01
Step 1
List every published page with its URL, handle, target topic and the terms it currently ranks for or is assigned, together with the catalog collections it covers and the keyword evidence the merchant holds for those topics.
Back to topic
Spark playbook scenarios · Spark: AI Store Assistant
Identify unanswered topics in the existing content
Existing guides keep circling the same handful of topics while buyers ask things no page answers. In this case, the immediate task is to identify unanswered topics in the existing content. The workflow should produce a keyword-to-page map and research priorities derived from the merchant's own pages and keyword evidence.
Topic
Keyword Research and SEO Opportunities
Target keyword
shopify content gap analysis
Copyable AI prompt
A prompt you can drop directly into Spark
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.
ai-prompt.txt
Act as a Shopify operations specialist.
Help me identify unanswered topics in the existing content.
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: [every published page with its handle, target topic and assigned terms, the catalog collections each page covers, and the keyword evidence the merchant holds]. Mark as a gap each buyer question that no published page answers in its own copy, distinguishing it from a term that is simply absent while the answer already exists, rank the gaps by catalog coverage and the evidence held, and mark unsupported ones as hypotheses.
Return a keyword-to-page map and research priorities confirmed 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.How to solve
A recommended resolution workflow
Split the work into input, judgment, and deliverable phases. Verify each step's output before moving to the next.
02
Step 2
Mark as a gap each buyer question that no published page answers in its own copy, distinguishing it from a term that is simply absent while the answer already exists, rank the gaps by catalog coverage and the evidence held, and mark unsupported ones as hypotheses.
03
Step 3
Deliver a keyword-to-page map showing each gap with the question, the page that should own it or the new page it requires, the evidence and the priority, then confirm every gap traces to a published page's missing answer and that no mapped term duplicates an existing page's target.
FAQ
Common questions when running this scenario
Cover decision rules, frequent misunderstandings, and required inputs so the team aligns on prerequisites before execution.
How do we tell a gap from a page that just ranks poorly?
A gap is a question no published copy answers at all, while a ranking problem is an answered question that is not being found; the first need is new or extended content, the second is a page or promotion issue, and the two go into different backlogs.
Should a gap always close with a new page?
No: when an existing page already targets the same intent, the cheaper fix is to extend that page's answer, and a new page is reserved for a question no current page can absorb without competing with its own target term.
What keeps the gap list evidence-based?
Every gap cites the record that supports it, such as a term with tracked data or a repeated customer question, and anything without such a source is labelled a hypothesis and ranked below the evidenced items rather than being presented as a finding.
Related scenarios
Continue with adjacent or same-topic scenarios
Start with scenarios under the same topic, then expand into cross-topic matches suggested by similarity.
Next step
Want these AI scenarios embedded directly into daily operations?
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.