The problem isn't that agents are bad. It's that they fail the same way every time.

AI coding agents are fast. If you've reviewed enough agent-written diffs, though, you've seen the same short list of failures show up again and again:

A dropped await that turns an async call into a race you only find in production.

as any sprinkled in wherever the types didn't line up.

An import from a package that isn't in package.json.