Ryan Merlin

Gartner says agentic AI puts $234 billion of enterprise application spending at risk by 2030.

Skills marketplaces are becoming the first visible exchanges for a new scarce resource: not human notice, but admission to the trusted decision-and-action loops of AI agents.

Generation is becoming cheap.

A vault protects storage, not trust.

If both human and machine are thin, biased minds whose errors correlate by construction, the value was never oversight but composition: arranging correctors that go dark in different places so the same mistake isn't broadcast twice.

The engine behind today's AI and the leading theory of consciousness break at the same undescribed part, the workspace, which is evidence of shared constraints, not shared experience.

Working memory suggests the conscious self isn't the whole mind but a small, constrained access layer: the narrow beam where a few selected states become reportable and usable.

The missing skill in AI-built software isn't syntax.

Getting better at agents is not watching less.

MCP's ratified 2026-07-28 spec removes sessions from the protocol.

A five-layer setup for running long-lived agent sessions you can reach from your phone: persistent Zellij sessions under systemd, a self-healing Claude Code launcher, Remote Control, zellij web, and a tunnel with the WebSocket gotcha that bites everyone.

MCP is how agent capabilities travel.

Consciousness is not usually the first mover in moment-to-moment choice.

DORA says the AI productivity dip lasts three months.

MCP won.

2026 is the year the agent protocol stack started to look real.

The .env file is a collaboration tool for human engineers.

Enterprise AI projects don't fail because organizations lack information.

Every agent platform shipping today treats a model call as a request: short-lived, stateless, RPC.

Multi-agent systems don't fail because the agents are stupid.

Several persistent Claude Code sessions, scoped to different domains, coordinating through EdgePlane.

Every serious attempt to build a multi-agent system converges on the same shape.