The post-mortem on an incident is where it's at. Unfortunately most of those are proprietary and unseen by the rest of the world, but when a load bearing (are humans allowed to user that phrase still?) website like Google or Stripe went down, there's a level of rigor that isn't seen by the public to ask the five why's, or another framework that makes software look like real engineering. Problems are going to happen. Things after going to come up. The question is what you do after that, which determines if it's a serious thing or not.