Software

AI has made software generation so cheap that an entire category is now born disposable — created for a single context, used once, and discarded when the moment passes.

AI engineering has evolved through three compensatory phases (prompt, context, and harness), each addressing a failure the previous layer couldn't fix. Harness Engineering is the governance layer that keeps teams of agents coherent across complex, long-running tasks.

This essay argues that AI is reshaping software at an architectural level, moving from human-centered applications to a composable agentic ecosystem where CLIs, Skills, and MCP form distinct layers that agents invoke as primary users.

Claude Code and CoWork share a codebase but diverge sharply — local vs managed-VM execution shapes resumability, attachability, and autonomy.