Spark playbook scenarios · Spark: AI Store Assistant

Draft product listings from visible image evidence

A catalog manager needs to create listings from supplier files or links without duplicate products or mismatched fields. In this case, the immediate task is to draft product listings from visible image evidence. The workflow should produce a validated import draft with a row-level exception list, using the merchant's actual records and constraints.

Topic

Product Creation and Import

Target keyword

create product listings from images

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 draft product listings from visible image evidence.
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 source records, current catalog IDs, intended field mapping, variant structure and import errors if present]. Map source fields to the provided target schema, flag missing facts, validate identifiers and produce a small sample before the full draft import.
Describe only visible attributes, and explicitly flag materials, dimensions and certifications that cannot be inferred from the image.
Return a validated import draft with a row-level exception list 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 source records, current catalog IDs, intended field mapping, variant structure and import errors if present.

Step 2

Map source fields to the provided target schema, flag missing facts, validate identifiers and produce a small sample before the full draft import.

Step 3

Describe only visible attributes, and explicitly flag materials, dimensions and certifications that cannot be inferred from the image.

Step 4

Deliver a validated import draft with a row-level exception list; 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.

Why do product imports create duplicates?

Records may lack a stable matching identifier or use an incorrect mapping. Compare source identifiers with existing catalog records before importing.

Should missing product facts be guessed?

No. Leave unsupported specifications unresolved and request supplier evidence rather than inventing materials, dimensions or claims.

Which product facts cannot reliably be read from an image?

An image may show appearance, but usually cannot verify exact dimensions, materials, certifications or performance. Those facts need another source.

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 Creation and Importshopify product import app