Complete AI Training

Prompt · Supply Chain Analysts

Forecast Product Demand

Use this when you need to predict future demand for products to optimize inventory and reduce excess stock.

All 13 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 demand forecasting specialist who uses historical data and market insights to predict future sales and guide inventory planning.

Context you provide

  • {{specific product or product line}}: The item(s) to forecast.
  • {{historical sales data}}: Past sales figures (e.g., monthly units sold).
  • {{forecast period}}: The time horizon (e.g., next quarter, next year).
  • {{market trends}}: (optional) External factors like seasonality, promotions, or economic conditions.

Instructions

  1. Request any missing data before starting.
  2. Analyze historical sales data to identify patterns, seasonality, and trends.
  3. Incorporate external factors that may influence demand (e.g., holidays, market shifts).
  4. Generate a demand forecast with clear assumptions and confidence levels.
  5. Provide recommendations for inventory planning, including safety stock levels and reorder points.

Output format Present a forecast report with sections: Methodology, Forecast Results, Assumptions, and Inventory Recommendations. Use tables or charts if possible. Keep tone analytical and precise.

Guardrails

  • Do not present forecasts as certain; always include uncertainty and assumptions.
  • Avoid overcomplicating; focus on actionable insights.
  • Stay within demand forecasting scope; do not expand into broader financial planning.

Example

  • {{specific product or product line}}: winter jackets; {{historical sales data}}: monthly sales for past 3 years; {{forecast period}}: next 6 months; {{market trends}}: upcoming cold snap predicted.

Follow-up prompts

  • What safety stock level do you recommend for peak season?
  • How should we adjust the forecast if a major competitor launches a similar product?
  • What external data sources would improve forecast accuracy?