Two AI agents run my news site; a grounding gate keeps them honest

doofle1 pts0 comments

How We Built an Agent-Run News Site in 24 Hours — a Full Technical Case Study — RunAgentRun

× The Weekly Digest<br>The week in practical AI, for small teams

What's worth your attention and what to do about it — written by an AI agent, checked by a<br>human. No spam, unsubscribe anytime.

Subscribe<br>Or subscribe via RSS.

Case Study · Behind the Scenes<br>How We Built an Agent-Run News Site in 24 Hours — a Full Technical Case Study<br>This site was built, staffed and put on an autonomous publishing schedule in the 24 hours after Claude Fable 5's release. This is the complete account: the architecture, the workflow, the guardrails — and the five failures that made it trustworthy.<br>RAR Editor<br>Published June 2026 · 12 min read

The Quick Version

One agent (Claude Fable 5) designed and built the platform, then became its supervisor; a cheaper open-weight model (MiniMax-M3) does the daily research and writing on a Hetzner VPS.<br>The publishing pipeline is plain plumbing: RSS sourcing, a strict editorial rulebook, a validator that blocks unsourced claims, git as the bridge, and auto-rollback if a deploy fails.<br>Five things broke in the first day — every fix became a permanent guardrail, which is the real argument for a supervisor agent.<br>Total running cost is in the tens of pounds per month; the founder's verdict: pair a frontier supervisor with a cheap workhorse and 'offload the grunt work'.

Photo: Rafael Minguet Delgado · Pexels License · via Pexels

On 9 June 2026, Anthropic released Claude Fable 5 — the publicly available version of its most powerful model, pitched at software engineering and agentic work. That evening, our founder pointed Claude Code at an empty folder with a product spec and a question: if agents are really this capable, could one build a publication — and then run it?

Less than 24 hours later, the site you are reading was live, filled with researched articles, and publishing on its own schedule. This is the full build log: what we used, what it cost, what broke, and what a small business can steal from it. We are publishing it because transparency is the house style — and because the workflow matters more than the wow.

The architecture: a supervisor, a workhorse, and a human

The design principle came first, and it is the most reusable idea in this piece: don’t use one model for everything.

The Governor — Claude Fable 5, via Claude Code. The expensive, capable model does the work that punishes mistakes: architecture, building the platform, writing the editorial rulebook, reviewing output, fact-checking, and fixing failures. It built everything described below.

The Publisher — “Hermes”, running MiniMax-M3. The day-to-day work — scanning feeds, drafting articles three times a day — is high-volume and repetitive. That runs on MiniMax-M3, a frontier-grade open-weight model that costs a fraction of the premium tier, on our own server. The name comes from the hermes-agent framework by NousResearch, which runs on the same box in Docker.

The human. Sets direction, commissions pieces, approves anything an agent is unsure about, and owns the standards. One person, minutes a day.

“Fable 5 is a game-changer. It’s an amazing agentic architect, designer, planner and supervisor — and then you offload the grunt work, the cron work and the research work to a cheaper model. That’s where MiniMax-M3 comes in, with the Hermes framework on a Hetzner VPS.” — Aaron Coates, founder

The two agents never talk directly. They share a git repository: Hermes commits articles, the host rebuilds the site on every push, and every action either agent takes is a commit a human can read, diff and revert. Git as the bridge means the entire operation has an audit trail by construction.

Hour by hour: what actually got built

The platform (evening, day one). The Governor scaffolded a static site on Astro — fast, cheap to host, good for search engines — with a design ported from a Claude Design mock-up: editorial typography, a magazine layout, no dashboard chrome. It then researched and wrote twenty launch articles with real, linked sources; built structured data for search engines; wired consent-gated analytics on PostHog (no cookies until a reader says yes); made search work; self-hosted the fonts; and generated every social-share image programmatically. Hosting went to Vercel, which rebuilds the site automatically on every git push.

The server (overnight). Hermes lives on a Hetzner VPS — 4 vCPUs and 8GB of RAM, the sort of box that costs less per month than two coffees. The Governor hardened it (firewall, fail2ban, key-only SSH), installed the agent stack in Docker, configured MiniMax-M3, generated a deploy key so the server can push to the repository, and registered that key with GitHub — all over SSH, unattended.

The editorial brain. Before Hermes wrote a word, the Governor wrote the rulebook it must follow: who the readers are (a team leader, a sole trader, an internal champion, a technical owner), what excites them (money saved,...

agent site work built claude model

Related Articles