AI Doesn't Write Bad Code. It Writes Convincing Code.

Over the last month I’ve been putting Claude Code through its paces inside a structured mono-repo “Foundry” environment.

I’ll say it plainly: I’m impressed.

But I’m also uneasy.

I’m not using it as autocomplete on steroids. I’m using it inside a real system:

• A mono-repo with clear structure
• Specs and ADRs (Architecture Decision Records) committed to the repo
• Ubiquitous language documented
• Clear architectural boundaries
• Defined quality gates

The Controversial Thought

Here it is:

AI is not dangerous because it writes bad code.

AI is dangerous because it writes convincing code.

Bad code you catch. Convincing code slips through — because a rushed reviewer, a busy engineer, or a stakeholder who wants the ticket closed will read the AI output, nod, and merge it. The code looks plausible. It might even work for the happy path. But it embeds assumptions nobody thought through, patterns nobody validated, and edge cases nobody tested.

The Working Hypothesis

Here’s what a month of real use has convinced me of:

AI performs dramatically better inside an opinionated, well-documented system. Without that structure, it amplifies chaos.

Give AI a codebase with clear boundaries, ADRs it can read, quality gates it must clear, and a ubiquitous language it can reason in — and it’s transformative. It compresses delivery time without cutting corners.

Give AI a codebase that’s a soup of inconsistent patterns, mystery abstractions, and undocumented decisions — and it will generate more of the same, faster. The output will look confident. The system will get worse.

This is why the Start with Good principle matters even more in an AI-augmented workflow. The structure that used to be optional for a small team becomes non-negotiable when you scale delivery with agents. The chaos gets scaled too.

What I’m Watching

If you’re leaning into AI-driven workflows: what is genuinely better today than a year ago?

If you’re skeptical or opposed: what risk do you believe early adopters are underestimating?

For QA leaders specifically: is this improving quality — or just shifting where defects surface?

No hype. No vendor pitches. Just signal.

Has AI changed how you build, or only how you type?