01
Step 1
Collect every product's verified identifying attributes in a fixed field order, the storefront's stated title length limit, and the character counts of the current titles so over-limit items are known before drafting.
Back to topic
Spark playbook scenarios · Spark: AI Store Assistant
Generate clear product titles from verified attributes
Titles were written ad hoc, so one product type appears under several wordings and some run past the storefront limit. In this case, the immediate task is to generate clear product titles from verified attributes. The workflow should produce one title per identifier built only from recorded attributes, checked against the storefront length rules.
Topic
Product Titles and Descriptions
Target keyword
shopify product title generator
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 generate clear product titles from verified attributes.
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: [verified identifying attributes per product in fixed field order, the storefront's stated title length limit, and character counts of current titles]. Compose each title only from recorded attributes, placing the product type first, the key distinguishing variant attribute second, and supplementary identifiers last, and mark any product whose shortest honest combination still exceeds the length limit.
Return generated titles per identifier and verify each against the supplied attribute records 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
Compose each title only from recorded attributes, placing the product type first, the key distinguishing variant attribute second, and supplementary identifiers last, and mark any product whose shortest honest combination still exceeds the length limit.
03
Step 3
Deliver one title per product identifier with the attribute values used, then reconcile that every value in each title appears verbatim in the attribute records and that no generated title still exceeds the stated limit.
FAQ
Common questions when running this scenario
Cover decision rules, frequent misunderstandings, and required inputs so the team aligns on prerequisites before execution.
What happens when a title exceeds the length limit?
Attributes are trimmed from the end of the fixed order before marketing words are ever considered, and any product whose identifying combination alone still exceeds the limit is marked for a merchant decision; silently shortening further would drop the attribute that distinguishes the variant.
Why keep a fixed attribute order across the catalog?
A shared order makes near-identical variants differ in the same position, so shoppers scanning a collection can compare items on the distinguishing attribute instead of hunting for it, and reviewers can spot a wrong title at a glance.
How is a generated title verified?
Each title is checked word by word against the attribute record for that identifier; only values that appear verbatim in the record may be used, and any word with no matching attribute is flagged rather than left in place.
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
Prepare a batch of revised product titles
Rewrite existing descriptions without changing product facts
Improve product titles for clarity and search relevance
Generate product descriptions that answer buyer questions
Draft AI-assisted descriptions grounded in product facts
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.