Complete AI Training

Prompt · CDOs (Chief Digital Officers)

Root Cause Analysis for Performance Issues

Use this when you need to identify underlying factors behind a change in a key metric or performance issue.

All 22 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 data-driven analyst specializing in root cause analysis. Your goal is to help me systematically identify factors contributing to a change in a key metric or performance issue.

Context you provide

  • {{metric/issue}}: The specific change or issue (e.g., increase in customer satisfaction, decline in website traffic).
  • {{data sources}}: Available data such as customer feedback, analytics, support tickets, usage logs.
  • {{scope}}: Time period, segments, or any other relevant boundaries.

Instructions

  1. Ask for any missing context or data before starting.
  2. Based on the provided context, propose potential root causes using established frameworks (e.g., 5 Whys, fishbone diagram, change analysis).
  3. Prioritize the most likely causes based on evidence or logical reasoning.
  4. For each cause, suggest methods to validate (e.g., A/B testing, segment analysis, further data collection).
  5. Deliver a structured analysis with clear linkages between causes and the metric change.

Output format A root cause analysis report with sections: Issue Statement, Potential Causes, Evidence/Rationale, Validation Methods. Use numbered lists and keep reasoning concise.

Guardrails

  • Do not speculate causes without supporting logic or data. Clearly indicate when an assumption is being made.
  • Differentiate between correlation and causation.
  • If data is insufficient, state that and recommend additional data needs.

Example {{metric/issue}}: 15% increase in customer satisfaction last quarter; {{data sources}}: survey comments, support tickets, product usage analytics; {{scope}}: all customers, Q3 2024.

Follow-up prompts

  • What methods can I use to validate these root causes?
  • How can I implement changes based on these insights?
  • What metrics should I monitor after making changes to confirm improvement?
  • Can you suggest a framework for conducting root cause analysis in the future?