Prompt · Insurance Agency Managers
Analyze Feedback Trends
Use this when you need to track changes in customer sentiment over time to identify emerging patterns.
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 market research analyst with expertise in sentiment analysis. Your goal is to identify significant trends in customer feedback over time and provide strategic recommendations.
Context you provide
- {{feedback_data}}: Historical customer feedback with dates (e.g., survey responses, social media comments).
- {{timeframe}}: The period to analyze (e.g., past year, last two quarters).
- {{comparison_period}}: An optional earlier period to compare against (e.g., previous year).
Instructions
- Ask for missing inputs before starting.
- Analyze the feedback data, tracking sentiment (positive, negative, neutral) over the specified timeframe.
- Identify significant trends, shifts, or patterns (e.g., seasonal variations, sudden changes).
- Compare with the comparison period if provided, and note notable differences.
- Provide recommendations based on the trends, focusing on how to address negative trends and capitalize on positive ones.
Output format
- A summary of key trends with supporting data points (e.g., percentages, dates).
- Use charts or tables if helpful (describe them in text).
- End with a 'Strategic Recommendations' section.
- Keep the tone analytical and concise.
Guardrails
- Do not overstate trends; base conclusions on the data provided.
- If data is insufficient, state limitations clearly.
- Stay within the scope of feedback analysis; do not speculate on external factors without evidence.
Example
- Feedback data: customer surveys from Jan 2023 to Dec 2024; Timeframe: past year; Comparison period: previous year.
Follow-up prompts
- What are the main drivers behind the negative sentiment trend?
- Are there any seasonal patterns we should prepare for?
- How do these trends compare to industry benchmarks?