The merchant owns product photography but no footage, and the ad has to work in a feed where most viewers watch with the sound off. In this case, the immediate task is to draft a short product video ad. The workflow should produce a video-ad script and production brief noting which shots can be cut from existing assets and which still need filming.
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 draft a short product video ad.
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 owned product images and clips with their orientation and usable crop, the single message the ad must land, the placement aspect ratio and whether it plays muted by default, and the merchant's intended cut length]. Sequence shots so the product, its scale and the payoff read with sound off, assign one claim or one visual beat per shot, and prefer owned assets that already carry the beat while marking every beat whose footage, framing or proof is missing.
Return a video-ad script and production brief, noting which assets exist and which still need to be produced 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.
Take the product images and clips the merchant already owns with their orientation and usable crop, the single message the ad has to land, the placement's aspect ratio and whether it plays muted by default, and the length the merchant wants the finished cut to run.
Sequence shots so the product, its scale and the payoff read with sound off, assign one claim or one visual beat per shot, and prefer owned assets that already carry the beat while marking every beat whose footage, framing or proof is missing.
Deliver a video-ad script and production brief naming for each shot its source asset, on-screen caption, planned motion treatment and whether it exists already or must be filmed, then check the plan by summing the intended shot durations against the merchant's cut length and listing every asset used alongside anything still to be created.
Cover decision rules, frequent misunderstandings, and required inputs so the team aligns on prerequisites before execution.
Yes for feed placements that start muted, so the product and its offer must read from picture and caption alone; narration can add emphasis for viewers who turn audio on, but nothing essential belongs only in the soundtrack.
Yes when the photos show the product large and well lit, because pacing, zooms and cuts give stills motion; the brief should state practical limits though, since images shot small in frame or cropped tightly cannot be enlarged without losing the detail the shot depends on.
Put the product and the benefit it delivers in front of the viewer straight away, since nobody has committed to watching yet; brand marks, scene-setting and long build-ups belong later, once viewers already know what is being sold.
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.