Latest articles
-
Bounded Autonomy: The Architecture I Had to Build Before AI Agents Could Do Real Work
I run a small team of AI agents that do real work for me. They’re built on Paperclip and Hermes, and they run on self-hosted models in my…
The approach
1. Visibility
Can the agent see the job, and can you see what it did?
2. Accountability
Its own identity, scoped access, a record you can reconstruct.
3. Automation
Gate the irreversible. Approval is a workflow state.
“If you cannot validate, do not automate.”