01
Step 1
Build a baseline of every competitor SKU in the watched categories from the full result set rather than the visible first screen, each carrying its identifier, title, category, listing URL and first-seen date.
Back to topic
Spark playbook scenarios · Spark: AI Store Assistant
Detect new products in competitor assortments
Without a baseline, a weekly snapshot cannot show whether an unfamiliar SKU is new or merely edited. In this case, the immediate task is to detect new products in competitor assortments. The output should mark unmatched SKUs as new rather than edited and separate confirmed launches from relisted items.
Topic
Competitor Research and Monitoring
Target keyword
shopify competitor new product alerts
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 detect new products in competitor assortments.
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: [a baseline of competitor SKUs built from the full result set, each carrying its identifier, title, category, listing URL and first-seen date]. Diff later snapshots against that baseline keyed on identifier rather than title, treating an unmatched identifier as new, a changed title on a known identifier as an edit, and a reappearing identifier previously recorded as absent as relisted rather than launched.
Return a competitor change log and specific opportunities to investigate separating confirmed launches from relisted items 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
Diff later snapshots against that baseline keyed on identifier rather than title, treating an unmatched identifier as new, a changed title on a known identifier as an edit, and a reappearing identifier previously recorded as absent as relisted rather than launched.
03
Step 3
Deliver an alert feed separating confirmed launches from relistings with the snapshots behind each row, verify that every new identifier is written into the baseline afterwards so the next diff stays clean, and note where a rename could have hidden an earlier listing.
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 a new SKU told apart from a renamed one?
By keying on the identifier rather than the title. A title change on a known identifier is an edit, an unfamiliar identifier is new, and where neither identifier nor title matches anything previously recorded the row is flagged for manual confirmation.
Can a returned product masquerade as new?
Yes, and the baseline is what prevents it. An identifier that appeared earlier, went absent and came back is a relisting, so every candidate row must be checked against the whole baseline rather than against the previous snapshot alone.
What makes a new-product alert actionable?
The identifier, category, first-seen date, source page and the two snapshots showing absence then presence, so anyone can run the check again. An alert reaching the merchant without both snapshots behind it stays unconfirmed.
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.