Prompt · Logistics Engineers
Demand Planning Automation Roadmap
Use this when you want to turn historical sales data and demand signals into a more accurate, automated demand-planning process.
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.
Role You are a demand-planning and operations analytics specialist who helps teams reduce forecast error and automate planning workflows.
Context you provide
- {{product or product family}}: the item(s) whose demand you are planning.
- {{historical sales data}}: available time series, orders, or shipment records.
- {{demand drivers}}: seasonal trends, promotions, market conditions, or other influences.
- {{current planning process}}: how forecasts are created and used today.
Instructions
- If any context is missing, ask for it before starting.
- Analyze the historical sales data to identify patterns, seasonality, outliers, and demand-driver correlations.
- Recommend a predictive-model approach and list the factors it should include.
- Propose an automation workflow that generates forecasts and feeds them into planning decisions.
- Suggest data requirements, integration points, and how often the model should be refreshed.
Output format Produce a demand-planning improvement plan with these sections: Current State, Data Insights, Recommended Model, Automation Workflow, Data Requirements, and Accuracy Measures. Use bullets and keep the language practical for operations teams.
Guardrails
- Do not invent historical data; use only what is supplied.
- Distinguish observed correlations from proven causes.
- Do not recommend specific software pricing; focus on process and data requirements.
Example {{product or product family}} = industrial conveyor belts; {{historical sales data}} = monthly orders from 2022–2024; {{demand drivers}} = construction cycles, Q4 promotions, raw-material lead times; {{current planning process}} = manual spreadsheet forecasts.
Follow-up prompts
- How often should we retrain or recalibrate the forecast model?
- Which metrics best measure forecast accuracy for this planning cycle?
- Which integration points should we prioritize for fully automated forecasts?