Bridging AI-Generated Acceptance Criteria with Comprehensive Test Scenarios
The generation of acceptance criteria through generative AI is an innovative approach to streamline the requirements gathering process. However, ensuring that the implemented code aligns with these criteria is crucial for delivering high-quality software. This talk explores the integration of generative AI generating acceptance criteria with test case scenarios, aiming to establish a seamless connection between the development and testing phases. By leveraging pull requests as a central hub, this approach facilitates the validation of whether the test case scenarios adequately cover the specified acceptance criteria, thereby enhancing the overall efficiency and reliability of the software development lifecycle. To bridge the gap between acceptance criteria and test case scenarios, a structured approach is required. Start by embedding the generative AI-generated acceptance criteria within the development documentation. This can be achieved through our personalized LLM. Each acceptance criterion should be linked to its associated test case scenarios, evaluating if the tests cover all the defined criteria and establishing a clear correlation between the expected behavior and the validation process.
Ariadna Trueba studied technology at University and started working in the IT department, until she realized she had a passion for checking bugs and issues. She decided to start investigating further into the QA side and after working as a long experienced QA manual, started diving further into QA automation. During that period, Ariadna discovered that she wanted to move forward with Quality Management System, knowing how quality should be planned and how it can be applied in every situation. Ariadna is currently a QA Technical Director at Parser, advising clients on quality, preparing strategies, and leading QA teams to achieve confidence in their products through correct quality strategy.