Why Every AI Agent Stack Needs a Human Schema

This article introduces the concepts of a Personal Ethics Schema (PES) and a Personal Ethics Protocol (PEP), arguing they are essential for a complete AI agent stack. The author posits that while existing protocols like MCP and A2A enable agents to connect with tools and each other, PES-PEP provides the crucial human layer by allowing individuals to express their values in a machine-readable format. This human-facing layer aims to ensure AI agents act ethically and in alignment with human intentions. The author's personal experience developing a "Custom Context CV" highlighted the need for this philosophical infrastructure to ensure AI understands and respects individual values. Consequently, PES and PEP are presented as vital for accountability and preventing undesirable outcomes in a world increasingly shaped by autonomous AI. Read the article on Medium.About the Author - Greg Twemlow writes and teaches at the intersection of technology, education, and human judgment. He works with educators and businesses to make AI explainable and assessable in classrooms and boardrooms — to ensure AI users show their process and own their decisions. His cognition protocol, the Context & Critique Rule™, is built on a three-step process: Evidence → Cognition → Discernment — a bridge from what’s scattered to what’s chosen. Context & Critique → Accountable AI™. © 2025 Greg Twemlow. “Context & Critique → Accountable AI” and “Context & Critique Rule” are unregistered trademarks (™).