Nate B Jones frames slow delivery with AI coding agents as a problem of team setup, using Lauren Tan's reported pull request output as an illustration of what a carefully designed workflow can enable rather than a target every engineer should meet. He stresses that pull request counts alone do not establish customer value.
Nate B Jones's six principles are to make agent work visibleAI agent observability makes an agent's state, actions, tool use, failures, resource use, and outcomes visible enough to understand and operate it. and reusable across a team, store decisions and history outside individual chatsAI agent memory is stored information that an agent can retrieve and use across steps, sessions, or changing contexts., keep humans accountable for what shipsHuman judgment in AI is the accountable interpretation and decision-making people contribute when setting goals, evaluating evidence, and managing consequences., leave progress and tests in a state another person or agent can resumeAn agent handoff transfers an AI task, relevant context, authority, and responsibility between agents, people, sessions, or environments., give agents ways to check their own workAgent completion verification checks evidence that an agent achieved the requested outcome rather than merely producing intermediate work., and remove process steps that no longer serve a purpose.
Nate B Jones recommends small, practical systems with clear permissions and checks. He distinguishes useful human connection from administrative rituals and argues that teams should measure whether the setup helps them deliver work customers care about, rather than simply generating more code or agent activity.
Watch on YouTube
