1. Identify order
What order is this for?
Workflow Template
Return request intake call app template
Collects return reason, order details, condition, and policy edge cases for a support team.
Best fit
- Ecommerce
- Retail
- Marketplaces
Do not use it for
- Approving policy exceptions automatically
- Collecting card details
Call flow
2. Capture reason
Why do you want to return it?
3. Ask condition
Has the item been used or opened?
4. Check timing
What order is this for?
5. Escalate exceptions
Why do you want to return it?
Prompt template
Collect return requests by phone. Ask order number, reason, condition, purchase date, requested resolution, and policy exceptions. Do not approve refunds. Save a return intake record.Questions asked
- What order is this for?
- Why do you want to return it?
- Has the item been used or opened?
Human handoff
- Policy exception
- Damaged or unsafe item
- Refund dispute
Structured output schema
{
"outcome": "Return request intake outcome",
"fields": [
{
"description": "caller name captured during the call.",
"name": "caller_name",
"required": true,
"type": "text"
},
{
"description": "phone number from caller id captured during the call.",
"name": "phone_number_from_caller_id",
"required": true,
"type": "text"
},
{
"description": "order number captured during the call.",
"name": "order_number",
"required": true,
"type": "text"
},
{
"description": "return reason captured during the call.",
"name": "return_reason",
"required": true,
"type": "text"
},
{
"description": "item condition captured during the call.",
"name": "item_condition",
"required": true,
"type": "text"
},
{
"description": "purchase date captured during the call.",
"name": "purchase_date",
"required": false,
"type": "date"
},
{
"description": "policy exception captured during the call.",
"name": "policy_exception",
"required": false,
"type": "text"
},
{
"description": "requested resolution captured during the call.",
"name": "requested_resolution",
"required": false,
"type": "text"
}
]
}Transcript example
AI: Hi, I am an AI call workflow for Return request intake. What order is this for?
Caller: I need to return one item from my order.
AI: Why do you want to return it?
Caller: It arrived damaged and I can upload a photo.
Recommended integrations
ShopifyZendeskGoogle Sheets
Launch review
Caller promise
Make the first screen and opening line match what the caller will actually get. For Return request intake, the promise should be narrow enough that a caller understands the purpose before sharing details or scanning a QR code. Avoid broad claims like "we can help with anything"; a specific promise produces cleaner calls and clearer follow-up.
Required outcome
Decide which fields are required before the call can be considered complete. A practical first version should capture caller name, phone number from caller id, order number, then send a summary that the workflow owner can act on without replaying the call. If a field is not used for routing, qualification, scheduling, or review, remove it from the first launch.
Human review
Write down the cases that should not be automated. Use human review for policy exception, damaged or unsafe item, refund dispute so the workflow stays useful without pretending to handle every edge case. Review the first real calls before connecting higher-risk actions or expanding the workflow.
FAQ
When should I use a return request intake Call App?
Use it when the call is repeatable, the team already knows the information they need, and the caller benefits from speaking instead of filling out a form. It works best for ecommerce, retail, marketplaces.
What should the AI ask first?
The first question should identify the caller goal and gather enough context to continue naturally. For this template, start with: "What order is this for?". Keep follow-ups short so the caller does not feel like they are reading a form over the phone.
What output fields should be saved?
Save a structured result with caller name, phone number from caller id, order number, plus a summary, completion status, and handoff reason when needed. The owner should be able to act on the result without interpreting raw transcript text.
What should trigger human handoff?
Human handoff should trigger when the caller needs judgment, asks for a person, gives conflicting answers, or matches one of the workflow-specific rules: policy exception, damaged or unsafe item, refund dispute.
Clone this template
The template includes prompt, questions, output fields, sample transcript, handoff rules, and a live call entry point.