01
Step 1
Collect the product identifiers in the agreed selection, the fields named for this edit, the current value of each field in the original export, the transformation to apply, and the products deliberately excluded.
Back to topic
Spark playbook scenarios · Spark: AI Store Assistant
Prepare targeted bulk edits to product records
A merchandiser holds a defined product list and a short set of fields to touch, with several products kept out of the change. In this case, the immediate task is to prepare targeted bulk edits to product records. The output should be a row-by-row old-versus-new preview plus the records the original export cannot confirm, drawn from the merchant's own data.
Topic
Bulk Product Editing
Target keyword
shopify bulk product editor
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 prepare targeted bulk edits to product records.
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 product identifiers in the agreed selection, the fields named for this edit, each field's current value in the original export, the transformation to apply, and the deliberately excluded products]. Apply the transformation only to the named fields, leaving every other attribute at the value it holds today, and compare old against new row by row so an unexpected change surfaces before the edit is committed.
Return a bulk change preview and exception report flagging records the original export cannot confirm 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
Apply the transformation only to the named fields, leaving every other attribute at the value it holds today, and compare old against new row by row so an unexpected change surfaces before the edit is committed.
03
Step 3
Deliver the preview with one row per affected product and the unconfirmed records listed separately, verify the affected row count equals the selection minus the exclusions, and retain the original values for reversal.
FAQ
Common questions when running this scenario
Cover decision rules, frequent misunderstandings, and required inputs so the team aligns on prerequisites before execution.
Why work from an export rather than live data?
The export is the one record both the preview and the check can be reconciled against, and it holds the original values that a reversal would need afterwards.
What makes a record unconfirmed?
A product in the selection that the export cannot match, or one lacking a value in a field being edited; it is reported separately instead of being guessed at or silently changed.
How are excluded products protected?
They are listed before the run and must show no difference at all in the preview, which is the check proving the selection did not leak past its boundary.
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.