Step 1
Pull the verified use steps, the footage plan listing which shots exist for each step, the on-screen text the merchant requires, and the intended runtime for the finished video.
Use steps exist in the product notes but nobody has turned them into narration that fits the planned footage. In this case, the immediate task is to write a product video script from verified use steps. The workflow should produce narration beats with per-beat timing that match what the footage will show and the merchant's 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 write a product video script from verified use steps.
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: [verified use steps, the footage plan with shots per step, required on-screen text, and the intended runtime]. Convert the steps into narration beats so each beat describes only what its planned shot shows, assigning a duration to every beat, and flag steps that have no matching footage before writing around them.
Return a script with timing per beat, verified against the supplied records and footage plan 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.
Pull the verified use steps, the footage plan listing which shots exist for each step, the on-screen text the merchant requires, and the intended runtime for the finished video.
Convert the steps into narration beats so each beat describes only what its planned shot shows, assigning a duration to every beat, and flag steps that have no matching footage before writing around them.
Deliver the script with per-beat narration, shot reference and timing, then verify the beat durations sum to the intended runtime and every beat traces to a recorded use step.
Cover decision rules, frequent misunderstandings, and required inputs so the team aligns on prerequisites before execution.
They are flagged at the planning stage instead of receiving narration, because a voiced step with no shot either freezes the frame or promises content the edit cannot deliver; the flag is the trigger to shoot, cut or convert to on-screen text.
Beat-level durations let the narrator's pace be tested against the footage before recording, and their sum gives the runtime check; a script timed only as a whole hides which beats must be shortened.
Each beat's narration may state only what its referenced shot and the records show, so adjectives implying more than the demonstration are flagged in review rather than recorded.
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.