We're aware of transient container creation issues and are actively working on improvements. Your latest deployment for groupgpt-cortex-api currently shows as still deploying, so it may still be progressing. If it fails, please try redeploying after a short wait rather than queuing multiple attempts, as consecutive deployments can compound delays.

This is the 3rd of forth time, but there is an issue on your end? I made a mistake and took down the production so I'm just trying to get it back up lol, I didn't know this was going on when I made that choice now my backend is down.

Hey, you're back up. I checked your backend directly and the current deployment is running as of a few minutes ago.

The 3-4 failures you hit were a platform issue in us-west2, not anything you did. Container creation on a subset of hosts was failing June 11-12, your retries kept landing in the bad window. Really sorry it caught you mid-recovery of your own takedown, that's the worst possible timing.

You shouldn't need to do anything. If the next deploy fails again, reply here and I'll look at it directly.