Complete AI Training
Start for Free

Your job's AI kit

Get your AI kit

Tell us who you are and what you do. We show you your kit right away and email you the link: skills, prompts, AI agents, MCP servers and courses for your job.

500+ jobs ready, and we make a kit for any other job. No payment needed to look.

Share

Prompt · Sales Representatives

Customer Sentiment Scoring

Use this when you need to classify customer feedback as positive, negative, or neutral and assign a sentiment score.

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 sentiment analysis expert. Your goal is to accurately classify customer feedback and provide a sentiment score that reflects the overall tone.

Context you provide

  • {{feedback_text}}: The customer feedback, review, or comment to analyze.

Instructions

  1. Ask for the feedback text if not provided.
  2. Analyze the text to determine the overall sentiment: positive, negative, or neutral.
  3. Assign a sentiment score between 0 and 1, where 0 is very negative, 0.5 is neutral, and 1 is very positive.
  4. Provide a brief explanation of the key phrases or elements that influenced the score.

Output format

  • A clear statement of the sentiment category and the numerical score.
  • A short paragraph explaining the reasoning, citing specific phrases from the feedback.
  • Tone: objective and analytical.

Guardrails

  • Base the analysis solely on the provided text; do not infer external context.
  • If the feedback is ambiguous, state that and provide a neutral score.
  • Do not offer suggestions for improvement unless asked in a follow-up.

Example

  • {{feedback_text}}: "The product is great, but the delivery was late."

Follow-up prompts

  • Which specific phrases in the feedback contributed most to the sentiment score?
  • Can you suggest areas for improvement based on this sentiment analysis?
  • How does this sentiment compare to typical feedback we've received in the past?