Beyond Code Coverage: Functionality Testing with Playwright MCP
summary
Argues for flipping TDD so an agent writes failing Playwright tests first and then generates code to make them pass demonstrates this with the Playwright MCP server and GitHub Copilot CLI running against a toy store search feature the agent types search queries clicks category and price filters and the headed browser shows Furby and Simon results tests go red then green and screenshots and headless runs are recommended for CI and per‑feature tests are encouraged
AI-written summary · about
chapters (13)
- 0:00Introduction to GitHub Octoverse stats and 2025/2026 growth
- 2:13Does AI actually increase developer productivity?
- 3:52Importance of maintaining a clean codebase
- 4:36Test-Driven Development (TDD) and the Red-Green-Refactor cycle
- 6:07Common criticisms of TDD and unit testing
- 7:43The problem with AI-generated self-affirming tests
- 8:09Introduction to Playwright for functional testing
- 9:18Integrating AI agents with Playwright for faster TDD
- 10:54Live Demo: Adding search and filter features to a toy store app
- 12:25Using GitHub Copilot CLI and Work IQ for feature requests
- 13:50Generating and running Playwright tests live
- 16:10Best practices for using AI with Playwright
- 17:30Q&A: Handling state management and testing across different screen sizes
related talks
48mSupercharged Testing: AI-Powered Workflows with Playwright + MCP
35mState of end-to-end testing for modern web applications
49mReal World Lessons from Scaling Test Automation
43mLeveraging GitHub Copilot to 3X Your Playwright Test Efficiency
29mPlaying your tests wright
51mAdvanced Playwright Techniques for Flawless Testing
17mTesting with Playwright in an AI-Assisted Development World
45mAI-Powered Debugging & Browser Automation with Playwright MCP