Feedback Collection with Outbound Calls

An outbound AI voice agent calls passengers after their trip, conducts an interactive conversational survey, and records structured feedback.

The problem this solves

SMS and email feedback surveys have low completion rates, while manual call centers are too expensive to reach every customer after a trip.

Traditional robocall systems sound rigid and un-interactive, leading callers to assume spam and hang up within seconds.

What this use case does

Customers appreciate being heard when the conversation is warm, concise, and interactive. This pattern dials passengers after travel and greets them naturally.

The agent collects ratings on comfort, punctuality, and service/cleanliness one question at a time, handling interruptions and conversational pauses seamlessly.

Structured feedback and call dispositions are written to JSONL for automated analytics, followed by a graceful call disconnect.

What it looks like in practice

A passenger finishes a bus trip. The agent places an outbound call, opens conversationally asking for a quick moment, and collects 1–5 ratings on comfort and timeliness.

The passenger provides brief answers, the agent records the structured score, thanks the passenger, and disconnects cleanly.

What it means for your operation

Survey response rates increase significantly compared to passive email forms, delivering actionable operational feedback in real time.

Automated voice outreach scales to thousands of post-trip surveys daily with zero human dialing costs and complete structured data capture.

What happens on a call

  1. 01

    Dial and greet conversationally

    Initiate the outbound call and greet the passenger warmly asking for a quick moment.

  2. 02

    Conduct structured survey

    Ask comfort, punctuality, and cleanliness ratings one question at a time.

  3. 03

    Record data and conclude

    Save structured survey results to JSONL, speak a warm goodbye, and disconnect.

Let's build this

Clone the sample, configure DESTINATION_NUMBER in .env, and run main.py to receive the survey call.

Required to start

4
  • Python 3.12+

    Runtime for the sample and its dependencies.

  • AgentDuet API key and connector UUID

    Authenticates the sample against your AgentDuet workspace.

  • Gemini API key

    Powers the live bidirectional speech session for outbound calls.

  • Destination Phone Number

    The telephone number to receive the outbound feedback call.

  1. Step 1

    Clone the sample

    bash
    git clone https://github.com/AgentDuet/agentduet-samples.git
cd agentduet-samples/use-cases/outbound-feedback

  2. Step 2

    Install dependencies

    bash
    python3.12 -m venv .venv && source .venv/bin/activate
pip install -r requirements.txt

  3. Step 3

    Configure credentials

    Copy .env.example to .env and fill your phone numbers and API keys.

    bash
    cp .env.example .env

  4. Step 4

    Run the agent

    Run main.py to initiate the automated outbound call directly to the destination number.

    bash
    python main.py
Full tutorial in the docs →

What to try on a call

Answer the phone when your connector dials.

  1. 01

    Answer the phone and listen to the warm opening greeting.

  2. 02

    Provide your 1–5 comfort rating and comment on trip punctuality.

  3. 03

    Check data/feedback_results.jsonl after the call to verify your logged feedback.

Related use cases

Voice AI Agent for Appointment Booking

An AI voice agent handles inbound appointment scheduling over the phone, checks live availability against a calendar, and confirms bookings with calendar and messaging writes.

View use case

AI Receptionist with CRM Lookup

An AI voice receptionist looks up the caller in CRM before greeting, personalizes known callers, creates leads for unknown numbers, and answers company FAQs.

View use case

Put a voice agent on a real number.

AgentDuet owns the phone and messaging boundary. Your model runs the conversation.

Explore the SDK