The catalog is ready to widen, but past buys have peaked right after they were ordered. In this case, the immediate task is to identify emerging product trends before expanding the catalog. The workflow should produce a shortlist of emerging candidates, each with its evidence window and a small validation test, drawn from the dated signals supplied.
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 identify emerging product trends before expanding 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: [recent dated demand signals with sources, listing and search evidence, current catalog boundaries, sourcing lead times, and per-signal observation windows]. Separate rises sustained across consecutive periods from single-window spikes, test each sustained candidate for fit with the existing assortment and audience, and mark anything whose evidence window is too short to distinguish the two.
Return a shortlist of emerging candidates with the evidence window for each and a small validation test 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.
Pull the most recent dated demand signals available with their sources, listing or search evidence for the same periods, the merchant's current catalog boundaries, and the sourcing lead times that determine how early a trend must be caught.
Separate rises sustained across consecutive periods from single-window spikes, test each sustained candidate for fit with the existing assortment and audience, and mark anything whose evidence window is too short to distinguish the two.
Deliver a shortlist of emerging candidates each with its evidence window, its fit read and a small validation test sized to the lead time, then check that every signal cited carries its date and source from the supplied records.
Cover decision rules, frequent misunderstandings, and required inputs so the team aligns on prerequisites before execution.
By whether the rise persists across consecutive dated periods, since a fad spikes once and recedes; a candidate with only one strong window is marked unjudgeable rather than promoted, and the persistence read names the periods it covers.
Because a trend that peaks before stock can arrive is not an opportunity at this speed, so each candidate's viability is checked against the sourcing lead time; ones that cannot be landed in time are dropped with the timing reason recorded.
The smallest exposure that yields a decision before full commitment, such as a limited listing run with a written success condition; it is scheduled so the result arrives before the ordering window closes, which the lead-time check in the plan ensures.
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.