01
Step 1
Compile the catalogue fields per product, the variant-level differences, the recurring questions with who asked them and through which channel, and every answer already in use anywhere across the store.
Back to topic
Spark playbook scenarios · Spark: AI Store Assistant
Answer specific product questions consistently
The same product question gets different answers depending on who replies, and the store has no single approved wording. In this case, the immediate task is to answer specific product questions consistently. The workflow should produce an answer library with one approved wording per question, an owner and a review date, verified against the catalogue.
Topic
AI Customer Support and Chatbots
Target keyword
shopify product questions chatbot
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 answer specific product questions consistently.
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 catalogue fields per product, variant-level differences, recurring questions with their asker and channel, and every answer already in use across the store]. Write exactly one approved answer per product version and question pair, express it in identical wording at every place it appears, resolve any disagreement between two internal sources by escalating for a decision, and never publish a merged or provisional version.
Return the answer library with ownership and review dates verified against the 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
Write exactly one approved answer per product version and question pair, express it in identical wording at every place it appears, resolve any disagreement between two internal sources by escalating for a decision, and never publish a merged or provisional version.
03
Step 3
Deliver the answer library recording the owner and review date behind each entry, verify every answer against live product data, and mark any entry without owner, review date or supporting record as not approved for use.
FAQ
Common questions when running this scenario
Cover decision rules, frequent misunderstandings, and required inputs so the team aligns on prerequisites before execution.
Why keep one approved wording per question?
Two agents or two channels answering differently about the same product creates a conflict over what was promised; a single approved entry is the only version any channel may serve, so the shopper hears one story.
When should existing answers be rewritten?
Whenever a catalogue, variant or policy change touches them, plus a scheduled sweep at the interval the merchant sets; an answer left untouched after a product update is stale however well it once read.
What if two internal sources disagree?
Both records are escalated together for a decision and the question stays unapproved until then; publishing whichever source appeared first simply makes whichever record happened to be stale into the official wording.
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.
Build a chatbot workflow using approved store information
Design grounded AI customer service responses
Answer presales questions from verified product facts
Answer availability questions using current stock evidence
Draft consistent replies to common customer requests
Generate answers to recurring product questions
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.