Ciwi
Back to topic
Spark playbook scenarios · Spark: AI Store Assistant

Generate descriptions for a batch of product records

A batch of product records has no descriptions yet, and one shared template would make near-identical items indistinguishable. In this case, the immediate task is to generate descriptions for a batch of product records. The workflow should produce a batch of descriptions keyed by identifier, each verified against the supplied product records.

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: [product records in scope with verified attributes, the merchant's shared section order, and per-record sibling-differentiating attribute notes].

Generate one description per record following the shared section order but varying the sentence patterns per record so near-identical items remain distinguishable, and flag records whose attributes are too sparse to fill the required sections.
Return a batch of descriptions keyed by identifier and verified against the supplied product 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.
Use in Spark
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.

01

Step 1

Collect the product records in scope with their verified attributes, the shared section order the merchant wants, and a per-record note of the attributes that differentiate near-identical siblings.

02

Step 2

Generate one description per record following the shared section order but varying the sentence patterns per record so near-identical items remain distinguishable, and flag records whose attributes are too sparse to fill the required sections.

03

Step 3

Deliver descriptions keyed by identifier with duplicate checks across the batch, then verify each description against its source record and reconcile that the delivered count equals the record count with every flagged gap listed.

FAQ

Common questions when running this scenario

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

How is near-duplicate wording caught?

Each generated description is compared against the rest of the batch for overlapping sentence patterns, and any two records whose descriptions match beyond the shared section headings are regenerated with their differing attributes brought forward.

What happens to records with sparse attributes?

The generator writes only what the record supports and flags the empty sections per record instead of padding with assumptions; the flag list tells the merchant exactly which product data to complete before relisting.

What does the final reconciliation count?

Delivered descriptions are matched one-to-one with the input identifiers, the flagged-gap list is checked against the sparse records, and any record with neither a description nor a flag marks a silent miss that must be resolved before the batch ships.

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.

Open Spark product pageBack to Spark scenario library