Four C’s of an AI Operating System

The sequential framework Nate Herk uses to build and teach a personal AI Operating System (AIOS) in Claude Code. The four layers are Context, Connections, Capabilities, and Cadence — and they must be built in order.

Key points

  • Context — what the AI knows about you, your business, your goals, and your constraints. Captured in CLAUDE.md, context files, and the onboarding interview [src-013]
  • Connections — what data sources the AIOS can reach: calendar, email, task manager, meetings, revenue dashboards. Wired via APIs or MCPs [src-013]
  • Capabilities — what the AIOS can produce: skills (reusable markdown SOPs), reference files, and task-specific sub-agents [src-013]
  • Cadence — when it acts autonomously: cloud routines, /loop cron jobs, and daily planning habits [src-013]

The order is non-negotiable: “You can’t have cadence without connections. You can’t have capability without context” [src-013].

Related entities

Related concepts

Source references

  • [src-013] Nate Herk — “Build & Sell Claude Code Operating Systems (2+ Hour Course)” (2026-05-01)