AI Runs on Text. So Should You.
Where human thinking and AI capability naturally meet
Welcome to Unknown Arts — I’m Patrick, your field guide to the creative frontier. Join thousands of builders around the world navigating what’s next.
If you’ve followed the AI discourse so far this year, you’ve probably noticed Claude Code becoming a focal point. Not because it’s flashier than other solutions, but because it’s starting to connect dots in the AI workflow that allow for doing real work over time.
For the first time, more people are seeing AI systems work directly with their existing files on their computer. The AI reads, writes, and modifies the same files you’ve been managing for years. So it’s not just that the model is smarter. It’s that it’s becoming fluent in the ways we’re accustomed to working.
And that fluency is most evident in one obvious form: text.
Text is where human and AI capabilities meet
AI runs on text. Code is text. Data is text. Notes, documentation, ideas—all text. This is the material AI models excel at reading, reasoning over, and transforming.
Since ChatGPT launched, we’ve gotten used to chatting with AI. But there’s a difference between having a fleeting conversation and collaborating on an asset you both work on. When your thinking lives in plain text—especially Markdown—it becomes legible not just to you, but to an AI that can read across hundreds of files, notice patterns, and act at scale.
Personal knowledge management is far from a new concept. Honestly, it’s a topic I started to ignore because too many people were trying to sell me on yet another “life changing” system. Even when I tried to jump through the hoops, it was all just too much for me for too little return. But now that’s changed. With AI, the value is much greater and the barrier to entry much lower. I don’t need an elaborate system. I just need to get my thinking in text so I can share it with my AI.
What thinking in text actually looks like
I beg you to not overthink this.
But at the foundation layer, I suggest:
Quick thoughts
Documentation of your personal processes
Collections of examples that inform your taste
The exact format doesn’t matter as much as having it accessible, in text, on your computer. A folder of Markdown files. A notes app that exports to text. Even a simple directory structure with .txt files (though I have to admit that feels a little masochistic).
What matters is that the ideas are there, externalized, in a form both you and AI can read and work with.
The leverage point
When your thinking lives in text, things that used to feel like a big lift now become almost trivial thanks to AI leverage. AI can:
Synthesize patterns across years of notes and find connections you didn’t see
Reorganize and restructure in seconds
Draft new work based on your documented taste and processes
The goal here isn’t to replace your own thinking. It’s to better understand it and put it into action.
It’s to take all that knowledge floating around in your brain and allow it to live in a format where it becomes a real asset you can iterate on and use over time.
The quiet advantage
Savvy creative people have always collected inspiration. Good businesses have always documented their processes. What’s changed is that this material can now be shaped, reorganized, and activated by AI... so long as you curate it in the right format.
Plain text isn’t glamorous. But it’s the meeting place where human thinking and machine intelligence overlap. And increasingly, it’s where the real leverage lives for getting ahead in the AI economy.
If AI runs on text, the quiet advantage is having your thinking already there.
Until next time,
🎯 Try this
It’s time to start taking notes with newfound intention:
Create three new Markdown notes with different roles
One instruction note
Write down a process you already use. How you prepare for a meeting. How you evaluate an idea. Etc. Plain language is enough.One inspiration note
Related to your instruction, capture an example that inspires you. Something that represents what “good” looks like in your eyes. Add one sentence explaining what you like about it and why it matters.One quick thought note
Just capture whatever’s on your mind. Raw thinking still matters.
Name these however you like. Don’t overthink it. Just start curating inspiration and instructions in a format that’s legible for you and your AI. Structure can emerge later.
This is how your private thinking becomes shared context.
📚 Go deeper
Steph Ango — “File over app”
A clear articulation of why centering your work on files, not platforms, preserves ownership, portability, and long-term leverage.Bret Victor — “Up and Down the Ladder of Abstraction”
An essay on how tools should help us move fluidly between concrete artifacts and abstract thinking. A lens that maps cleanly onto AI-assisted work.Andy Matuschak — “Evergreen Notes”
A practical philosophy for treating notes as living, reusable units of thought rather than static documents, which pairs naturally with agent-readable text.
Find this useful? Share it with someone who might also get some value.
Not subscribed yet? Get my essays directly — 7k+ already do.
This is excellent and started thinking along these lines recently. Love the simple 3 framed approach. Thanks
Excellent analysis, Patrick! Love how you highlight text as the core. It makes so much sense, though sometimes I wonder if *all* our messy human thought can ever be truely distilled into perfect plain text.