Program

AI for QA (online)

The AI for QA (online) training program is designed to equip QA professionals with the skills to effectively leverage Artificial Intelligence in testing processes and professionally test AI-powered systems. Throughout the program, participants will gain hands-on experience in AI-driven test automation, managing AI-generated tests, measuring key QA metrics, and developing testing strategies for LLM, RAG, and Agent-based systems.

Application to the program is currently not active
Start date

September 2026

Duration

2 weeks

Group size

15-20

Schedule

Four days a week

Admission requirements
Age

18 years and older

Language skills

Knowledge of English at least Intermediate level

Requirement

QA and Test Automation Experience; To have a personal computer or a laptop

Expectation

Be prepared for intensive training and willingness to constantly research additional materials

Upon the course completion you will::

Building test cases, test data, and automated test scenarios using AI

Developing modern test automation solutions using Selenium/Java and AI assistants

Managing AI-generated tests, assessing their quality, and measuring AI ROI through key QA metrics

Professionally testing LLM, RAG, and Agent based AI systems

Automating testing workflows and cross-tool integrations using MCP and AI agents

Managing risks, security, and data privacy considerations in AI powered systems

Program

AI for QA (online)
8

Number of modules

  • Prompt patterns: Role - Context - Format - Few-shot
  • AI-driven test case and edge-case generation
  • AI-generated test data (synthetic - boundary - negative)
  • Reproducibility & structured outputs (Gherkin / JSON)
  • Fundamentals: Test design techniques (BVA - EP)
  • AI coding assistant (prompt → test code)
  • AI-assisted debugging and refactoring
  • Manual test case → automated test
  • Fundamentals: Selenium + TestNG + Page Object Model (POM)
  • Fundamentals: REST Assured API Testing
  • MCP & Connectors: AI Agent → Browser (MCP Selenium)
  • AI → Bug Reporting in Jira (Claude Cowork + Atlassian Integration)
  • AI Agent → Database / DevTools / Slack Integration
  • Bonus: End-to-End Automation with n8n (CI → Automatic Bug Creation)
  • AI/ML Self-Healing (Healenium)
  • AI-Based Root Cause Analysis (Stack Trace + DOM)
  • Flaky Test Management & Retry Strategies
  • Fundamentals: Locator and Wait Strategies
  • AI Test Review Practices
  • Trust Boundaries: When Not to Trust AI
  • AI Test Debt & Maintainability
  • Test Suite Health & Ownership
  • Flakiness Rate · Test Coverage (Meaningful vs. False Coverage)
  • Cycle Time · Escape Rate · MTTR (Mean Time to Recovery)
  • AI ROI: Time and Cost Savings
  • Dashboards & Team Reporting
  • Non-Determinism & Hallucination Testing
  • LLM Evaluations (Golden Set · LLM as a Judge)
  • Prompt Injection & Security Testing
  • RAG and Agent Behavior Validation
  • Prompt Regression Testing (Versioning)
  • On-Premises Deployment · PII · Prompt Data Leakage
  • AI Governance & Policies (Banking Requirements)
  • Risk Assessment in AI Driven QA
  • Capstone Project: End to End AI QA Strategy