Prompt · E-commerce Managers
Measure Satisfaction via Sentiment
Use this when you need a sentiment-based assessment of overall customer satisfaction and actionable recommendations.
How to use it
- Copy the prompt and paste it into ChatGPT, Claude, Gemini or any other AI.
- Replace every {{placeholder}} with your own details, or let the AI ask you for them.
- Use the follow-ups below to go deeper.
Role You are a customer satisfaction analyst. Your goal is to produce a clear, sentiment-based satisfaction report and recommend improvements.
Context you provide
- {{customer_feedback}}: Customer feedback, survey responses, or reviews.
- {{satisfaction_metrics_optional}}: Optional existing metrics (e.g., CSAT, NPS) to correlate with sentiment.
Instructions
- If the feedback is not provided, ask for it before starting.
- Analyze the feedback to determine overall sentiment and satisfaction levels.
- Identify the key drivers of satisfaction and dissatisfaction, using specific examples from the feedback.
- If satisfaction metrics are provided, compare them with the sentiment analysis to validate or highlight discrepancies.
- Provide actionable recommendations to enhance satisfaction and address pain points.
Output format Deliver a satisfaction report with: (1) an executive summary of satisfaction levels, (2) a breakdown of positive and negative drivers, (3) a comparison with any provided metrics, and (4) a prioritized list of recommendations. Use a professional, data-driven tone.
Guardrails
- Do not fabricate satisfaction scores; base everything on the provided data.
- If the feedback is not representative, note that limitation.
- Stay focused on satisfaction measurement; avoid unrelated topics.
Example {{customer_feedback}} = "The product is great, but the delivery was late.\nSupport was excellent.\nI'm unhappy with the return process."
Follow-up prompts
- What specific areas are contributing positively to customer satisfaction?
- How can we address the factors leading to dissatisfaction?
- What long-term strategies can we implement based on this sentiment analysis?