The collection holds products worth describing, but the current copy says nothing specific about the assortment or its intended searches. In this case, the immediate task is to draft informative collection descriptions. The output should be revised copy that explains the assortment using only attributes present in the merchant's product 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 draft informative collection descriptions.
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 collection's active product list with attribute values populated per variant, the existing published copy, the buyer searches the page should serve, and the merchant's terminology and banned-claims rules].
Draft description copy stating what the assortment contains, who it suits and how the options differ, using only attributes present in the supplied records and leaving every sentence that needs price, stock or delivery detail empty and marked as awaiting the merchant's values.
Return a collection-level SEO brief and revised copy with each claim checked against the merchant's product data 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.
Gather the collection's active product list with the attribute values populated per variant rather than averaged per product, the copy already published, the buyer searches the page should serve, and the merchant's terminology and banned-claims rules.
Draft description copy stating what the assortment contains, who it suits and how the options differ, using only attributes present in the supplied records and leaving every sentence that needs price, stock or delivery detail empty and marked as awaiting the merchant's values.
Deliver the revised copy as a field-by-field draft with the source line behind each claim, re-read the finished text against the current product list to catch items the collection no longer contains, and note the date the product data was last refreshed.
Cover decision rules, frequent misunderstandings, and required inputs so the team aligns on prerequisites before execution.
Anything about price, availability, delivery time or materials the product records do not state. Those values move without the copy moving, so each claim has to trace to a supplied field, or the sentence stays empty and flagged for the merchant to fill.
Enough to explain what the collection contains and how the options differ, and nothing added merely to reach a length. Sentences that only restate the title belong below the grid or nowhere, because padding dilutes the specific detail the shopper came for.
No, it must be re-read against the live product list first. A draft built from a stale extract can describe items the collection no longer includes, or omit the variants that now carry the page, so verification precedes publication every time.
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.