Voice Governance

Read ten AI-assisted "About" pages and you'll notice they sound identical. The same cadence, the same transitions, the same way of building to a point. Different words, same voice. The person disappears and what's left is the tool's default register. You can fix this partially with style guides, voice examples, tone specifications. The output gets better than the default, but it still won't sound like the person. It sounds like an AI doing an impression of a style guide. The reason is structural, and once I figured out why, I could build something that actually works. Why it happens Large language models learn to write from published text. Blog posts, articles, marketing copy, documentation, books. All of it polished. All of it shaped for an audience. Published writing is a performance. The way someone writes a LinkedIn post is not how they think. The way someone writes a case study is not how they explain the same project to a friend over dinner. The rough edges, the false starts, the