[zug_zug]

> This post covers how we got to a place where over 60% of our pull requests (PRs) are agent-assisted

Well I mean you could (and should) turn on 100% agent code-reviews, and that's a type of assistance.

The hard part is that most orgs never made disposable environments nor any meaningful local testing, so the ability to validate code doesn't break something indirectly (e.g. memory leak, hammer the prod DB, cache values with the wrong key, etc) isn't there. In my experience AI code has several subtle bugs and is deceptively dangerous (because it can look so competent in other ways).

[giancarlostoro]

> The hard part is that most orgs never made disposable environments nor any meaningful local testing, so the ability to validate code doesn't break something indirectly (e.g. memory leak, hammer the prod DB, cache values with the wrong key, etc) isn't there. In my experience AI code has several subtle bugs and is deceptively dangerous (because it can look so competent in other ways).

There's ways to improve on this, but nobody ever wants to invest more in disposable dev environments, dev is always the wimpiest environment of them all.