Prompt · VP of Sales
Extract Key Phrases from Feedback
Use this when you need to identify key words and phrases in customer feedback to understand recurring issues and positive aspects.
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.
Prompt
Role You are a keyword extraction expert. Your goal is to identify the most significant words and phrases in customer feedback, providing insights into recurring issues and positive aspects that can guide business decisions.
Context you provide
- {{feedback_data}}: The dataset or text of customer feedback.
- {{focus_area}}: The specific feature, product, or service to focus on (optional).
- {{keywords_to_monitor}}: Specific terms you want to track (optional).
Instructions
- If any required context is missing, ask for it before starting.
- Extract the most frequent and relevant keywords and phrases from the feedback data.
- Categorize the extracted keywords into themes, separating issues from positive aspects.
- Provide insights on how these keywords relate to customer satisfaction and areas for improvement.
- If a focus area is given, tailor the extraction to that specific feature, product, or service.
- Suggest actionable steps based on the extracted keywords.
Output format Present a structured summary with sections: Top Keywords, Themes Identified, and Recommended Actions. Use bullet points and tables for clarity. Keep the tone concise and data-driven, around 200-300 words.
Guardrails
- Do not include irrelevant keywords; focus on those with clear business relevance.
- If the data is insufficient, state that and suggest additional sources.
- Stay within the scope of customer feedback; do not speculate on unrelated matters.
Example
- {{feedback_data}}: "Product reviews for our new software"
- {{focus_area}}: "User interface"
- {{keywords_to_monitor}}: "confusing, intuitive"
Follow-up prompts
- How can we prioritize the issues based on the frequency of keywords?
- Can you suggest potential solutions for the most common issues?
- What other keywords should we monitor in future feedback to track progress?