We’ve gone fully AI-native on purpose: AI writes code, AI reviews code, AI helps debug. Some people call that overuse. Fair.

This series is a practical stress-test of the usual objections, from inside an AI-first workflow: I design the system, direct the agents, and use AI to structure reviews so my attention goes where the risk is.

The bet: if you steer with architecture, separate concerns for review, and keep humans on the hard paths, end-to-end AI is a workflow you can defend. If those pieces are missing, the critics are right.

Drafted with AI. Reviewed and edited by Ed Henderson.

How to read this

Each post: the common claim, what I’ve seen in practice, where the objection still bites, and what I’d change in the workflow. Start with #1 and #2.

Published

Coming up

Confident wrongness · Architecture drift · Test theater · Security / secrets · Ops blindness · Skill atrophy · Ownership fog · Context window lies · Dependency / license sludge · Team sync (design in chat history) · Speed addiction · Evaluation gap