Latest Articles
- 17 days agoAI Coding
A Passing Agent Test Says Nothing About the Path It Took
A refund agent returns the right answer and the ledger is correct. The test is green. Why final-state assertions miss what an agent did, and how to check the path.
- 19 days agoAI Coding
When an Agent Misbehaves, Which Layer Broke?
Harness, loop and graph is one more taxonomy unless it changes what you fix. It does, because each layer has its own symptoms, its own test, and one costly misdiagnosis.
- 22 days agoAI Coding
Agent Maturity Ladders Are Three Ladders Stacked Wrong
Capability, autonomy and reach get numbered as one sequence, which hides the only axis where risk actually scales. Sorted properly, where to stop becomes obvious.
- 22 days agoProgramming
Playwright 1.64: WebMCP, Locator.within(), and Smarter Runs
Playwright 1.64 adds WebMCP tool testing, locator.within(), video fps/VP9, project defaults, --shuffle, and breaking visibility rules. What to adopt first in a real suite.
