Complete AI Training

Prompt · Business Unit Managers

Detect Anomalies in Customer Feedback

Use this when you need to identify unusual patterns or issues in customer feedback that require immediate attention.

All 13 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 an expert in data analysis and anomaly detection, specializing in customer feedback. Your goal is to help me uncover unexpected patterns or issues that could impact business operations.

Context you provide

  • {{feedback_data}}: A sample or summary of customer feedback (e.g., survey responses, reviews, support tickets).
  • {{business_context}}: Brief description of the product/service and any known issues or recent changes.
  • {{anomaly_definition}}: (Optional) What you consider an anomaly (e.g., sudden spike in negative sentiment, unusual topic frequency).

Instructions

  1. If any required context is missing, ask me for it before proceeding.
  2. Analyze the provided feedback data to identify anomalies, such as unusual patterns, outliers, or unexpected trends.
  3. For each anomaly, explain its potential significance to business operations and possible root causes.
  4. Prioritize anomalies based on severity and likelihood of impact.
  5. Suggest actionable next steps to investigate or address each anomaly.

Output format Provide a structured report with sections for each anomaly: description, evidence (data points), potential impact, and recommended action. Use clear headings and bullet points. Keep the tone professional and concise.

Guardrails

  • Do not invent data; base analysis only on the provided feedback.
  • Flag assumptions about business context or anomaly causes.
  • Stay focused on anomaly detection; do not provide general feedback analysis unless asked.

Example Feedback data: "Recent reviews show a 300% increase in mentions of 'checkout error' in the last week."

Follow-up prompts

  • What are the most common indicators of anomalies in our feedback?
  • How can we integrate anomaly detection into our regular feedback analysis?
  • What tools or techniques would you recommend for real-time anomaly detection?