This papers reviews AI coding, and in particular the exploding interest in vibe coding, both in terms of main existing framework, advantages and challenges. In particular, we point out in particular an aspect less often discussed: the potential complications for the support and maintenance of software products/code generated via vibe coding. These problems result especially because the generated code often ends up no more be understandable, even to its developers.Then, we introduce VIBE4M, a framework of workflows, policies and practices to alleviate these challenges. However, such approach goes against the trend that AI makes developers more productive, as they now must perform rigorous code verifications. It also goes against the objective of democratization of coding. Yes coding can be done with "no code", but such code is not maintainable, which may not matter for side projects, but matters for software products. If approaches like VIBE4M are applied, they may be hard to follow for non-programmers. Therefore, there would be value to now automate such frameworks.