Candidates are assessed ad hoc, so outcomes cannot be compared across the evaluation set or justified afterwards. In this case, the immediate task is to evaluate product opportunities using a structured research workflow. The workflow should produce a per-candidate evaluation sheet with evidence and next tests, verified against the supplied records.
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 evaluate product opportunities using a structured research workflow.
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: [full candidate product list, dated demand evidence with sources, competitor listing prices, supplier cost and freight quotes, the merchant's stated minimum margin rule, and unconfirmed supplier claims]. Run every candidate through the same ordered checks of demand evidence, landed cost against the stated margin rule and competitive exposure, recording for each check whether it passed, failed or could not be completed because an input is missing.
Return a per-candidate evaluation sheet with evidence and next tests, verified against the supplied records 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.
Assemble the full candidate list with each item's dated demand evidence and its source, competitor listing prices, quoted supplier cost and freight terms, the merchant's stated minimum margin rule, and any supplier claims that still lack confirmation.
Run every candidate through the same ordered checks of demand evidence, landed cost against the stated margin rule and competitive exposure, recording for each check whether it passed, failed or could not be completed because an input is missing.
Deliver an evaluation sheet with one row per candidate showing each check result, the evidence cited, missing inputs and the next test to run, then verify that every candidate on the input list appears exactly once with a decision or an incomplete flag.
Cover decision rules, frequent misunderstandings, and required inputs so the team aligns on prerequisites before execution.
The check is marked incomplete with the missing input named, such as an unquoted freight cost, and the candidate keeps its other results; the rule matters because a silent guess would lock in a ranking that changes the moment the real figure arrives, and the candidate can still advance once the input is supplied.
The fixed order keeps judgments comparable across the evaluation set, since a candidate dropped early on demand is never scored as if it had cleared demand; abandoning the order midway lets personal preference decide which check matters, and any comparison drawn from mixed sequences is not defensible afterwards.
Claims that only the supplier asserts, such as production capacity or material grade, are carried as unverified inputs and never counted as passing a check; they matter because a shortlist built on them inherits the supplier's optimism, and each claim is listed with the confirmation step that would make it usable.
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.