Content Hub OS: Lab Notes - 04.11.26
In this Note: How CHOS handles newsletters across four visibility types. The three fields that make newsletter output different from every other content type.
The Automator's Log documents Content Hub OS as I use it — what's inside, how it works, and what I've learned running it on my own brand before opening it to anyone else. If you're new here, CHOS is an AI-powered content operating system built for operators who are done doing everything manually. These notes are the inside look.
The Newsletter Workflow
Newsletters are the most flexible content type in CHOS. That flexibility required the most specific form.
Fill out the basics. Brand, title, intended audience, content goal, content style, newsletter type for platform context. Then the three fields that make this different from every other content type in the system.
Visibility. Client/Internal for branded or internal updates. Private for company lists or private communities. Public for LinkedIn, Substack, Beehiiv, and similar platforms. The AI uses this to calibrate tone before it writes a single word.
Key Points. The specific points the newsletter must cover. Not suggestions. Required coverage.
Newsletter Angle. The lens. Contrarian. Data driven. Personal story. Inspirational. The more specific the input here the less editing on the back end. This is the most powerful field in the entire system when used well.
Paste your source content or write from scratch in the notes field. Select your prompt, choose your AI model, hit Add.
The outputs are the newsletter itself and an image if you need one. That’s intentional. A newsletter is a publishing format not a promotional asset. It doesn’t feed into social posts or emails. It stands on its own.
The hardest part of building this workflow wasn’t the automation. It was the prompts. A Substack issue reads differently than a LinkedIn newsletter reads differently than a client update reads differently than an internal brief. Four contexts. Four tones. Four style guides baked into the prompt architecture so the AI doesn’t flatten them into the same generic voice.
The automation was straightforward. Teaching the system to write like the platform it’s writing for was the real work.
✌️ Audra
If you're still fighting the slop and want to see how this runs inside a real system, I'm documenting the full CHOS build here as I go. Follow along or come try it yourself at contenthubos.com.