Designing loops and skills is how you stop re-explaining intent every session and start compounding it. In Knowledge as Code, I argued for the file: institutional memory that survives a tool …
Reliable AI Begins Before the Model
The most reliable AI systems are not built on better prompts alone; they are built on knowledge that has been structured, bounded, tested, traced, and made accountable to human …
Continue Reading about Reliable AI Begins Before the Model →
Knowledge Priming: The Attention Budget
Knowledge as code fails in production when the files exist but the agent still ships the average of the internet. In Knowledge as Code, I argued for the file: institutional memory that …
Continue Reading about Knowledge Priming: The Attention Budget →
Coordination Debt
Organizations accrue coordination debt when AI tools multiply handoffs faster than anyone redesigns who decides what happens next. The familiar complaint sounds like a pace problem. Everyone feels …
Negative Knowledge
Deletion without annotation is the actual failure. Most knowledge systems treat retirement as cleanup; the audit trail of how conclusions changed is a qualification, not clutter. In Knowledge …
Agent Sprawl as an Organizational Risk
Every team can deploy an agent in an afternoon. Almost no organization can tell you how many are running, what systems they touch, or who owns the judgment when they act. In May, the Wall Street …
Continue Reading about Agent Sprawl as an Organizational Risk →