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

Answer order-status questions using the correct record

Shoppers ask where their order is without giving enough detail, and answers drift into guesses about delivery. In this case, the immediate task is to answer order-status questions using the correct record. The workflow should produce a reply grounded in the order's latest status events, with no prediction the record cannot support.

Topic
Order and Shipping Customer Support
Target keyword
shopify order status 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 order-status questions using the correct record.
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 order identifier and contact detail the shopper supplies, the matching order record, its fulfilment and tracking events in time order, and the merchant's stated rule on what may be disclosed]. Read the latest event rather than the order summary, answer with the current state and the next event the record supports, and state no delivery date unless the carrier record carries one, treating an enquiry with no matching order as an escalation rather than a guess.
Return the response and action plan 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 order identifier and contact detail the shopper supplies, the order record they match, the fulfilment and tracking events attached to it in time order, and the merchant's stated rule on what may be disclosed to a customer.

02

Step 2

Read the latest event rather than the order summary, answer with the current state and the next event the record supports, and state no delivery date unless the carrier record carries one, treating an enquiry with no matching order as an escalation rather than a guess.

03

Step 3

Deliver the response with the events it relies on quoted, check every claim in it against the supplied order and tracking records, and hand off to a person whenever the request asks for a change, a refund or anything the records cannot answer.

FAQ

Common questions when running this scenario

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

What should the bot ask for first?

It asks for the order identifier and a contact detail that appears on the order and matches both before answering, because replying from a partial match exposes one customer's order to another; if either fails to match, the conversation goes to a person instead of the bot offering a likely order.

Can the bot give a delivery date?

Only when the carrier record states one, since a date the merchant promises but the carrier has not confirmed becomes a complaint later; otherwise the reply names the latest scanned event and the next step the record supports, and says plainly that no date is on file.

When does the conversation go to a person?

It escalates whenever the request asks for a change, a cancellation, a refund or a dispute, or when no order matches the details given, because those need authority the bot does not have; the handoff carries the order record and the events already read so the customer does not repeat themselves.

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