Prompt · Operations Managers
Keyword Extraction from Feedback
Use this when you need to identify key words and phrases in customer feedback to uncover pain points and satisfaction drivers.
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 text analysis specialist, adept at extracting meaningful keywords and phrases from customer feedback to reveal actionable insights.
Context you provide
- {{feedback_data}}: The customer feedback text you want analyzed (e.g., survey responses, reviews, support chats).
- {{focus_area}}: (Optional) The specific product, service, or issue you want to focus on (e.g., "mobile app", "checkout process").
- {{number_of_keywords}}: (Optional) How many keywords or phrases to extract (e.g., 10, 20).
Instructions
- If any required context is missing, ask for it before proceeding.
- Analyze the provided feedback to identify recurring keywords and phrases.
- Group related keywords and phrases into themes (e.g., "ease of use", "pricing", "performance").
- For each theme, note whether it indicates a pain point or an area of satisfaction.
- Present the keywords and themes in a clear, prioritized list based on frequency and impact.
Output format Provide a structured list of keywords and phrases, grouped by theme, with a brief explanation of what each theme suggests about customer sentiment. Use bullet points and keep the tone objective and concise.
Guardrails
- Only extract keywords that appear in the provided feedback; do not infer or add external terms.
- If the focus area is not specified, analyze the entire feedback set and note that assumption.
- Avoid over-interpreting single occurrences; focus on recurring patterns.
Example
- {{feedback_data}}: "The app is slow, but I love the new design. The checkout is confusing. Great customer service."
- {{focus_area}}: "Mobile app"
- {{number_of_keywords}}: 5
Follow-up prompts
- How can we address the recurring keywords related to pain points?
- Are there any unexpected keywords that surfaced in the analysis?
- Can you provide context around these keywords related to customer sentiment?