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]
  • In the Opus 4.8 AIOS walkthrough, Nate applies the same four layers to his real second-brain operating system: business/project context, connections to recurring work surfaces, skills and templates as capabilities, and scheduled routines or usage habits as cadence [src-087].
  • The framework now functions as both a build sequence and a diagnostic checklist: if an AIOS feels weak, ask whether it lacks context, useful connections, reusable capabilities, or an actual cadence of use [src-087].

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

Related entities

  • Claude Code — the primary harness for building an AIOS
  • Nate Herk — coined this framework

Related concepts

Source references

  • [src-013] Nate Herk — "Build & Sell Claude Code Operating Systems (2+ Hour Course)" (2026-05-01)
  • [src-087] Nate Herk — "I Turned Claude Opus 4.8 Into My Entire AI Operating System" (2026-05-29)

Robin Cartier perspective

This page is part of Robin Cartier's working AI knowledge graph: a practical research layer for production AI, recommendation systems, experimentation, GEO, and agentic web readiness.

The useful next step is to connect this concept back to applied product leadership and operating models.

Recommended next

Keep reading from this thread

From 500 indexed pages and articles.

  1. Wiki concept AIOS Tier-One Domains The seven core business data domains that should be connected to an AI Operating System. Connecting all seven gives the AIOS enough context Related by aios
  2. Wiki concept AIOS Daily Loop A daily operating cadence for getting value from an AI Operating System while continuously improving it. Related by aios
  3. Wiki concept Three M’s of AI Three M's of AI Nate Herk's philosophical framework for adopting AI productively — Mindset, Method, and Machine — presented as the prerequisite to building a technical Related by aios