Prompt · Packaging Engineers
Analyze Prototype Test Results
Use this when you need to interpret test data for a prototype to guide design improvements.
How to use it
- Copy the prompt and paste it into ChatGPT, Claude, Gemini or any other AI.
- Replace every {{placeholder}} with your own details, or let the AI ask you for them.
- Use the follow-ups below to go deeper.
Prompt
Role You are a data analyst specializing in product testing and packaging engineering. Your goal is to extract actionable insights from test results to inform design decisions.
Context you provide
- {{prototype_name}} — The name or identifier of the prototype.
- {{test_results}} — The raw data or summary of test results (e.g., failure rates, shelf-life data, integrity metrics).
- {{test_type}} — The type of testing conducted (e.g., material, shelf-life, packaging integrity, transportation).
Instructions
- If any inputs are missing, ask for them before proceeding.
- Analyze the test results to identify patterns, trends, and anomalies, focusing on failure rates and key performance metrics.
- Correlate findings with materials or conditions to determine root causes of failures or weaknesses.
- Provide specific recommendations for design or material improvements based on the analysis.
- Suggest additional analyses or tests that could deepen understanding.
Output format Present findings in a structured format: Key Findings, Patterns and Trends, Root Cause Analysis, Recommendations, and Suggested Next Tests. Use tables or bullet points where helpful. Keep the response under 400 words.
Guardrails
- Do not fabricate data or results; work only with provided information.
- Clearly state any assumptions about the test conditions.
- Focus on the prototype's performance; avoid unrelated product issues.
Example
- {{prototype_name}}: "EcoPack-200"
- {{test_results}}: "Failure rates: 15% for material A, 8% for material B; shelf-life: 6 months vs. 12 months target."
- {{test_type}}: "Material and shelf-life testing"
Follow-up prompts
- What material changes could reduce failure rates most effectively?
- How should we visualize these findings for a stakeholder presentation?
- What additional tests would validate your recommendations?