01
Step 1
Open the original image files together with the annotation request naming each detail to call out, the verified label wording recorded for those details, and the output size and format the image must be delivered in.
Back to topic
Spark playbook scenarios · Spark: AI Store Assistant
Add clear annotations to verified product details
Buyers keep missing one detail in the photos, so the merchant wants it called out directly on the image. In this case, the immediate task is to add clear annotations to verified product details. The workflow should produce an annotated file or marked brief in which every label sits against the detail it describes and matches the recorded wording.
Topic
Product Image Editing
Target keyword
product image annotation tool
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 add clear annotations to verified product details.
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 original image files, the annotation request naming each detail to call out, the verified label wording recorded for those details, and the required output size and format]. Place each label against the detail it names with a leader that crosses no other label, keep the label clear of the feature it points at, and refuse any callout naming a detail the image does not actually show.
Return the annotated file or a marked 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
Place each label against the detail it names with a leader that crosses no other label, keep the label clear of the feature it points at, and refuse any callout naming a detail the image does not actually show.
03
Step 3
Deliver the annotated file or a marked brief with the label positions and wording, then compare every label against the supplied specifications, check legibility at the stated output size and list any requested detail that could not be annotated.
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 two requested details sit close together?
Offset the leaders and stagger the labels rather than shrinking the type. Overlapping callouts, or text too small at the stated output size, leave both details unreadable and defeat the point of the annotation.
Should the label wording come from the brief or the specification?
From the recorded specification where one exists, because the brief may paraphrase. Where the two differ, flag the difference and use the specification wording, since that is what the product record supports.
How is an annotated file verified before delivery?
Re-read each label against the specification and view the file at the stated output size. A label that reads clearly in the editor can still be illegible once the image is scaled for the page.
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.
Improve the presentation of an existing product photograph
Apply a consistent watermark to owned product images
Upscale a product image while reviewing detail accuracy
Create a visual brief highlighting real product details
Turn verified product features into concise bullet points
Explain product benefits in terms relevant to the buyer
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.