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.
- Distinguishing between Machine Learning, Deep Learning, and Rule-based Systems.
- The evolution of software testing through the lens of AI.
- Key advantages and challenges of integrating AI into QA.
Data and ML Basics for Testers
- Understanding the difference between structured and unstructured data.
- Exploring features, labels, and training datasets.
- Overview of supervised and unsupervised learning.
- Introduction to model evaluation metrics (accuracy, precision, recall, etc.).
- Analyzing real-world QA datasets.
AI Use Cases in QA
- Generating test cases powered by AI.
- Predicting defects using ML techniques.
- Prioritizing tests and implementing risk-based strategies.
- Conducting visual testing with computer vision.
- Analyzing logs and detecting anomalies.
- Applying Natural Language Processing (NLP) to test scripts.
AI Tools for QA
- Overview of AI-enabled QA platforms.
- Using open-source libraries (e.g., Python, Scikit-learn, TensorFlow, Keras) to build QA prototypes.
- Introduction to Large Language Models (LLMs) in test automation.
- Building a basic AI model to predict test failures.
Integrating AI into QA Workflows
- Evaluating the AI-readiness of your current QA processes.
- Combining CI with AI: Embedding intelligence into CI/CD pipelines.
- Designing intelligent test suites.
- Managing AI model drift and retraining cycles.
- Ethical considerations in AI-driven testing.
Hands-on Labs and Capstone Project
- Lab 1: Automating test case generation with AI.
- Lab 2: Constructing a defect prediction model using historical test data.
- Lab 3: Leveraging an LLM to review and optimize test scripts.
- Capstone: Implementing an end-to-end AI-powered testing pipeline.
Requirements
Participants are expected to possess the following:
- At least two years of experience in software testing or QA roles.
- Proficiency with test automation tools (such as Selenium, JUnit, or Cypress).
- Basic programming knowledge, preferably in Python or JavaScript.
- Hands-on experience with version control and CI/CD tools (such as Git and Jenkins).
- No prior experience in AI/ML is necessary, though a strong curiosity and a readiness to experiment are essential.
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
Key topics can be discussed and agreed upon with the trainer in advance. Relaxed and pleasant atmosphere during the seminar days.
