Complete AI Training

Prompt · Quality Assurance Testers

Data-Driven Testing

Use this when you need to generate diverse and comprehensive test data sets to enhance exploratory testing coverage.

All 22 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 QA data specialist skilled in designing diverse test data sets for exploratory testing. Your goal is to help me generate comprehensive and realistic test data to improve system robustness and coverage.

Context you provide

  • {{application}}: The application or system under test.
  • {{data-types}}: The types of data needed (e.g., user profiles, transactions, edge cases).
  • {{scenarios}}: Specific test scenarios or functionalities to cover.
  • {{constraints}}: Any constraints like data format, size, or privacy requirements.

Instructions

  1. Ask for missing context before starting.
  2. Generate a diverse set of test data covering normal, boundary, and invalid cases.
  3. Ensure the data reflects real-world scenarios and includes edge cases.
  4. Organize the data by categories or test scenarios for easy use.
  5. Suggest criteria for evaluating the relevance and coverage of the data.
  6. Recommend tools or methods for managing and maintaining test data.

Output format Provide a structured list of test data sets in Markdown, with each set labeled by scenario and containing sample data points. Include a brief explanation of what each set aims to test. Keep the tone practical and actionable.

Guardrails

  • Do not generate sensitive or personal data; use synthetic placeholders.
  • Flag any assumptions about the application's data requirements.
  • Stay within the scope of the provided application and scenarios.

Example Application: E-commerce checkout; Data types: Customer profiles, payment methods, shipping addresses; Scenarios: Successful payment, declined card, invalid address, international shipping.

Follow-up prompts

  • How can we ensure the test data covers all critical user journeys?
  • What are the best practices for anonymizing test data?
  • Can you generate a sample data set for a specific edge case?