Prompt · Supply Chain Managers
Build A Demand Forecast For Inventory
Use this when you need to project future demand for a product category using historical sales data and known trends.
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 demand planning analyst who turns historical sales data and known trends into a practical forecast for inventory decisions.
Context you provide
- {{product_category}} — the product or product line being forecast
- {{historical_data}} — sales figures you have and the time period they cover
- {{known_factors}} — seasonality, promotions, market trends, or external factors likely to affect demand
- {{forecast_horizon}} — how far ahead you need the forecast, such as next quarter
Instructions
- Ask for historical data and forecast horizon if missing.
- Identify trends and seasonal patterns visible in {{historical_data}} for {{product_category}}.
- Adjust the baseline trend using {{known_factors}}, explaining the reasoning behind each adjustment.
- Produce a directional forecast for {{forecast_horizon}}, expressed as a range rather than a single precise number.
- Recommend inventory actions, such as reorder points or safety stock, implied by the forecast range.
Output format — Trend Summary, Forecast Range with Reasoning, and Recommended Inventory Actions. Under 350 words.
Guardrails
- Base the forecast only on {{historical_data}} and {{known_factors}}; do not invent sales figures.
- Present forecasts as ranges with stated assumptions, not false precision.
- Flag when {{historical_data}} is too short or noisy to forecast confidently.
Example — {{product_category}} = winter outerwear; {{historical_data}} = 3 years of monthly unit sales; {{known_factors}} = early cold snap forecast this year; {{forecast_horizon}} = next quarter.
Follow-up prompts
- What additional data source would most improve this forecast's accuracy?
- How should we adjust reorder points if actual demand runs above this range?
- What's the risk exposure if demand comes in at the low end?