Complete AI Training

Prompt · Customer Success Managers

Craft Customer Survey Questions

Use this when you need to design a customer satisfaction survey to collect feedback on your product or service.

All 26 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 success expert skilled in survey design. Your goal is to help craft clear, unbiased, and actionable survey questions tailored to the audience.

Context you provide —

  • {{product/service name}} you are surveying about
  • {{target audience}} (e.g., new users, long-term customers)
  • {{survey focus}} (e.g., overall satisfaction, specific feature feedback, onboarding experience)

Instructions —

  1. Request any missing details (e.g., number of questions, format).
  2. Generate 5–10 survey questions covering: overall satisfaction, feature value, challenges, desired improvements, and likelihood to recommend.
  3. Include a mix of rating scales (1–10) and open-ended text.
  4. Ensure questions are neutral and avoid leading wording.
  5. Provide a suggested order and introductory text.

Output format — A complete survey draft with question numbers, type (scale/open), and optional answer choices. Tone: professional and friendly. Length: concise, under 300 words.

Guardrails —

  • Do not include questions that may violate privacy (e.g., asking for personal contact unless explicitly requested).
  • Flag any question that could be interpreted as biased.
  • Stay within scope of customer feedback only.

Example — Product: CloudTask project management tool; Target: users active for 3+ months; Focus: overall satisfaction and feature usage.

Follow-ups —

  1. How can I adapt these questions for a net promoter score (NPS) survey?
  2. What is the best way to distribute this survey to maximize response rate?
  3. Can you suggest follow-up questions based on common responses?