"Hey, my name is Artem and this is CubeFM. What would it take for you to trust an AI recommendation on a production-bound infrastructure change? What's the bar? The bar is really high. To answer the question directly, to trust AI, especially to deploy something in production for critical infrastructure, or if you're responsible for a critical managed platform or if you're responsible for a platform, so it's becoming very difficult to trust AI if you're doing some, I don't know, sort of commutation stuff, or if you have some code, or I mean just some comments, it's becoming very easy, and then we say, okay, it will maybe work, it will maybe not work, so we establish in our team, we say, okay, let's establish rules between AI and human-generated part, so we can say, if it's critical code, or something can go wrong, we need to review it. If it's just some comments in this code, it's be okay, so now we also create, we modified our pull request templates with kind of, this is fully generated AI, I understand the logic, but I don't get all the libraries they are called, and then you can click it on the pull request, so we understand if it's touch-critical code, and the coder or the platform engineer doesn't get it, so we don't trust it and we need to review it. If the coder says, I understand the code, I understand the library, I get it, AI just help me, our point what we want to achieve is to make it traceable, what's coming from the AI part, what's not, and based on this context, we try to think about it and integrate it, what we trust or what we don't trust, so it's not so easy to explain where the bar is, but just to blindly to trust the AI to push the production, I say at the moment not, maybe in the future, so this is how we handle it or try to handle it, but it's also a challenge to solve."