1. Capture identity
What would you like help with?
Workflow Template
Customer intake call app template
Turns a general inquiry into a complete intake record with contact details, need, urgency, and owner follow-up.
Best fit
- Professional services
- Clinics
- Agencies
- Support teams
Do not use it for
- Diagnosing a caller
- Collecting passwords or full payment details
Call flow
2. Clarify goal
What details should the team know first?
3. Ask required intake questions
How soon do you need a response?
4. Classify urgency
What would you like help with?
5. Save next step
What details should the team know first?
Prompt template
Collect customer intake by phone. Ask concise questions, capture identity, request type, urgency, and preferred follow-up. Avoid sensitive unnecessary data. Save a structured intake record.Questions asked
- What would you like help with?
- What details should the team know first?
- How soon do you need a response?
Human handoff
- Sensitive personal information
- Complaint or threat
- Caller needs emergency help
Structured output schema
{
"outcome": "Customer 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": "email captured during the call.",
"name": "email",
"required": true,
"type": "text"
},
{
"description": "request type captured during the call.",
"name": "request_type",
"required": true,
"type": "text"
},
{
"description": "summary captured during the call.",
"name": "summary",
"required": true,
"type": "text"
},
{
"description": "urgency captured during the call.",
"name": "urgency",
"required": false,
"type": "text"
},
{
"description": "preferred follow up captured during the call.",
"name": "preferred_follow_up",
"required": false,
"type": "text"
}
]
}Transcript example
AI: Hi, I am an AI call workflow for Customer intake. What would you like help with?
Caller: I am a new customer and I am not sure where to start.
AI: What details should the team know first?
Caller: I need someone to understand the situation and tell me the next step.
Recommended integrations
Google SheetsAirtableNotion
Launch review
Caller promise
Make the first screen and opening line match what the caller will actually get. For Customer 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, email, 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 sensitive personal information, complaint or threat, caller needs emergency help 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 customer 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 professional services, clinics, agencies.
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 would you like help with?". 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, email, 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: sensitive personal information, complaint or threat, caller needs emergency help.
Clone this template
The template includes prompt, questions, output fields, sample transcript, handoff rules, and a live call entry point.