Episode Details

What happens when AI agents start writing documentation alongside humans — and the two versions inevitably drift apart? In this episode, we explore the five dimensions of an AI-native knowledge platform: machine-friendly structure, human-friendly editing, provenance and attribution, conflict resolution, and the single shared store. We look at why existing tools like Obsidian, Notion, and Confluence fall short, and what a graph-based system of atomic assertions with authority-weighted version control might look like. The conversation touches on the failures of the semantic web, the rise of agent authorship, and the governance systems needed for shared truth between humans and machines.