Darkhouse Enterprises · Papers
Papers
A series of seven papers on running AI agents safely, written to be read in order. Each one also stands on its own.
- 01
A Year in the Life of AI
What a year of building with agents taught us and what happens when there are a thousand of them.
- 02
Agents: Handling Deputies, Directories & Encodings
Why the tool protocol everyone is connecting cannot be the thing that keeps a secret.
- 03
The Engineering Authority
A function, run by a small team, that owns the route to live for agents and stops your many suppliers wasting your money and your data.
- 04
The Airlock
How to build an estate where nobody holds the keys and all work arrives as a sealed task.
- 05
Estate, Feeds, Deployment
Once you are in that shape, patching becomes routine: know what runs, read the feeds and ship the fix through the one way in.
- 06
The Small Model
A model the organisation trained, on its own estate, that notices an event, flags the right response and never decides.
- 07
The Life Raft
Where to build: start with recovery and move the organisation across one service at a time.