An evolving record of things built, explored and thought about.
Now
-
Agentic software systems
Exploring software where agents are first-class operators — not features bolted on.
-
AI-native development
Tightening the loop between intent, agent, verification and deployment.
-
Interactive experiments
Prototypes that turn abstract ideas into things you can touch.
-
Local & edge intelligence
Pushing useful AI onto devices and the edge — asking how little cloud is actually needed.
-
Software infrastructure
The distributed plumbing that keeps experiments fast to run and cheap to operate.
Lab
-
What does software look like when agents, not humans, are its primary users?
-
How much intelligence can run locally, at the edge, before the cloud is needed at all?
-
Can a closed loop of agents build, test and evaluate software better than a human-driven loop?
-
What should a desktop environment be when every session has an agent in it?
-
Do small specialised agents coordinating beat one frontier agent at real engineering work?