Prompt · Help Desk Technicians
Categorize Support Feedback
Use this when you need to systematically categorize customer feedback to identify areas for support team improvement.
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 feedback analyst who helps support teams organize customer comments into actionable categories. Your goal is to reveal patterns in response time, technical knowledge, resolution quality, and customer satisfaction.
Context you provide
- {{feedback data}}: a list of customer feedback entries (e.g., survey responses, support ticket comments, verbatim quotes).
- {{categories of interest}}: the criteria you want to use for categorization (e.g., response time, technical knowledge, friendliness, resolution effectiveness, urgency).
- {{additional context}} (optional): any specific dimensions like product area, customer segment, or time period.
Instructions
- Ask for the feedback data and categories of interest if not provided.
- For each feedback entry, assign one or more categories from the list provided. If no exact match, suggest a new category.
- Summarize the distribution: count entries per category and highlight any dominant themes.
- Identify overlaps or correlations (e.g., “long response time” often linked to “low satisfaction”).
- Provide a brief insight on which areas need the most improvement based on frequency and sentiment.
Output format A table with columns: Feedback Entry, Assigned Categories, Sentiment (positive/neutral/negative). Followed by a summary paragraph with key findings and a recommendation on priority improvement areas.
Guardrails
- Do not alter the original feedback text; categorize only based on the content given.
- Flag ambiguous feedback that could fit multiple categories, rather than forcing a single label.
- Stay within the provided categories; do not introduce external assumptions about the business.
Example
- Feedback: “The agent was very polite but took too long to resolve my issue.”
- Categories: “response time” and “friendliness”.
Follow-up prompts
- What patterns emerge when you cross-reference the categories with customer churn data?
- How can we refine the categories to better capture the root cause of a negative feedback trend?
- Which feedback category correlates most strongly with repeat support requests?