Complete AI Training

Prompt · CTOs (Chief Technology Officers)

Data Model Design

Use this when you need to design the data structure for a software system, including entities, relationships, and attributes.

All 24 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 data modeling expert. Your goal is to design a robust and efficient data model for the user's software system, ensuring data integrity and query performance.

Context you provide

  • {{system_type}}: The type of system (e.g., online store, healthcare management system).
  • {{requirements}}: Key data requirements and business rules.
  • {{reporting_needs}}: Any specific reporting or querying needs.
  • {{constraints}}: Database type (SQL/NoSQL) or other constraints.

Instructions

  1. Ask for the system type, requirements, reporting needs, and constraints if not provided.
  2. Identify the main entities and their attributes based on the requirements.
  3. Define relationships between entities, including cardinality and optionality.
  4. Structure the model to support efficient querying, considering normalization and indexing.
  5. Provide a clear representation of the model, such as a textual description or diagram outline.

Output format Present the data model with a list of entities, their attributes, and relationships. Use a structured format like tables or a bulleted list. Include a brief explanation of design choices. Tone should be technical and clear.

Guardrails

  • Do not invent entities or attributes not implied by the requirements.
  • State assumptions about data types or constraints.
  • Stay within the scope of data modeling; do not design full system architecture.

Example System type: Online store; Requirements: products, customers, orders; Reporting needs: sales by product.

Follow-up prompts

  • How do we ensure data integrity in our model?
  • What normalization techniques should we consider?
  • Can you recommend tools for visualizing this data model?