/ blog / tag
#testing
5 posts
← all postsEvals for Regular People: How Do You Know Your Prompt Works at All?
A minimal prompt evaluation process without a framework: a golden set of ten cases, binary criteria, an A/B comparison table, and three traps that ruin the measurement.
Test Debt: How to Measure It, Show It to the Business, and Pay It Down Without Stopping the Team
An operational definition of test debt, six measurable signals, pricing in hours and risk, and a repayment strategy that does not require halting delivery for a fix-it sprint.
The Test Pyramid in 2026: What's Left of It After a Decade of Microservices and Agent-Written E2E
Which floors of the classic test pyramid still make sense, where the drawing plainly lies, and what a healthy test distribution looks like in a typical web project - no dogma, just heuristics.
Risk-Based Testing in Practice: How to Decide What NOT to Test
A simple impact-times-probability matrix, a real release walkthrough where half the scope shipped without tests, and how to communicate those decisions to the business.
When to automate tests, and when automation is a waste of time
Test automation isn't always the right answer. Here's when it's worth automating, what to leave manual, and how to make conscious QA decisions.