01
Step 1
Assemble the current product records with their variants, options and metafield values, collection membership, inventory state per location, the explicit list of fields the agent may write, and a product export taken before any edit.
Back to topic
Spark playbook scenarios · Spark: AI Store Assistant
Coordinate AI-assisted product management tasks
Catalogue updates arrive in bulk and the merchant needs them applied without touching unauthorized fields. In this case, the immediate task is to coordinate AI-assisted product management tasks. The workflow should produce an agent task plan and action log, with conflicting writes held for approval and results reconciled against the exported product data.
Topic
AI Store Management and Agents
Target keyword
shopify ai product management
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 coordinate AI-assisted product management tasks.
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: [the current product records with variants, options and metafield values, collection membership, inventory state per location, the explicit list of writable fields, and a pre-edit product export]. Group the requested edits by attribute, test each against the live catalogue record for conflicting values, apply writes only to permitted fields, and queue for merchant approval any edit whose source disagrees with the existing value.
Return an agent task plan and action log reconciled against the exported product 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
Group the requested edits by attribute, test each against the live catalogue record for conflicting values, apply writes only to permitted fields, and queue for merchant approval any edit whose source disagrees with the existing value.
03
Step 3
Deliver the task plan and action log naming per change the product, field, old and new value and its source, then reconcile against a post-change export so row counts, conflicts held and protected fields left untouched all agree.
FAQ
Common questions when running this scenario
Cover decision rules, frequent misunderstandings, and required inputs so the team aligns on prerequisites before execution.
Which product fields may the agent write?
Only those the merchant enumerates; titles, descriptions or pricing outside that list go to a review queue instead of being edited, because an unlisted field usually carries SEO or reporting dependencies nobody has mapped.
How are conflicting attribute values resolved?
Both records are surfaced side by side with their source and timestamp and the edit waits for a merchant decision; letting one system win silently rewrites the other source's version of the truth without a trace.
Why export the catalogue before editing?
The pre-edit export fixes the baseline for verifying every write and for restoring values later, and it is taken before the first edit rather than after, because a bulk update applied to the live catalogue offers no undo.
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.