Playwright with AI: Agents, Context, and Test Automation Patterns

Course details

Modern test automation demands speed, reliability, and the ability to adapt as applications evolve. This course is designed for QA test automation engineers who are responsible for end-to-end, cross-browser automation in CI/CD environments, as well as web developers who want to automate tests to protect their code. Join instructor Andrew Knight as he shows you how to build stable Playwright tests that run consistently across browsers and environments, then enhance your workflows with AI-powered test generation and self-healing techniques that reduce flakiness and maintenance time. Along the way, you'll also learn how to optimize test execution, apply predictive test selection, and integrate Playwright into CI/CD pipelines for continuous testing and faster releases.

Learning objectives
Build reliable end‑to‑end Playwright tests across browsers and environments.
Create AI‑enhanced, self‑healing test scripts that adapt to UI changes.
Generate and refine test cases from natural‑language prompts.
Use predictive test selection and performance optimization techniques.
Integrate automated tests into DevOps pipelines for continuous delivery.

Concepts

Introduction

Smarter web testing starts with Playwright and AI
Using GitHub Codespaces

Exploring the App and Vibe Coding for Rapid Insights

Framing the test development process
Using AI to rapidly explore a web app s behavior
Vibe-coding raw Playwright scripts

Discovering Tests with Playwright's Planner Agent

Adding Playwright agents to the project
Generating a test plan automatically with the Planner Agent
Executing tests directly from natural-language plans

Formulating Test Code with Playwright's Generator Agent

Converting test plans into Playwright test scripts
Improving AI-generated tests for accuracy and focus

Automating Reliable Execution with Playwright's Healer Agent

Using the Playwright Healer Agent to fix broken tests

Switching Playwright's Agents from MCP to CLI

Configuring Playwright CLI with skills
Generating new tests with Playwright CLI and skills

Scaling Maintainability with Page Objects and Fixtures

Refactoring Playwright tests using page objects
Building test fixtures for clean, maintainable code

Expanding Test Coverage Strategically

Uncovering what tests are missing
Deriving tests directly from existing specs
Automating API tests with AI assistance
Doing exploratory testing with screenshots and videos

Optimizing Parallelism, Collisions, and Large Suites

Detecting and fixing parallel test collisions in Playwright

Running Playwright Tests in CI CD Pipelines

Building a GitHub Actions pipeline for Playwright tests
Running the pipeline to execute Playwright tests

Conclusion

Next steps