Back to topic
Spark playbook scenarios · Spark: AI Store Assistant

Generate advertising creatives from a repeatable brief

Creative is needed for many products and channels, and comparing the results only works if every request runs through one documented brief. In this case, the immediate task is to generate advertising creatives from a repeatable brief. The workflow should return the creatives with the filled brief attached and flag any field the merchant's records left empty.

Topic
Ad Creative and Copy Generation
Target keyword
shopify automated ad creative generation
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 generate advertising creatives from a repeatable brief.
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 brief template fields for product facts, audience, offer, format, tone and approval rules, filled from the merchant's product, offer and channel records]. Run every request through the same template and the same step order so two runs differ only in their inputs, and stop the run at any empty field instead of filling it from a similar product or an earlier campaign.
Return the generated creatives with the filled brief attached and any field the supplied records left empty flagged 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.
Use in Spark
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.

01

Step 1

Fix the brief template first with one field for each product fact, audience, offer, format, tone and approval rule, and fill it from the merchant's product, offer and channel records rather than from the previous run's output.

02

Step 2

Run every request through the same template and the same step order so two runs differ only in their inputs, and stop the run at any empty field instead of filling it from a similar product or an earlier campaign.

03

Step 3

Deliver each generated creative with its filled brief attached and every unresolved field flagged with the record needed to fill it, then reconcile the number of creatives produced with the number of products and channels requested and confirm that no creative shipped with a flagged field still open.

FAQ

Common questions when running this scenario

Cover decision rules, frequent misunderstandings, and required inputs so the team aligns on prerequisites before execution.

Why fill the brief from records rather than the last run?

A brief copied from the previous run inherits that product's claims and offer, which is how an expired promotion reaches a new creative; filling from the current product and offer records keeps each run independent and auditable.

What should an empty brief field produce?

A flag naming the record needed, never a guessed value, because the whole point of the template is that two runs stay comparable, and a guessed field silently breaks that comparison while looking complete.

How is output compared across products and channels?

By the brief, since identical step order and identical fields make any difference in the creatives traceable to an input; where two runs used different fields, the outputs are marked non-comparable rather than ranked.

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.