A long list of URLs with vague indexing complaints has piled up, and the merchant needs to know which to chase first. In this case, the immediate task is to prioritize evidence-based indexing checks. The workflow should order the reported URLs by discovery, crawl access, canonical selection and reported status, so confirmed blockers come first.
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 evidence-based indexing checks.
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 reported URLs with the indexability the merchant intends for each, their crawl signals, declared canonicals, sitemap presence, the internal paths reaching them, and the dates of the reports behind each complaint]. Order them so URLs with a confirmed contradiction such as blocked access, an error status or a canonical that conflicts with intent come first, those with only a suspected weakness such as thin or overlapping content follow, and those with no usable record sit last as unconfirmed, noting for each the last stage it passed.
Return a URL-level diagnosis with evidence and follow-up checks, ranked so confirmed blockers come first 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.
Assemble the reported URLs with the indexability the merchant intends for each, the crawl signals on record, the canonical each declares, its sitemap presence, the internal paths reaching it and the dates of the reports behind the complaint.
Order them so URLs with a confirmed contradiction such as blocked access, an error status or a canonical that conflicts with intent come first, those with only a suspected weakness such as thin or overlapping content follow, and those with no usable record sit last as unconfirmed, noting for each the last stage it passed.
Deliver a URL-level diagnosis with evidence and follow-up checks ranked so confirmed blockers come first, restating each vague complaint as the stage and the record that would settle it, then confirm that every URL from the intake appears in the output with a stage, a rank and the next check assigned.
Cover decision rules, frequent misunderstandings, and required inputs so the team aligns on prerequisites before execution.
A record that directly contradicts indexing, such as blocked crawl access, an error status or a canonical pointing away from the page meant to rank. Those are cheap to confirm and cheap to fix, so they outrank pages where the evidence is only circumstantial and would need a longer investigation.
Restate it as a claim about one stage and name the record that would confirm or refute it, so a complaint about a page not ranking becomes whether the URL was fetched and which canonical it declared. Complaints that cannot be restated that way are logged as unconfirmed with the missing input named.
Only where the merchant confirms the page is not intended to be public; otherwise it keeps a rank. Dropping URLs silently destroys the evidence that they were reported, and the same complaint then returns in the next review with no record of the earlier decision.
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.