A ranking report circulates every month, but nobody can separate the measured movements from the assumed ones. In this case, the immediate task is to review keyword performance and identify research priorities. The workflow should produce a keyword-to-page map and research priorities rechecked against the merchant's own tracking 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 review keyword performance and identify research priorities.
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: [each tracked term with its assigned page, the reporting window the data covers, the source and definition behind every metric in that window, the matching prior window used as baseline, and the date each term entered tracking].
Compare each term against its own baseline in the same window length and on the same page, mark as measured only movements supported by records from both windows, mark as unmeasured any movement where the page assignment, tracking setup or metric definition changed, and set aside terms whose history is too short to compare rather than reading a trend into them.
Return the review with research priorities, rechecking each claim 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.
Collect each tracked term with the page assigned to it, the reporting window the merchant's data covers, the source and definition behind every metric in that window (impressions, clicks, position or orders), the matching prior window used as baseline, and the date each term entered tracking so new entries can be separated from established ones.
Compare each term against its own baseline in the same window length and on the same page, mark as measured only movements supported by records from both windows, mark as unmeasured any movement where the page assignment, tracking setup or metric definition changed, and set aside terms whose history is too short to compare rather than reading a trend into them.
Deliver a keyword-to-page map with each term's measured movement, baseline, evidence source and a research priority, then recheck every claim against the supplied records and list separately the terms marked unmeasured or insufficient.
Cover decision rules, frequent misunderstandings, and required inputs so the team aligns on prerequisites before execution.
Because a term's movement is only meaningful against the same page and the same window length, and using one shared baseline hides that some pages changed while others did not; where no matching prior window exists the term is recorded as insufficient, not as declining.
A change counts as measured only when both windows carry records from the same source and definition and the page assignment is unchanged; if the tracking setup, the page or the definition changed in between, the movement is labelled unmeasured and listed for rechecking instead of being reported as a result.
It is marked insufficient and kept on the map with its page, because sparse records cannot separate a real movement from noise; the term becomes eligible for review once it has a comparable window, and until then no priority is derived from it.
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.