01
Step 1
Export the batch's product identifiers, variant-level options, current titles and the attributes that distinguish each item from its siblings, with a per-row note of which attribute separates it.
Back to topic
Spark playbook scenarios · Spark: AI Store Assistant
Prepare a batch of revised product titles
Titles were written product by product, so shoppers cannot spot the attribute that separates near-identical variants. In this case, the immediate task is to prepare a batch of revised product titles. The workflow should produce a batch file of identifier and new title pairs, spot checked against the supplied attribute data.
Topic
Product Titles and Descriptions
Target keyword
shopify bulk edit product titles
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 a batch of revised product titles.
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: [product identifiers, variant-level options, current titles and sibling-distinguishing attributes for the batch, with per-row distinguishing notes]. Rebuild every title in one fixed token order shared across the batch so the distinguishing attribute always occupies the same position, and flag rows where the distinguishing attribute is missing from the record or where two variants would produce identical titles.
Return a batch file of identifier and new title pairs, spot checked against the supplied attribute 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.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
Rebuild every title in one fixed token order shared across the batch so the distinguishing attribute always occupies the same position, and flag rows where the distinguishing attribute is missing from the record or where two variants would produce identical titles.
03
Step 3
Deliver an import-ready file of identifier and new title pairs plus a change report showing old and new per row, then spot check a merchant-defined sample of rows against the source records and confirm the file's row count equals the selected product count.
FAQ
Common questions when running this scenario
Cover decision rules, frequent misunderstandings, and required inputs so the team aligns on prerequisites before execution.
Why flag variants that would get identical titles?
Two variants producing the same title means the distinguishing attribute never made it into the record, and applying the batch would leave shoppers unable to tell the items apart; those rows are held back rather than overwritten.
What does the spot check confirm?
A sample of rows is compared against the source export so each identifier maps to the intended product and every attribute value in the new title matches the record; the row count is also reconciled so no product was skipped or duplicated.
Can the batch be applied twice safely?
The file should be idempotent per identifier, meaning reapplying it yields the same titles, and the change report's old-title column gives the rollback values if the batch must be reversed.
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.
Generate descriptions for a batch of product records
Improve product titles for clarity and search relevance
Generate clear product titles from verified attributes
Draft clearer product copy for a defined audience
Rewrite existing descriptions without changing product facts
Replace selected description content using a verified template
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.