The stability question is real but I think it's framed wrong. The issue isn't whether an agent can write correct code in a single session -- they can, and pretty reliably now. It's whether there's a human with enough understanding of the codebase to debug it when something breaks at 2am.

I run parallel coding agents on my own projects daily. The code they produce is fine. What worries me is the "just ship it" energy where nobody on the team deeply understands what got built. That's not an AI problem, it's been a problem with outsourced codebases forever. AI just makes it faster to accumulate code nobody fully groks.

Cloudflare probably has the engineering depth to maintain this regardless of how it was built. A lot of other teams don't.

I too have seen a lot of comments asking where the products are. If you're now moving the goal posts to "stay online in the long run" you're gonna have to wait until there's been a long run to stay online in. Agents aren't that old yet.

This will largely be based on the maintainers’ priorities. Coding agents can audit and clean up code too, provided that you set the right goals.

Try again a few times, it ends up loading.