01
Step 1
Start from the catalog's categories, the product attributes and variants actually in stock, the audience and buyer stages the merchant describes, and the keyword evidence supplied, recording which items are live and which are only planned.
Back to topic
Spark playbook scenarios · Spark: AI Store Assistant
Find keyword opportunities that fit the catalog
Topic ideas arrive from generic tools without anyone checking whether the store actually sells anything matching them. In this case, the immediate task is to find keyword opportunities that fit the catalog. The workflow should produce the opportunity shortlist and research priorities rooted in the merchant's own product attributes.
Topic
Keyword Research and SEO Opportunities
Target keyword
shopify keyword opportunity finder
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 find keyword opportunities that fit the catalog.
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 catalog's categories, the product attributes and variants actually in stock, the audience and buyer stages the merchant describes, and the supplied keyword evidence]. Test each candidate term against those items by asking which live product or collection would win the click and whether the store can serve the intent behind it, keeping only terms with a concrete destination and dropping or deferring terms whose best match is out of stock or unplanned.
Return the opportunity shortlist mapped to pages, verified against the catalog and supplied evidence 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
Test each candidate term against those items by asking which live product or collection would win the click and whether the store can serve the intent behind it, keeping only terms with a concrete destination and dropping or deferring terms whose best match is out of stock or unplanned.
03
Step 3
Deliver the opportunity shortlist with each term's destination page, matched items, intent, supporting evidence and expected buyer stage, then verify against the supplied catalog that every listed destination exists or is explicitly marked as to be built, and that no term points at a discontinued item.
FAQ
Common questions when running this scenario
Cover decision rules, frequent misunderstandings, and required inputs so the team aligns on prerequisites before execution.
How is an opportunity different from any keyword with volume?
An opportunity must have a destination the store can serve now: a live product, collection or page that answers the intent; a term whose best match is a discontinued item or an unbuilt page is recorded as deferred, with the missing piece named.
Should terms be judged on volume before fit?
Fit first, because traffic that lands on a page with nothing to buy wastes the visit; volume then orders the shortlist among terms that already fit, and a low-volume term with an exact catalog match can outrank a broader one.
How do we avoid two pages chasing the same term?
Assign one owner page per term in the shortlist and mark close variants as secondary to it, so the map shows which page should rank; where two existing pages already target the same intent, the overlap is flagged for consolidation instead of adding a third.
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.