Latest Articles
- 9 days agoProgramming
Data-Driven Tests Multiply Runs, Not Coverage
Looping one assertion over several payloads raises the test count. Whether it raises coverage depends entirely on whether the rows disagree with each other.
- 12 days agoProgramming
Self-Healing Tests Repair the Symptom
A healer agent that rewrites a broken locator makes the test green again and throws away the only notice you had that the interface changed.
- 15 days agoAI Coding
Automate the Triage, Not the Test Writing
Agents get built for authoring tests because authoring demos well. Two thirds of the real workload is maintenance and failure investigation, and triage is the better target.
- 16 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.
