Spark playbook scenarios · Spark: AI Store Assistant

Generate descriptions for a batch of product records

A merchandising team has inconsistent or unclear listing copy that makes products difficult to understand. In this case, the immediate task is to generate descriptions for a batch of product records. The workflow should produce revised listing copy with an explanation of material changes, using the merchant's actual records and constraints.

Topic

Product Titles and Descriptions

Target keyword

shopify bulk product description 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 descriptions for a batch of 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: [provide current copy, verified product attributes, audience, target language, brand voice and intended keywords].

Identify unclear or repeated copy; rewrite the requested fields around verified features and customer needs; retain factual distinctions and show before-and-after examples.
Return revised listing copy with an explanation of material changes 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.

Use in Spark

Scenario & problem

When does this scenario usually come up?

Start with the business context, the trigger, and the expected output before moving into the execution 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.

Step 1

Start with current copy, verified product attributes, audience, target language, brand voice and intended keywords.

Step 2

Identify unclear or repeated copy; rewrite the requested fields around verified features and customer needs; retain factual distinctions and show before-and-after examples.

Step 3

Deliver revised listing copy with an explanation of material changes; verify the result against the supplied records and identify unresolved inputs.

FAQ

Common questions when running this scenario

Cover decision rules, frequent misunderstandings, and required inputs so the team aligns on prerequisites before execution.

Should every possible keyword appear in the title?

No. A title should identify the product clearly. Excessive repetition can make it harder to read and obscure distinguishing attributes.

Can AI add benefits that are missing from supplier data?

Only when supported by the supplied facts. Unsupported performance claims should be flagged for verification rather than stated as facts.

What information is needed to investigate this use case?

Start with current copy, verified product attributes, audience, target language, brand voice and intended keywords. These inputs establish the relevant scope and help separate an actual issue from missing information or an unsuitable comparison. Without them, the result should remain a proposed approach rather than a confirmed diagnosis.

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.

Product Titles and Descriptionsshopify product description generator