I was a big distributed, event-driven service guy for years. We used to talk about how it can make things 'faster' but you have to put some infrastructure around it in order to be able to move like that. I'm basically talking about CI/CD stuff, automated tests, security, load test, etc. You use feature flags, blue green deploys, stuff like that.
I _think_ that the same concept could apply to agentic code. If you have the guardrails in place, you could trust it a bit more. Anyway, that's a lot of what I think about and but have had limited success getting people to buy in as much as I think they should. :)
I completely agree. My first intervention with this person was to try to get them to set up a test driven development framework. Unfortunately, that's also when I learned he didn't know what that was. He also just copied "do TTD" into Claude. It was definitely my mistake, and probably over optimism about what AI might be able to do, that we didn't enforce that a lot earlier, and have been working on making sure to enforce a lot more gates going forward.