01
Step 1
Take a dated baseline snapshot of each competitor's watched categories by paging through every result rather than the first screen, capturing each listed product identifier, title, listing URL and the category it appeared under.
Back to topic
Spark playbook scenarios · Spark: AI Store Assistant
Detect newly launched products in competitor catalogs
The merchant wants to react to competitor launches early but has no dated record of what was listed before. In this case, the immediate task is to detect newly launched products in competitor catalogs. The output should confirm each launch date and cite the snapshots that support it.
Topic
Competitor Research and Monitoring
Target keyword
track competitor product launches
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 newly launched products in competitor catalogs.
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 dated baseline snapshot of each competitor's watched categories taken across every result page, with each listed product identifier, title, listing URL and category placement]. Diff each later snapshot against that baseline and the candidates already logged, promoting an item to a confirmed launch only when it is absent from every earlier dated snapshot and present in a later one, and marking previously seen items as relisted or edited instead.
Return a competitor change log and specific opportunities to investigate citing the snapshots that support each launch 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 each later snapshot against that baseline and the candidates already logged, promoting an item to a confirmed launch only when it is absent from every earlier dated snapshot and present in a later one, and marking previously seen items as relisted or edited instead.
03
Step 3
Deliver a change log where each launch row cites the snapshot showing absence, the snapshot showing presence and the date observed, verify that new rows plus returned rows reconcile with the diff count, and keep unconfirmed candidates in a separate section.
FAQ
Common questions when running this scenario
Cover decision rules, frequent misunderstandings, and required inputs so the team aligns on prerequisites before execution.
What makes a launch confirmed rather than suspected?
A dated snapshot in which the item is absent, followed by one in which it appears, both covering the same category range. A single sighting with no earlier snapshot to compare against stays flagged as suspected until the next observation pass settles it.
How is a relisting kept out of the launch count?
Search the baseline and every earlier snapshot for the identifier before writing a new row. An item that was listed, withdrawn and returned is a relisting, and counting it as new quietly inflates how often the competitor is said to launch products.
Why capture the whole category instead of the top results?
Display order shifts between visits, so a product can slide below the captured window and reappear later looking new. A full category snapshot removes that false signal and keeps absent entries genuinely absent rather than merely unpaginated.
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.