Research
Notes on building agentic systems.
What we are learning as we build, written for the people doing the same.
Architecture
An agent should never borrow your keys
Most agents in production authenticate as a person. That one shortcut is where accountability quietly disappears.
7 min read
Memory
The context window is not memory
Stuffing more tokens into a prompt is not the same as building a system that knows things. One is a buffer. The other is infrastructure.
6 min read
Multi-agent
Ants do not hold meetings
The most studied multi-agent systems on earth coordinate without messaging each other at all. They leave marks in a shared environment instead.
8 min read
Evaluation
A benchmark is a snapshot. A track record is evidence.
We hire people on what they have done repeatedly. We deploy agents on what they did once, in a demo. That asymmetry is the whole problem.
7 min read
Operations
The autonomy slider
The question is never whether to keep a human in the loop. It is which loop, on which task, and at what cost.
6 min read
Infrastructure
Run it where you can turn it off
Every serious operator eventually asks the same two questions about their agent stack. Who can switch this off, and can I take my data with me?
7 min read