Developers are shipping AI agents without any oversight mechanisms, I'm building a pattern library to fix that

Six months ago I started paying attention to how developers talk about AI agents they've built and shipped. Something came up again and again. They'd describe what the agent does. They'd mention a bug or an unexpected output. Then someone would ask: "What stops it from doing that again?" And the answer, often than not, was some version of: "I haven't really thought about that." This isn't negligence. It's a tooling gap. There's a lot of writing about AI safety at the research level - papers on alignment, interpretability, RLHF.