A raw export mixes informational lookups with purchase-ready searches, so one page ends up serving several intents at once. In this case, the immediate task is to group search terms by shared intent. The workflow should produce a keyword-to-page map and research priorities built from the merchant's own term list and 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 group search terms by shared intent.
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 raw term list with attached evidence, the catalog and collection structure, the pages the store already publishes, and the audience descriptions on record]. Cluster terms by the task and page intent behind them rather than by shared wording, keep brand terms apart from generic ones, assign each cluster to exactly one existing or intended page, and split any cluster whose members require different answers on the same page.
Return a keyword-to-page map and research priorities verified against the supplied records, noting any assignment gap 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 the raw term list with any evidence attached, the product catalog and collection structure, the pages the store already publishes, and the audience descriptions on record, noting for each term the wording and the page it currently lands on.
Cluster terms by the task and page intent behind them rather than by shared wording, keep brand terms apart from generic ones, assign each cluster to exactly one existing or intended page, and split any cluster whose members require different answers on the same page.
Deliver a keyword-to-page map listing every cluster with its member terms, the assigned page, the intent statement and the terms left unassigned, then verify that the term count across clusters equals the input list and that no page carries two clusters with conflicting intent.
Cover decision rules, frequent misunderstandings, and required inputs so the team aligns on prerequisites before execution.
Shared wording often covers different intents, so a cluster built on wording puts buyers with opposite needs on one page; the test is whether one page can answer every member, and where it cannot, the cluster is split even if the terms look alike.
Keep them in their own cluster mapped to the brand or store page, because visitors searching a name expect that destination and not a category answer; mixing them into a generic cluster makes the page try to serve both, which weakens the match for the generic terms.
It is listed as unassigned with the reason, usually a missing page or an intent the catalog does not serve; unassigned terms become either a content request or evidence that the term should leave the list, but they are never forced into a neighbouring cluster.
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.