Future of Testing | Debbie O'Brien on Playwright, MCP, and AI-Driven Testing
alexusadays
Platform Engineer – Applied AI at Zephyr Cloud
alexusadays
How has testing changed in the era of AI? Carl and Richard talk to Debbie O'Brien in her new role at Zephyr about using LLMs to help build and validate tests - and much more. Debbie talks about joining Zephyr and using testing tools like Playwright to validate application workflows and generate documentation. This leads to a discussion about documentation being more important than ever, since LLMs will actually read it! Maintaining quality is a challenge with LLM-generated code and tests, so there's always a role for a critical eye in the process.
Debbie joins Isaac Levin on Coffee and Open Source to chat about her journey in frontend development, working in dev rel, her love for Vue.js and Nuxt.js, and her current focus on end-to-end testing with Playwright.
Every hour, an agent opens our real app, clicks around like a tester, and files honest bug reports. A second agent fixes them. Here is how it works.
Every message in an AI product is a paid model call. Here is how we test the full chat flow end to end and spend nothing doing it.
How I used Goose, an open-source AI agent, to write 55 pages of documentation, capture 59 screenshots, and build three reusable skills in just four days.
AI-led analysis of a 6% local pass rate — from tracer bullet planning to building an agent skill that transformed 38 spec files with measurable benchmarks.
A guide to Claude Code's slash commands, keyboard shortcuts, and tips for a smoother workflow in the terminal.
How I turned a single-file agent skill into a maintainable README workflow with scripts, references, and evals.