Research tends to start from whatever terms someone remembers rather than from what the store actually sells. In this case, the immediate task is to build a relevant keyword research shortlist. The workflow should produce a keyword-to-page map and research priorities anchored in the merchant's own catalog.
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 build a relevant keyword research shortlist.
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 seed terms on record with their origin, the product catalog with categories and attributes, the target market and language, and any keyword evidence the merchant holds]. Match every candidate term to at least one live catalog item or a planned one, group terms by the buying task behind them, and drop terms with no plausible catalog match or whose intent the store cannot serve, marking the dropped ones with the reason rather than deleting them silently.
Return a ranked research shortlist with page assignments, with scope verified against the merchant's 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 seed terms already on record, the product catalog with its categories and attributes, the target market and language, and any keyword evidence the merchant holds, recording for each seed term where it came from so the source can be cited later.
Match every candidate term to at least one live catalog item or a planned one, group terms by the buying task behind them, and drop terms with no plausible catalog match or whose intent the store cannot serve, marking the dropped ones with the reason rather than deleting them silently.
Deliver a ranked research shortlist with each term's matched catalog items, intended page, evidence and confidence, then verify the term count against the seed list plus expansions and confirm every retained term traces to a real catalog item and a stated source.
Cover decision rules, frequent misunderstandings, and required inputs so the team aligns on prerequisites before execution.
A term is kept when at least one live catalog item can answer it under its own attributes, and it is dropped when the store can only serve it by stretching a category; the reason is recorded for every dropped term, so the decision can be revisited when the catalog changes.
Yes, as candidates marked unmeasured, because excluding them hides demand the tracking data has not yet covered; they sit in a separate section of the shortlist and carry no priority until the merchant's records or a later review supports them.
Require each entry to name the catalog items and the buyer task behind it; a broad category word survives only where it maps to a real collection page, and anything that needs a new page is labelled with the page it would require.
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.