The Autonomy Ladder
ai8 min read
Google's A2A protocol and MCP are live under shared governance. The protocol layer is solved. The trust layer that determines whether agents can actually discover and rely on each other is not.
#systems
7 posts
Queryable Thinking
ai8 min read
What happens when your writing becomes a callable knowledge service and the reader becomes a synthesiser.
Inside the Memory Layer
ai5 min read
How I built a persistent AI memory layer — MCP server, control panel, embeddings, and a query UI that turns conversation history into usable knowledge.
The memory layer is the moat
ai4 min read
I built a persistent memory layer that sits outside any single AI provider. Now every tool I use shares the same context, and it turns out the memory matters more than the model.
Prompting Is Not the Moat
ai5 min read
Prompt engineering courses are booming, but the skill they teach is depreciating fast. The durable value in AI sits above the interface.
The Alignment Problem Is a Human Problem
ai6 min read
AI alignment research assumes humans can specify what they want. Behavioural science says otherwise.
What OpenClaw Actually Proved
ai5 min read
Jensen Huang ranked OpenClaw alongside Linux. The real lesson is that users wanted AI with tool access and execution rights, and the industry spent three years optimising for the wrong thing.