01
Step 1
Capture each supplied competitor listing page with the sort order applied, the rank and badge labels shown, review counts, stock or restock messages, and the date, shipping destination and currency in force for that view.
Back to topic
Spark playbook scenarios · Spark: AI Store Assistant
Investigate the products competitors appear to prioritize
Public listing pages display ranking, placement and review signals, but the merchant has never recorded what those signals suggest. In this case, the immediate task is to investigate the products competitors appear to prioritize. The output should list the products recurring across the supplied sources together with the signal behind each one.
Topic
Competitor Research and Monitoring
Target keyword
find competitor best selling products
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 investigate the products competitors appear to prioritize.
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: [competitor listing pages with the applied sort order, rank and badge labels, review counts, stock messages, and the date, shipping destination and currency in force for each capture]. Treat those displays as evidence of the seller's own emphasis rather than as measured demand, recording which products carry several signals across independent sources and never scoring a product on a signal the dated page did not actually show.
Return a competitor change log and specific opportunities to investigate citing the observed signals 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
Treat those displays as evidence of the seller's own emphasis rather than as measured demand, recording which products carry several signals across independent sources and never scoring a product on a signal the dated page did not actually show.
03
Step 3
Deliver a prioritised shortlist where every row names the signal, its source page and the observation date, reconcile the entries against the number of supplied sources so none were read selectively, and restate each finding as something to investigate.
FAQ
Common questions when running this scenario
Cover decision rules, frequent misunderstandings, and required inputs so the team aligns on prerequisites before execution.
Do public rankings prove competitor sales?
No, because a badge or a leading position shows what the seller chose to promote, which can follow margin or inventory rather than unit demand. Each row is therefore filed as a signal worth investigating and never as a sales figure anyone should quote.
How much weight does a single signal carry?
Little on its own. A product carrying the same signal across several independent sources observed on different dates earns attention, while one badge seen once is recorded and left at the bottom of the shortlist until further passes add support.
Why record the sort order used on each capture?
Many default orders are merchandising choices rather than popularity rankings, and some rotate between visits. Noting the sort applied separates a genuinely held position from whatever that particular arrangement happened to surface on the day.
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.
Track observable competitor stock changes
Track prices for comparable competitor products
Identify gaps and emphasis in competitor product catalogs
Build a structured competitor research brief
Identify relevant competitors from supplied advertising examples
Compare a competitor's product assortment with your own
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.