Independent research grounded in real, instrumented production systems. Every figure is measured; every paper is explicit about its limits. Working papers, not peer-reviewed — the honesty is the point.
How autonomous production collapses while verification, observability, and trust do not.
The flagship thesis: AI collapses the cost of production but not of verification, observability, or trust — and those, in an Amdahl-law sense, bound how far it scales. Then the architecture that bends them. Grounded in a 52-million-record natural experiment.
Can an AI-operating system observe itself?
The ceiling on autonomous operation is not the agent's intelligence but whether the system can answer questions about itself. A defect taxonomy, a field study, and a family of failures root-caused to a system scanning its own substrate.
North-star adjudication for multi-agent systems.
How to guarantee a swarm of agents actually finished the job when the agents grade their own homework. Reify work as a durable packet; adjudicate completion against evidence, not self-declaration.
An economic and trust architecture for multi-tenant AI.
Why a platform that never buys a token — and never proxies a customer's key — is a stronger trust and safety design. Decoupling payment, custody, and provenance.
A mathematical framework for AI decision routing.
Six borrowed formalisms as one control vocabulary — audited self-critically into two load-bearing 'engines' and four design 'compasses'. Rigor through honesty about what's proven versus proposed.
Architecture, scale, and the discipline that kept it maintainable.
What one engineer working with AI agents actually built — and the discipline (turned into automated gates) that drove the fix-to-feature ratio from 2.1:1 to 0.88:1 while doing it.