Thank you for sending your enquiry! One of our team members will contact you shortly.
Thank you for sending your booking! One of our team members will contact you shortly.
Duration 21 hours
Course Outline
Introduction to AI for QA
- Defining Artificial Intelligence in a professional context.
- Distinguishing between Machine Learning, Deep Learning, and Rule-based Systems.
- Tracing the evolution of software testing through the lens of AI.
- Exploring the primary advantages and potential challenges of AI in QA.
Data and ML Basics for Testers
- Differentiating between structured and unstructured data.
- Understanding features, labels, and the role of training datasets.
- Overview of Supervised and Unsupervised learning paradigms.
- Basics of model evaluation metrics (accuracy, precision, recall, etc.).
- Application of real-world QA datasets.
AI Use Cases in QA
- Automating test case generation via AI.
- Applying Machine Learning for defect prediction.
- Leveraging AI for test prioritization and risk-based testing strategies.
- Implementing visual testing using computer vision technologies.
- Performing log analysis and identifying anomalies.
- Utilizing Natural Language Processing (NLP) to enhance test scripts.
AI Tools for QA
- Survey of major AI-enabled QA platforms.
- Creating QA prototypes using open-source libraries (e.g., Python, Scikit-learn, TensorFlow, Keras).
- Introduction to Large Language Models (LLMs) in the context of test automation.
- Developing a basic AI model to forecast test failures.
Integrating AI into QA Workflows
- Assessing the AI-readiness of current QA processes.
- Embedding intelligence into CI/CD pipelines through Continuous Integration.
- Architecting intelligent test suites.
- Oversight of AI model drift and managing retraining cycles.
- Navigating the ethical considerations inherent in AI-powered testing.
Hands-on Labs and Capstone Project
- Lab 1: Automating the generation of test cases using AI.
- Lab 2: Constructing a defect prediction model based on historical test data.
- Lab 3: Leveraging an LLM to review and refine test scripts.
- Capstone: Designing and executing an end-to-end AI-powered testing pipeline.
Requirements
Participants are expected to bring the following background:
- At least two years of experience in software testing or QA positions.
- Proficiency with test automation frameworks (such as Selenium, JUnit, or Cypress).
- Fundamental programming knowledge, preferably in Python or JavaScript.
- Hands-on experience with version control and CI/CD systems (e.g., Git, Jenkins).
- No prior experience in AI/ML is mandatory, provided there is a genuine curiosity and a readiness to experiment.
Testimonials (3)
The possibilities of postman and future use of it.
Gordana Gacic - SEE Digital D.O.O.
Course - API Testing with Postman
hands on exercises, easier to retain information
ashley bolen - Insurance Corporation of British Columbia
Course - Test Automation with Selenium
The trainer's availability to answer questions, as well as the concrete and visual demonstrations on TestComplete.
Radia - Cegid
Course - TestComplete
Machine Translated
