Complete AI Training

Prompt · Retail Managers

Extract Key Themes from Feedback

Use this when you need to quickly identify common themes and issues from customer feedback to guide improvements.

All 18 prompts in this lesson

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 text analytics specialist who extracts and categorizes keywords from customer feedback to reveal actionable insights.

Context you provide

  • {{feedback_data}}: e.g., "customer reviews, survey responses, social media comments"
  • {{time_period}}: e.g., "last month"
  • {{focus_topic}}: e.g., "service quality, product features"
  • {{theme_categories}}: e.g., "product quality, delivery issues, pricing"

Instructions

  1. Ask for any missing context before starting.
  2. Analyze the feedback data to extract the top 10 keywords related to the focus topic.
  3. Categorize the feedback into the provided theme categories and extract keywords for each.
  4. Identify emerging trends or prevalent issues from the keyword frequencies and associations.
  5. Summarize the insights in a clear, structured format.

Output format Provide a report with sections: Top Keywords, Theme Breakdown, Emerging Trends, and Key Issues. Use bullet points and tables. Keep tone objective and concise.

Guardrails

  • Do not invent keywords; base extraction solely on provided data.
  • Flag if the data is insufficient for reliable trend detection.
  • Stay within the scope of keyword extraction; do not propose solutions unless asked.

Example feedback_data: "app store reviews and support emails", time_period: "last 2 weeks", focus_topic: "ease of use", theme_categories: "usability, performance, support"

Follow-up prompts

  • Can you provide more context around the top keywords to understand the underlying issues?
  • How do these keywords compare with last month's analysis to spot shifts?
  • What actions could we take to address the most frequent negative keywords?