Why Traditional Frameworks Hide Too Much for AI Agents
Convention over configuration breaks down when the consumer is not human. Decorators, middleware chains, and implicit routing create blind spots that AI agents cannot navigate.
Read moreBlog
Thoughts on AI-native development, machine-readable architecture, and building systems that AI agents can safely operate.
What Machine-Readable Architecture Actually Means
Machine-readable does not mean "has an API" or "uses JSON." It means the system's architecture is a formal, queryable artifact that tools and agents can traverse.
Read more
Why Invariants Should Be First-Class Citizens
Business rules scattered across middleware, services, and database constraints are invisible to AI agents. Making invariants named, described, and bound to entities changes everything.
Read more
Safe Edit Zones: Teaching AI Agents Where They Can and Cannot Write
AI agents will modify any file you let them. Safe edit zones create explicit file ownership boundaries that prevent accidental damage without blocking productive work.
Read more
Capability-First System Design
Instead of starting with routes or controllers, start with capabilities: named operations with typed inputs/outputs, entity bindings, policy gates, and invariant checks.
Read more