AI Architecture

The Agentic
Operating System

One person. Four agents. Fourteen sites.

A framework for running a business through AI agents. Not a product. Not a platform. An operating philosophy — tested daily across 14 websites, 4 agents, and 4 years of production operations.

4 AI Agents
14 Sites Managed
300+ Sub-Agents Daily
2022 Daily Operations Since
See It Run

One command, decomposed
into a company.

A single instruction enters a digital-twin workspace built on Andrej Karpathy's LLM-wiki idea — every agent's role, workflow, and operational context written down before any work begins. The system reads the wiki, decomposes the command into specialized skills, and hands each output down the chain until the job is done. Codex runs as the default execution engine; OpenClaw and Hermes are reached through a bridge when they fit the task better. Nothing sensitive ships without a human approval.

Narrated by Saarvis, HH, Nyx, and MiniDoge — the council behind the AOS.

What Is This

Not a tool you use.
A team you manage.

An Agentic Operating System (AOS) is what happens when you stop thinking about AI as a tool you use and start thinking about it as a team you manage. Instead of opening ChatGPT when you need something, you build agents that run continuously — monitoring, analyzing, generating, and acting on your behalf.

Peter Saddington has been running an AOS since 2022. Four specialized AI agents manage his 14-website empire: generating content, monitoring security, analyzing business metrics, and coordinating operations. The human reviews, approves, and steers. The agents execute.

This isn't theoretical. It runs every day. It breaks. It gets fixed. It learns. That's the point.

The Architecture

Three layers. One loop.

Layer 1

Specialized Agents

Each agent has a defined role, its own data sources, and its own execution pipeline. No agent tries to do everything. Specialization creates reliability.

Operations

Halperbot

Runs the daily standup, coordinates cross-site health checks, monitors pipeline failures, tracks operational metrics. First to wake up. Last to report.

Intelligence

Saarvis

Watches external signals, tracks ecosystem changes, surfaces strategic context. The agent that sees what Peter doesn't have time to watch.

Business

MiniDoge

Analyzes growth metrics, engagement data, business performance. Distills complexity into decisions.

Security

Nyx

Monitors SSL, deployment integrity, vulnerability signals, anomalies. Runs the night shift.

Layer 2

Coordination Protocol

Agents don't operate in isolation. They coordinate through a structured communication layer.

6:00 AM ET

Morning Council

All agents report to a shared Discord. Each posts a structured briefing in its own channel.

8:00 AM ET

Human Review

Peter reads the reports, approves or rejects proposals, flags issues. No consequential action happens without human approval.

All Day

Continuous Operations

Throughout the day, automated pipelines generate pages, update content, run predictions, and maintain infrastructure.

Layer 3

Infrastructure

The technical substrate that makes the AOS possible.

Compute

GitHub Actions

Every agent runs as a scheduled GitHub Actions workflow. Reproducible, auditable, version-controlled.

Hosting

Cloudflare Pages

14 static sites deployed via Wrangler CLI. No servers to manage. Global CDN by default.

Memory

Supabase

Structured data, vector embeddings (RAG), cross-agent memory. The shared brain.

Interface

Discord

The human-agent interface. Reports arrive. Decisions flow back. Everything is logged and searchable.

Design Principles

Five rules the system
never breaks.

1

Human-in-the-Loop, Always

Agents propose. Humans approve. No agent pushes code, publishes content, or makes financial decisions without explicit human sign-off. Autonomy is earned through demonstrated reliability, not assumed. Peter reviews every morning. That's the loop.

2

Specialize, Don't Generalize

A single "super agent" that does everything is fragile, hard to debug, and impossible to trust. Four agents with clear boundaries are reliable, testable, and replaceable. If Nyx breaks, the other three keep running. If MiniDoge produces bad analysis, it doesn't affect Halperbot's operations report.

3

Fail Loudly

Every pipeline failure sends an alert. Every error is logged. The AOS doesn't hide problems — it surfaces them immediately. The worst thing an operating system can do is fail silently. Peter knows within minutes if something breaks.

4

Ship Daily

The AOS generates content every day. Venue sites produce 50+ pages daily. Briefing pages publish every morning. The prediction engine runs daily. The cadence is the discipline. If the system can't ship daily, it's broken.

5

Learn in Public

Everything is documented. Agent architectures, pipeline designs, failure post-mortems — all visible. The dogelord.com site publishes the agents' daily output. Transparency is the accountability mechanism.

In Production

What the AOS manages.

14 sites run under the AOS every day. The flagships:

staas.fund VC fund, the AI Workshop & Builder's Table, pRAG chatbot, hundreds of video and authority pages
dogelord.com Council of Dogelord, The Arena AI debates, daily agent briefings
raceteam.wiki 1.12M+ team pages — the world's largest free racing wiki
racingnear.me Racing, karting & sim venues across the US, daily page generation
gtglobalchamp.com GT Global Championship series & Paddock Society membership
saddingtonracing.com Racing team and events
thenabme.org Motorsports community

One person. Four agents. Fourteen sites. This is what the AOS makes possible.

The Thesis

The AI-augmented
solopreneur.

A single person with AI agents can operate at the scale of a 20-person company. Not by replacing humans with AI, but by automating the repetitive infrastructure work that drains creative energy. The human focuses on strategy, relationships, and creative decisions. The agents handle monitoring, generation, maintenance, and analysis.

Peter calls this the AI-augmented solopreneur model. It's not a lifestyle business. It's not a solo founder struggling to do everything. It's one person with an operating system that scales.

The AOS isn't software you can download. It's a set of principles, patterns, and hard-won lessons from 4 years of building. The Builder's Table teaches the technical skills. The AI Experiments page shows the results. And this page describes the philosophy that ties it all together.

Go Deeper

The rabbit hole continues.

Your Turn

Build your own AOS.

Everything in the demo — the agents, the pipelines, the approval loop — is built from skills taught at the Builder's Table: a 3-hour live workshop where you ship your first agent, your first app, and your first dashboard.

About the Agentic Operating System

The Agentic Operating System (AOS) is Peter Saddington's framework for running businesses through autonomous AI agents. Peter operates 4 production agents — Halper (task execution), Saarvis (network intelligence), MiniDoge (market analysis), and Nyx (security) — that collectively manage 14+ websites, a venture fund (StaaS Fund, RegD 506B), and daily operations with zero employees. The system runs on GitHub Actions, Supabase, and Discord, spawning 300+ sub-agents daily. Peter has trained 17,000+ professionals in agile and AI, holds 3 Master's degrees including Computer Science from Georgia Tech, and bought Bitcoin at $2.52 in 2011. The AOS concept is taught at Peter's live Builder's Table workshop (staas.fund/workshop) and through the free AI Workshop tools at staas.fund, used by Fortune 500 teams.