A campaign has an objective and a defined audience on file, but the concepts proposed so far vary only in colour, crop and wording. In this case, the immediate task is to create distinct advertising creative concepts. The workflow should produce concepts differing in core message, each carrying its target audience and the check that would show it worked.
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 create distinct advertising creative concepts.
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: [the campaign objective, the audience definition and its purchase reason, the brand rules, per-channel format limits, and the product and offer records with the merchant's approved claims].
Build each concept around a different core message drawn from those records, rejecting any two concepts that differ only in colour, crop or wording, and dropping any concept whose central claim has no line in the supplied records to support it.
Return the concepts with the intended audience and success check for each, confirmed against the supplied constraints 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.
Collect the campaign objective, the audience definition with the reason that audience buys, the brand rules, the format limits of each channel, and the product and offer records on file, keeping the claims the merchant has approved separate from anything inferred.
Build each concept around a different core message drawn from those records, rejecting any two concepts that differ only in colour, crop or wording, and dropping any concept whose central claim has no line in the supplied records to support it.
Deliver the concepts with the audience each targets, the message it leads on, the supporting record and the success check that would show it worked, then verify the concept count against the number of distinct messages identified and list every claim removed for lacking support.
Cover decision rules, frequent misunderstandings, and required inputs so the team aligns on prerequisites before execution.
Write the core message of each concept in one sentence and compare them, because two concepts that can be summarised by the same sentence are one concept with different decoration; the message, not the visual treatment, is what the later test reads.
It is dropped or rewritten around a claim the records do carry, since an unapproved claim cannot be verified later and would leave the store defending a promise it never made.
One audience per test so the message is the only difference; concepts aimed at different audiences belong to separate campaigns, because otherwise a weaker result may simply mean that audience was colder.
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.