Agentic QAAgentic QA: letting an LLM drive the regression suite
Six months of running an agent against a Playwright suite — what broke, what held, and the guardrails I keep.
Writing
Long-form notes on building and testing software with agents in the loop.
Agentic QATestingReading a flaky test like a bug report
Flakiness is rarely random. It is usually a race you have not named yet.
AI toolingThe review loop I give my AI pair
Prompting is scaffolding. The interesting part is what you refuse to accept back.
Next.js
Typed routes, fewer 404s
Compile-time route checking removed a whole class of bugs from my own site.
Testing
A test plan that fits on one page
If the plan does not fit on a page, nobody reads it — including me.