How AI Generates Test Cases
AI Test Case Generation in AXQA is driven by structured input — not random assumptions. The system combines project context, selected parameters, and optional user notes to generate draft test cases that align with your intended testing scope.
Why it matters
- Generates relevant test cases aligned with your project context.
- Respects user-defined parameters such as test type and priority.
- Gives you structured drafts without forcing automatic insertion.
- Keeps full human control over what becomes part of your suite.
What the user provides
- Test type (e.g., functional, edge case, regression, etc.).
- Target or responsible role.
- Priority level.
- Number of test cases to generate (minimum: 2).
- Optional AI note to guide generation.
Note
In addition to these inputs, the system automatically references the project description defined by the user.
What happens in the background
- The system retrieves the project description.
- It combines the description with the selected parameters.
- If provided, the user’s AI note is included as additional guidance.
- The AI generates structured draft test cases.
- The drafts are presented for review — not automatically inserted.
Warning
The generation process also considers the project description and contextual information defined within your test case structure. Providing clear and well-written project explanations significantly improves the quality and relevance of the generated test cases.
Review before insertion
Generated test cases are displayed as drafts. At this stage, nothing is officially added to your project.
- You can review each draft individually.
- You can choose which test cases to insert.
- You can save drafts for later review.
Why drafts are important
- Prevents accidental pollution of your regression suite.
- Keeps final decision-making in human hands.
- Allows teams to refine and align test structure before activation.
Best practices
- Write a clear project description — it directly affects output quality.
- Use the AI note field to guide scope (e.g., focus on validation rules).
- Generate in small batches rather than large volumes at once.
- Review before inserting into active regression.
Common mistakes
❌ Leaving project description vague
✔ Provide meaningful context for better generation accuracy.
❌ Generating too many test cases at once
✔ Start with focused batches and refine gradually.
❌ Inserting all drafts without review
✔ Select only what fits your strategy.
Security & data handling
- AI operates strictly within the current workspace context.
- No draft is inserted automatically without user confirmation.
- Generated content remains editable and fully controlled by the user.
Related documentation
- AI Test Case Creation Overview
- AI Staffing Overview
- Automation Overview