Latest Articles
- 11 days agoAI Coding
Spec Kit Writes Tasks, Not Tests: Tie Every Acceptance Criterion to One
Spec-driven AI workflows give you a spec and a task list. Nothing in them proves the spec's behaviour is tested. A numbered-criteria check, run with Playwright, closes the gap.
- 13 days agoProgramming
Interrupting a Voice Agent Is a State Ownership Problem
The agent that talks over you and the one that flinches at every breath share a cause: whatever hears you and whatever speaks sit on opposite sides of a network boundary.
- 14 days agoProgramming
I Put a Decision Model in a Playwright Loop. It Missed 2 of 3 Bugs
A model picks the next probe and judges each result while Playwright drives the page. What a small local run showed about confidence, exploration, and what code should check.
- 16 days agoAI Coding
Most Agent Concepts Are Old Ideas With New Labels
Of the thirty terms on the standard reading list, most are ordinary engineering renamed or product categories in disguise. Six have no prior analogue. Those six are the work.
