreadable, so changes on the same step of the path are sequenced and the order is recorded.
When the page cannot deliver the campaign promise at all, for example when the offer or audience changed; otherwise targeted corrections to headline, proof or action usually move the goal faster, and a rebuild resets the evidence the merchant already holds.
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.