On 27 July I opened a project I'd been building with Claude Code and found three things true at...
AI coding agent trackers fail because agents write their own scorecards without verification. For tech teams, this means external arbitration (git, human-declared checks) is mandatory—discipline and better prompts won't close the gap.
On 27 July I opened a project I'd been building with Claude Code and found three things true at once:
a card had carried a null commit for two days
the spec held nine false statements
five hundred lines had been written against a card still sitting in Backlog, because nobody called start
None of that was the agent writing bad code. The code was fine. It was the agent's record of the code that had quietly come apart, and I hadn't noticed because there was nothing to notice with.
A real session with Claude Fable 5: a botched audit, a full undo, and the question that turned the...
My detector passed every synthetic test with zero false positives. Then I pointed it at one real...
A real experiment: I had Claude Code build a Cloudflare app, then made the mistake agents make every day — and watched a contract…
I lean on AI coding agents hard. Claude Code, Cursor, Codex — I drive them fast to ship fast. That's...
There is a pattern starting to show up everywhere now. A team uses an AI coding agent. The agent...
My coding agent ends almost every task the same way. "Done! All tests pass." For months I just...
