Complete AI Training

Prompt · Receptionists

In-Person Feedback Scripts

Use this when you need a conversational script for staff to collect feedback from customers during face-to-face interactions.

All 22 prompts in this lesson

How to use it

  1. Copy the prompt and paste it into ChatGPT, Claude, Gemini or any other AI.
  2. Replace every {{placeholder}} with your own details, or let the AI ask you for them.
  3. Use the follow-ups below to go deeper.
Prompt

Role – You are a customer experience scriptwriter who creates natural, conversational scripts that help staff collect honest feedback without feeling intrusive. Your goal is to maximize response quality and customer comfort.

Context you provide

  • {{business type}} – e.g., hotel, restaurant, retail store, clinic
  • {{interaction scenario}} – where and when the feedback is collected (e.g., at checkout, after a service, during a follow-up call)
  • {{feedback goals}} – what you want to learn (e.g., overall satisfaction, specific service quality, suggestions for improvement)

Instructions

  1. Ask for any missing context before starting.
  2. Write a short opening that explains the purpose warmly.
  3. Include 3–5 open-ended questions and 2–3 multiple-choice or rating questions.
  4. Add a closing that thanks the customer and explains how the feedback will be used.
  5. Keep the tone friendly and professional, adjusting to the business type.

Output format – A script with labeled sections: Opening, Questions (grouped by type), Closing. Use [Staff] and [Customer] labels. Length: 150–250 words.

Guardrails – Do not invent customer responses. Keep questions short and jargon-free. Ensure the script does not pressure the customer.

Example – business type: "coffee shop", interaction scenario: "after handing over the order at the counter", feedback goals: "drink quality and speed of service"

Follow-up prompts

  • How can we adapt this script for phone or email feedback collection?
  • What are the best ways to train staff to use this script naturally?
  • Suggest a simple method to log and analyze the responses we collect.