01
Step 1
Collect the product reference, the audience and the offer terms exactly as signed off with their start and end dates, the channel's format and permitted length, and the approved claim list with the wording allowed to appear on screen.
Back to topic
Spark playbook scenarios · Spark: AI Store Assistant
Write a video-ad script for a specific offer
A campaign needs a video ad of a fixed length for one particular offer, and the claims allowed on screen have already been signed off. In this case, the immediate task is to write a video-ad script for a specific offer. The workflow should produce a video-ad script and production brief with timing marks for checking each claim against the approved list.
Topic
Video Ad Creation
Target keyword
ecommerce video ad script generator
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 write a video-ad script for a specific offer.
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 product reference, audience and signed-off offer terms with their start and end dates, the channel format and permitted length, and the approved claim list with its allowed on-screen wording]. Budget the stated length across hook, demonstration and call to action rather than speeding the narration up, use only wording from the approved claim list, and flag any line that still needs sign-off before it can be spoken or shown.
Return a video-ad script and production brief, with timing marks a reviewer can check against the brief 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
Budget the stated length across hook, demonstration and call to action rather than speeding the narration up, use only wording from the approved claim list, and flag any line that still needs sign-off before it can be spoken or shown.
03
Step 3
Deliver a video-ad script and production brief giving each beat its cumulative timing mark, spoken line, caption and shot together with the offer dates and expiry, then verify by timing a read-through and ticking every on-screen claim and promise back to the approved list.
FAQ
Common questions when running this scenario
Cover decision rules, frequent misunderstandings, and required inputs so the team aligns on prerequisites before execution.
What if the script runs longer than the permitted length?
Cut content rather than narration pace, because rushed delivery hides the offer and often breaks approved wording anyway; drop the weakest beat, usually a secondary feature, then retime the sections while leaving the hook and the call to action intact.
Can an approved claim be reworded to sound better?
No, only the reviewed wording may be spoken or captioned, since the claim was cleared in that exact form; a stronger line is worth putting to whoever signed it off, and until approval arrives the beat either uses the original wording or carries no claim at all.
Should price or discount details appear on screen?
Only when the amount is fixed for the whole flight and matches the page the shopper lands on; if the offer varies by date, audience or currency, show the offer name instead and re-check the number in the caption at each scheduled review.
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.