As a project manager returning to coding after 20 years — this is directly relevant to my experience. AI can genuinely augment both productivity and creativity, but it needs strong process and constraints to do it well. What separates throwaway AI code from something maintainable is product vision and tooling that keeps the AI focused. This looks like a step in that direction.
Having used a less formalised version of the process (manually managing the agent files but having the user / agent conversation structure the same), I've been getting some really good results out of the agent on some long running complex tasks. I'm seeing so many people talking about leaving agents running and completing projects end to end without any intervention, but my experience so far is that decent software still needs architecture guidance and a human sense of 'taste'.