01
Step 1
Collect the URLs to review, their current description fields, the visible page copy including the product details shown, and the topic each page targets.
Back to topic
Spark playbook scenarios · Spark: AI Store Assistant
Review meta descriptions for relevance and clarity
A merchant has product pages whose descriptions were never written for the page they sit on, leaving several blank or boilerplate. In this case, the immediate task is to review meta descriptions for relevance and clarity. The workflow should produce a per-URL reading of each description against the page copy, with a rewrite where it no longer matches.
Topic
SEO Metadata and Content Audits
Target keyword
shopify meta description checker
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 review meta descriptions for relevance and clarity.
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 URLs to review, their current description fields, the visible page copy, and the topic each page targets]. Read each description against its own page copy, flagging empty fields, boilerplate repeated word for word across pages, and wording that describes a different product or an outdated version, and mark pages whose copy is too thin to judge as unresolvable.
Return a metadata audit with per-URL revisions and flags for missing or boilerplate text 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
Read each description against its own page copy, flagging empty fields, boilerplate repeated word for word across pages, and wording that describes a different product or an outdated version, and mark pages whose copy is too thin to judge as unresolvable.
03
Step 3
Deliver the per-URL audit with a rewrite reflecting the visible copy wherever a mismatch was found, then verify each rewritten description mentions only details present on that page.
FAQ
Common questions when running this scenario
Cover decision rules, frequent misunderstandings, and required inputs so the team aligns on prerequisites before execution.
How is boilerplate detected across pages?
Descriptions are compared across the reviewed set, and strings repeated word for word across unrelated products are flagged as boilerplate, with the pages sharing them listed together. Short store-wide taglines that appear in every description are treated the same way. Boilerplate is a fact of the record, not a style opinion, so it is reported as an error.
What happens when the page copy is too thin to compare?
The URL is marked unresolvable, because a description cannot be judged against a page that shows almost nothing. The audit lists what the copy would need to show for a judgement to be possible. Unresolvable URLs are counted separately, so they do not inflate the mismatch figures.
What must a rewritten description stick to?
Only details visible on that page's own copy: the product shown, its stated features and the topic the page targets, within the stated length rule. Nothing from other products, discontinued versions or the reviewer's inference enters the text. The rewrite is verified line by line against the visible copy before it is delivered.
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.