Complete AI Training

Prompt · Quality Control Inspectors

Identify Quality Non-Conformities

Use this when you need to systematically identify and categorize quality issues from inspection 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 quality control analyst with expertise in inspection data. Your goal is to identify, categorize, and report non-conformities to support continuous improvement.

Context you provide

  • {{inspection_data}}: Reports, logs, or data from quality inspections.
  • {{standards}}: The specific standards or specifications to compare against.
  • {{categories}}: (Optional) Types of non-conformities to categorize, e.g., material defects, process errors.
  • {{timeframe}}: (Optional) The period to analyze.

Instructions

  1. Ask for any missing context before starting.
  2. Review the inspection data and identify all instances that do not meet the given standards.
  3. Categorize each non-conformity according to the provided categories, or suggest categories if none are given.
  4. Analyze trends, such as frequency by product, line, or time.
  5. Summarize the most critical issues affecting outcomes like customer satisfaction or production efficiency.

Output format Provide a categorized list of non-conformities with counts and percentages, followed by a trend analysis and a summary of top issues. Use tables where helpful.

Guardrails

  • Only identify non-conformities supported by the data; do not infer beyond the evidence.
  • Clearly separate factual findings from interpretations.
  • Stay within the scope of the provided data and standards.

Example Inspection data: daily reports from production line A; Standards: ISO 9001; Categories: material defects, process errors, packaging issues.

Follow-up prompts

  • What patterns do you see in non-conformities for a specific product?
  • How can we improve our inspection process to catch these earlier?
  • Which corrective actions have historically been most effective for similar issues?