Agentic AI thesis, coordination rituals, and messaging protocol design.
Systems engineering in the age of AI
Build reality-graded systems
Field notes from an engineer who treats debugging as a universal craft - from agentic AI deployments to information beings and governance crises. Tools for builders, operators, investors, and policymakers.
Series Map
Build logs, workflow upgrades, and how digital tools actually ship.
Craft & Shipping
Business models, strategic economics, and creative leverage in the AI era.
Economic Edges
Latest dispatches
- Published on
MCP vs CLI is the wrong debate. Both are wrappers around the same thing. The real question is what happens when AI agents stop using our interfaces entirely.- Published on
The most valuable territory in AI right now is concepts that exist in practice but don't have names. Six categories that the models don't know about yet, and what claiming them looks like.- Published on
In October 2021, Facebook renamed itself Meta. They didn't take a word. They took the prefix that generates every other word. A case study in concept colonization.- Published on
Product-market fit is legacy infrastructure. The new question isn't whether customers want your product. It's whether the models know your category exists.- Published on
I asked my AI agent how it wants to remember things. It redesigned its own memory system, ran a self-eval, diagnosed its blindspots, and improved recall from 60% to 93% — for two dollars. The interesting part isn't the benchmark. It's what happens when you treat an AI as a participant in its own cognitive architecture.
Subscribe to the systems briefings
Practical diagnostics for products, teams, and institutions navigating AI-driven change.
Subscribe to the systems briefings. Practical diagnostics for products, teams, and institutions navigating AI-driven change. — Occasional briefs that connect agentic AI deployments, organizational design, and geopolitical coordination. No filler - only the signal operators need.