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 visible and reusable across a team, store decisions and history outside individual chats, keep humans accountable for what ships, leave progress and tests in a state another person or agent can resume, give agents ways to check their own 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
