§ 03 — Dispatch003
Index Four clusters

Dispatches

Field notes from a one-operator network: AI-native local journalism, agent orchestration, getting found in AI search, and solo-operator engineering.

Solo-operator engineering AI Needs Its ISP Moment I founded Western North Carolina's first ISP in 1995 and watched the internet get real one phone call at a time. AI is stuck where the internet was in 1994 — it needs the same local layer to reach the rest of the country. 5 MIN Solo-operator engineering What does 30 years of building the web teach you about the AI moment? I've worked through every platform shift since dial-up bulletin boards. The pattern underneath this one is the same — and the people who miss it always miss it the same way. 5 MIN Getting found in AI search (AEO/GEO) Is SEO dead now that AI answers questions directly? No — but the job changed from ranking on a results page to being the source an answer engine quotes. Here's what actually transfers. 4 MIN Getting found in AI search (AEO/GEO) How do you get your business mentioned by ChatGPT? There's no submission form and no paid placement. There is a repeatable set of moves that make you retrievable — here they are, in priority order. 5 MIN AI-native local journalism Can AI run a local newspaper without producing slop? Yes — if you build the guardrails before you build the pipeline. The anti-slop framework behind a 17-paper network, from someone who runs one. 5 MIN Agent orchestration & harnesses Why does every AI agent need a human approval gate? Because an agent that can act without a checkpoint will eventually act wrongly at machine speed. Plan-gating is the cheapest insurance in AI. 4 MIN Getting found in AI search (AEO/GEO) What is llms.txt, and should your website have one? A plain-markdown map of your site for AI systems — cheap to ship, zero downside, and one honest caveat about who reads it today. 4 MIN AI-native local journalism What would it take to launch a newspaper in every state capital in 24 hours? One command, about a hundred papers, live in a day. It's a real capability of the platform I run — and the interesting part is what it deliberately doesn't automate. 4 MIN Agent orchestration & harnesses How do you run multiple AI models in one pipeline without losing control? Assign models jobs, not vibes: planner and reviewer at the top, executors underneath, checks between every handoff. The org-chart approach to multi-model systems. 5 MIN Solo-operator engineering How does one person run platform-scale infrastructure? Seventeen newspapers, a SaaS platform, an agency, and a toolchain — one operator. The stack decisions and operating rules that make it hold. 5 MIN Getting found in AI search (AEO/GEO) How do you make Google and the AI models agree on who you are? This site is the demo: one canonical Person ID, schema on every page, a machine layer for the crawlers, and the same bio everywhere. The build, documented. 5 MIN AI-native local journalism 17 papers, two months, one operator — what the NewsroomAIOS beta proved The beta network ran 17 AI-powered papers across 16 US markets for two months. The A/B test is complete, the platform is finalized, and the network launches September 1. 6 MIN