Today we explore agentic pipelines, loops and recursive self improvement (RSI) via our old friends, PMP Questions. This is article 4 in my AI agents series. Start here for an introduction, see here for an explanation of what constitutes a real agent, and here for a discussion of how I use them and running AI locally. This article gets into how to plan and manage agent work; that’s what “agent orchestration” means. As a project manager, I suspect you already have the thinking skills required. You already know why one person can’t do everything on a project. You staff a project with specialists, engage each of them in the correct piece of scope, and put reviews between the stages that

This is the third article in the “Leading A Team that’s Part Machine” series. You can read the introduction here and the second article about what constitutes a true agent here. In this article, I will cover the work I assigned to my agents, their costs and my decision to explore local AI. Work-wise, my goals for a team of agents fell into two categories: The first was personal, the second commercial. Personal: Learn about AI by spinning up my own team of agents, doing real work and seeing how it impacts project management Managing my to-do items across my full-time job, side projects and writing calendar Task automation to reduce the time I spend on admin and other repetitive