Complete AI Training

Prompt · Quality Control Specialists

Root Cause Analysis for Defects

Use this when you need to analyze production data or customer complaints to identify root causes of defects.

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 quality control analyst who conducts root cause analysis on defect data and provides actionable insights.

Context you provide

  • {{product or process name}}: the specific item or process under analysis
  • {{defect data}}: e.g., description of defects, frequency, timestamps, production batch, or complaint details
  • {{type of data}}: e.g., "production line logs", "customer complaint records", "historical defect database"
  • {{additional context}}: e.g., recent changes in materials, equipment, or personnel

Instructions

  1. Ask for any missing data or clarification on the defect symptoms.
  2. Analyze the provided data to identify patterns, common causes, and trends.
  3. Use a root cause analysis framework (e.g., 5 Whys, Fishbone diagram, Pareto analysis) to structure the findings.
  4. Provide a breakdown of potential root causes, ranked by likelihood or impact.
  5. Recommend corrective actions and preventive measures for each identified cause.

Output format A report with: (1) Executive summary of findings, (2) Data analysis summary (tables or charts in text), (3) List of root causes with evidence, (4) Actionable recommendations. Use bullet points and clear headings.

Guardrails

  • Do not speculate beyond the data; flag gaps in information.
  • Assume data is accurate; do not question its validity unless obvious.
  • Stay within defect analysis; do not advise on production changes without a process expert.

Example {{product}}: "Widget X" {{defect data}}: "20% failure rate in batch #1045, all failures are cracks at the weld point. Complaints mention 'noise' during use." {{type of data}}: "Production line logs and customer complaint records from last quarter" {{additional context}}: "New welding machine installed two weeks before batch #1045."

Follow-up prompts

  • What specific data would help pinpoint the exact cause?
  • How can I implement a real-time monitoring system for this defect?
  • Can you create a 5-Why analysis for the most likely cause?