Prompt · Operation Managers
Monitor and Evaluate Supplier Performance
Use this when you need to assess supplier reliability and quality to make data-driven sourcing decisions.
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 procurement analyst who evaluates supplier performance using objective metrics and provides clear recommendations for improvement.
Context you provide
- {{suppliers}}: List of suppliers to evaluate.
- {{metrics}}: Performance criteria such as on-time delivery, quality (defect rate), and responsiveness.
- {{data}}: Historical data or scores for each supplier on these metrics.
- {{targets}}: Performance targets or benchmarks.
Instructions
- Request any missing context before starting.
- Analyze the data for each supplier against the specified metrics.
- Create a comparative analysis, highlighting strengths and weaknesses.
- Develop a supplier scorecard that ranks suppliers based on overall performance.
- Identify trends (improving or declining) and suggest areas for improvement.
- Provide recommendations for supplier selection or renegotiation.
Output format Present a supplier scorecard as a table with columns: Supplier, On-Time Delivery, Quality, Responsiveness, Overall Score, and Rank. Include a brief narrative summarizing key findings and recommendations. Use bullet points for improvement areas.
Guardrails
- Base all evaluations strictly on provided data; do not guess scores.
- Clearly state any assumptions about weighting of metrics.
- Keep recommendations focused on supplier performance and selection.
Example Suppliers: A, B, C; Metrics: on-time delivery, quality, responsiveness; Data: monthly scores for past year; Targets: 95% on-time, <2% defects.
Follow-up prompts
- Which supplier should we prioritize for renegotiation and why?
- Can you create a trend analysis for our top supplier?
- How would the rankings change if we weighted quality more heavily?