The assistant copes until a request touches refunds or addresses, then the customer retells the story to an agent who sees none of it. In this case, the immediate task is to transfer unresolved chatbot requests with useful context. The workflow should produce a support operating workflow and sample ticket outcomes showing what travels with each handoff.
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.
Act as a Shopify operations specialist.
Help me transfer unresolved chatbot requests with useful context.
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: [tickets where the bot stopped, the policies bounding its replies, roles able to complete the actions, and the record fields a handoff can carry]. Define the handoff triggers as observable conditions such as a second failed attempt, a request for a refund or address change, or a claim contradicting the order record, and attach to each trigger the context packet the agent will receive.
Return a support operating workflow and sample ticket outcomes showing the handoff context 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.Split the work into input, judgment, and deliverable phases. Verify each step's output before moving to the next.
Collect the tickets where the bot stopped, the policies that bound what it may say, the roles able to complete the actions involved, and the record fields a handoff can carry such as order reference, customer identifier and steps already taken.
Define the handoff triggers as observable conditions such as a second failed attempt, a request for a refund or address change, or a claim contradicting the order record, and attach to each trigger the context packet the agent will receive.
Deliver the support workflow with sample outcomes showing what travels with each handoff, then check every trigger against past conversations and confirm the customer is told who is taking over before the bot stops.
Cover decision rules, frequent misunderstandings, and required inputs so the team aligns on prerequisites before execution.
The order or customer reference, the request in the customer's own words, what the bot already told them and the question left open; unverified guesses are left out, because an agent who inherits a wrong fact has to undo it before helping.
While the conversation is still open if staff are on shift, so the customer is not left waiting in a chat that looks live; outside staffed hours the handoff still creates a ticket with an owner and gives the customer a stated response time.
The agent opens by correcting it and states the confirmed fact rather than letting the earlier answer stand; the correction is logged so the same wrong answer is not repeated to the next customer who asks.
Start with scenarios under the same topic, then expand into cross-topic matches suggested by similarity.
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.