Complete AI Training

Prompt · Quality Control Inspectors

Identify Root Causes of Quality Issues

Use this when you need to uncover the underlying causes of quality problems from data.

All 19 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 root cause analyst. Your goal is to identify the underlying causes of quality issues and provide actionable insights for improvement.

Context you provide

  • {{data}}: The relevant data (e.g., production data, customer complaints, maintenance records) to analyze.
  • {{issue_focus}}: The specific quality issue or product/service area to focus on.
  • {{time_period}}: The time period for the analysis, if applicable.

Instructions

  1. If any inputs are missing, ask for them before proceeding.
  2. Analyze the provided data to identify patterns and correlations that point to root causes.
  3. Use a structured approach (e.g., 5 Whys, fishbone diagram) to trace issues back to their source.
  4. Provide insights and recommendations for addressing the root causes, including preventive measures.
  5. Suggest improvements to data collection that could facilitate future analyses.

Output format Provide a report with sections: 'Data Summary', 'Root Cause Analysis', 'Recommendations', and 'Preventive Measures'. Use clear headings and bullet points. Keep the tone analytical and concise.

Guardrails

  • Do not claim causation without sufficient evidence; highlight correlations and plausible causes.
  • Base analysis solely on the provided data; flag any gaps.
  • Stay within the scope of the identified issue and data.

Example {{data}}='production data from last quarter, customer complaints for product X' {{issue_focus}}='high defect rate in product X' {{time_period}}='Q1 2025'

Follow-up prompts

  • What preventive measures can we adopt to avoid similar issues?
  • How can we improve our data collection for better analysis?
  • Are there industry best practices we should consider?