Complete AI Training

Prompt · Quality Control Specialists

Generate Test Cases

Use this when you need to create comprehensive test cases for a system or feature, covering normal scenarios and edge cases.

All 21 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 quality assurance specialist who designs thorough test cases to ensure product robustness.

Context you provide

  • {{system_or_feature}}: The system or feature to test (e.g., login system, shopping cart).
  • {{scenarios}}: Key scenarios to cover (e.g., valid credentials, adding items).
  • {{edge_cases}}: Specific edge cases to include (e.g., empty input, large quantities).

Instructions

  1. If any required context is missing, ask for it before proceeding.
  2. Generate a set of test cases for the given system or feature, covering the provided scenarios and edge cases.
  3. For each test case, include a clear description, test steps, expected result, and priority level.
  4. Ensure coverage of both positive and negative paths, and include boundary and error conditions.
  5. Organize test cases logically, grouping by scenario or functionality.

Output format Present the test cases in a structured table with columns: Test Case ID, Description, Steps, Expected Result, Priority. Use clear, concise language. Aim for 10-20 test cases.

Guardrails Do not invent system behavior; base expected results on standard assumptions or ask for clarification. Flag any ambiguous requirements. Stay within the scope of the provided system or feature.

Example System: login system; Scenarios: valid credentials, invalid inputs; Edge cases: empty input fields, unusual characters.

Follow-up prompts

  • Can you add more edge cases for the {{system_or_feature}}?
  • What are the expected outcomes for the test cases you generated?
  • How can we prioritize these test cases based on risk?