AI-Powered Debugging & Browser Automation with Playwright MCP
summary
Playwright MCP generates end to end tests from prompts, runs them, and reports results with roughly 50/50 initial pass rate during the demo; the agent explores the site, creates a spec for the conference registration flow, and auto-runs tests that produce screenshots and traces. Debugging uses copy prompt from the HTML reporter or the VS Code fix with AI button, and MCP relies on accessibility snapshots to drive robust locators; human review is still required.
AI-written summary · about
chapters (9)
- 0:00Welcome
- 3:37Playwright and MCP intro
- 7:45Installing Playwright MCP
- 11:11AI test generation setup
- 14:15Live demo: test generation
- 27:27AI agents for website exploration
- 33:58Manual test reports with AI
- 39:23Best practices
- 40:28Q&A
related talks
25mAI-Powered Debugging & Browser Automation with Playwright MCP
48mSupercharged Testing: AI-Powered Workflows with Playwright + MCP
39mHow to Use AI with Playwright for UI & API Testing
35mState of end-to-end testing for modern web applications
01h 31mWorkshop: Advanced Web Testing with Playwright and AI
13mHow to Use Playwright for Automating Accessibility Testing
48mBeyond Bugs: How AI Turns QA into Full-Cycle Engineers
17mTesting with Playwright in an AI-Assisted Development World