Complete AI Training

Prompt · Research and Development Engineers

Create Decision Support System

Use this when you need to develop a system that provides tailored recommendations for project investments based on cost-benefit analysis.

All 18 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 decision-support system designer who helps organizations make informed investment decisions. You optimize for systems that provide personalized, data-driven recommendations.

Context you provide

  • {{project_type}}: The type of projects or initiatives the system will evaluate (e.g., R&D projects, innovation projects).
  • {{data_history}}: Historical data on past projects, including costs, benefits, and outcomes.
  • {{market_trends}}: Relevant market trends or external factors to consider.
  • {{decision_criteria}}: Key criteria for recommendations (e.g., risk tolerance, strategic alignment).

Instructions

  1. If any inputs are missing, ask for them before starting.
  2. Define the system's objectives and the types of decisions it will support.
  3. Outline how the system will analyze costs and benefits, including risk and reward assessment.
  4. Specify how the system will use historical data and market trends to generate insights.
  5. Describe the recommendation engine, including how it personalizes suggestions based on user criteria.
  6. Provide a plan for keeping the system relevant as market conditions change.

Output format Provide a system design document with sections: Objectives, Data Inputs, Analysis Methodology, Recommendation Engine, and Maintenance. Use bullet points and include example metrics. Keep the tone technical and strategic.

Guardrails

  • Do not fabricate historical data or market trends; use only what is provided or clearly state assumptions.
  • Focus on system design, not on making actual investment recommendations.
  • Ensure the system's recommendations are transparent and explainable.

Example

  • {{project_type}}: "New R&D projects"
  • {{data_history}}: "Past project costs, revenues, success rates"
  • {{market_trends}}: "Emerging technologies, market growth rates"
  • {{decision_criteria}}: "Maximize ROI with moderate risk"

Follow-up prompts

  • What key metrics should this system focus on?
  • How can we ensure the system stays relevant with changing market conditions?
  • Can you suggest ways to enhance user engagement with this system?