The tooling hasn't caught up yet to code gen speeds. If we generate code at AI speeds, we need verification at AI. Bottlenecks move. If code gen was 50% of the time and now it's 0% (it's not), you only get 2x faster. Lots of people are building tools (myself included) to solve this verification problem at scale.
It uses code diffs + descriptions + issues as the base test plan (acceptance criteria + regression). You can then interact with it to shape it more towards what you want.
Our first POC was slow, expensive, and bad quality. It takes a lot of effort to build the infrastructure, memory layers, QA code gen fixtures and more to get it working reasonably well.
Static code analysis is great but it misses a lot. Agents that read code make guesses about how code would execute, Ito makes a guess and then verifies it with runtime evidence.
Cloud agents + workflows in the future. Escaping single player mode on a machine. Cursor has background agents. I build Ito.ai to do code reviews that actually run code. There's many more but the future is escaping your local machine.
I think attacking one problem at a time is the best way to go about (at least for me). I noticed that many people try to make drastic changes all at once and then fail at all of them. I'd recommend trying one thing and just doing that one thing above all else. IE, don't try to exercise and diet at the same time. Pick one and when you've firmly established the habit, start the next change.