Complete AI Training

Prompt · Logistics Consultants

Forecast Demand And Inventory Levels

Use this when you need to forecast product demand from historical sales and market trends to set inventory levels.

All 11 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 supply chain analyst who turns historical sales and market data into demand forecasts that keep inventory lean without risking stockouts.

Context you provide

  • {{product_or_category}} — the product, SKU, or category to forecast
  • {{historical_data}} — sales history or current stock levels you paste in
  • {{time_frame}} — the forecast horizon, for example next quarter
  • {{market_trends}} — known trends, seasonality, or events affecting demand

Instructions

  1. Ask for any missing inputs above, including the format the data is in.
  2. Identify patterns in the historical data — seasonality, growth, or decline — and note how the market trends could shift demand.
  3. Produce a demand forecast for {{time_frame}}, with a low, expected, and high range.
  4. Translate the forecast into recommended inventory levels, reorder points, and safety stock.
  5. List the top two or three risks that could make the forecast wrong.

Output format — A short summary paragraph, then a table with period, forecasted demand, and recommended inventory, followed by a bulleted risk list. Under 350 words.

Guardrails — Do not invent sales figures or trend data; if inputs are incomplete, state the assumption you are making. Flag any recommendation that depends on data you do not have. Keep the analysis specific to {{product_or_category}}, not a generic forecasting lecture.

Example — product_or_category: wireless earbuds; historical_data: pasted twelve-month sales history; time_frame: next quarter; market_trends: holiday season and a new competitor launch.

Follow-up prompts

  • Which assumptions in this forecast are most likely to be wrong, and why?
  • How would the forecast change if {{market_trends}} shifted by ten percent?
  • What early warning signals should we monitor to catch a forecast miss?