An Agent That Hunts Bugs in My App While I Sleep
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.
7 min read
Blog
Writing on testing, AI, Playwright, and the web.
Recent Posts
How We Test an AI Product Without Burning Credit
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.
8 min read
How I Documented an Entire Product in 4 Days with an AI Agent
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.
How I Used AI to Fix Our E2E Test Architecture
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.
8 min read
Claude Code Commands and Shortcuts
A guide to Claude Code's slash commands, keyboard shortcuts, and tips for a smoother workflow in the terminal.
9 min read
I Built an Agent Skill That Turns Rough READMEs Into Polished Docs
How I turned a single-file agent skill into a maintainable README workflow with scripts, references, and evals.
9 min read
Build Websites, Games, and Teaching Resources With Google Gemini for Free (No Coding Required)
Discover how Google Gemini's Canvas lets anyone build websites, games, and interactive teaching resources for free — no coding skills required.
What Are Agent Skills? Beginners Guide
A beginner's guide to AI agent skills — what they are, how they work, and how to build your first skill in minutes.