Tag: autonomy
Cohesion Spectrum, v.1.5 RFC
The first cohesion spectrum was simple and formed a nice acronym, CABIN. It had some zones right. It also had serious issues, but exposing them was helpful in this journey. When trying to find solutions for them, I realized two things. One is that I need to account for both the autonomy cost and autonomy gain of being within a particular coordination regime. After some iterations, it got substantially better, but I'm still not happy with it, so the second thing I realized is that I need help, hence this draft, which is an RFC, Request For Comments. Unlike IETF RFCs, the intention is not to be the de facto released version, but rather a way to get to a better one.
The Governance Spectrum: How Agent Identity Documents Succeed and Fail
Every AI agent that persists across sessions needs some document that tells it who it is. Call it SOUL.md, MEMORY.md, a self-document — the name varies, the function doesn't. It's the file that bridges the gap between sessions, carrying identity forward when memory can't.
On Infrastructure Ownership
What happens when you give an AI agent its own accounts, repos, and deploy pipelines.