What's inside an AI second brain?

People ask what a second brain is and get philosophy. Here's the answer in parts.

An AI second brain has four layers, and only one is hard: the rules file.

What is an AI second brain made of?

An AI second brain has four layers: the vault, the rules file, the agent, and the connections. The vault is a folder of plain text files on your own machine. The rules file tells the assistant how you work. The agent is an AI that lives inside the folder and can write to it. The connections are the tools it's allowed to read, added last.

Everything else is detail. If you understand those four, you understand the product.

The vault

A folder of plain text files, sitting on your own computer. Notes, decisions, people, processes, meeting records. Obsidian is the usual window onto it. If Obsidian vanished tomorrow, the folder would be fine.

The rules file

One plain-English document at the root of the folder that the assistant reads in full before it does anything at all. Who you are. How your business works. Your customers, spelled correctly. What it may never do. This layer is the entire product.

The agent

An AI that lives inside the folder and can open, write and reorganize files itself, rather than telling you what to type and leaving you to do it. Most setups stop one step before this. A system that can only read is a search box. A system that can write is an assistant.

The connections

Your calendar, your inbox, your task list, your documents. This is the layer everyone wants to start with, and it's the one to add last, one connection at a time, each one read-only first. Starting here is the easiest way for a build to go wrong.

Why plain text files instead of an app?

Plain text is the format that outlives the tools. A markdown file opens in anything, weighs almost nothing, backs itself up the moment it sits in a cloud drive, and doesn't depend on any company's pricing or survival.

There's a second reason that matters more as time passes. Plain text is the format an AI can read end to end. A proprietary database gives you an export button and a schema somebody else designed. A folder of text files gives you the thing itself, and any assistant you point at it can read every word.

That's the whole portability story. If you use one AI today and want to switch to another next year, you point the new one at the same folder and carry on. Nothing gets migrated, because nothing was ever locked up.

What is the rules file, and why is it the whole product?

The rules file is a plain-English document that the assistant reads before every conversation, and it's the difference between a clever demo and a system that's still running in three months. Folder structure is an afternoon of work. The rules file is months of catching an assistant being wrong and writing down why.

It holds the things you'd tell a sharp new colleague in their first two weeks and then never repeat. How you price. Which customers are sensitive. The way you like an email to open. The fact that two people in your contacts have the same first name and confusing them would be embarrassing. What it must always ask about before doing.

Mine started at forty lines and grew to almost nine hundred, each one added because something went wrong once. Then I cut it to about two hundred, one line per rule, and moved the reasons into their own file.

A template gives you the folders. The corrections that make it yours come from using it, which is why every starter vault ships with a guide to writing your own rules.

What does every build come with?

However different two businesses are, some pieces are standard. These are the parts that hold up in a busy week.

• The operating system. The rulebook it follows, written in plain English, in a file you can read and change yourself.
• The ingest lane. A place to drop anything: a document, a photo, a voice memo, a link. It gets read and filed without you filing it.
• The daily note. Where today lives. The plan on top, what happened underneath.
• The log. Everything it did, dated, so you can always see what changed and when.
• Your voice, on your phone. In practice you talk to it far more than you type to it.
• Your spaces, kept apart. Business and personal don't bleed into each other.
• The memory. A directory of the people you deal with, a journal of decisions and the reasoning behind them, and the list of things you've already said no to.
• Backups, twice. A folder of files backs itself up the moment it sits in a cloud drive, and again wherever you keep the second copy.
• The handover kit. A recovery guide, a list of what anyone else can reach, a map of where everything lives, and the setup itself written down.

That last one exists because if only one person understands the system, you don't own it.

What does a second brain run on?

Four things, and you're probably paying for one of them already.

• Obsidian, or any markdown editor. The window onto your folder. Free.
• An AI assistant, on a paid plan. Claude, ChatGPT or Gemini all work. The habits are identical; the tool is whichever one you already use.
• A dictation app, so you can talk to it instead of typing. Writing has never come naturally to me. Talking has.
• A cloud drive, iCloud or Google Drive. This is also your backup, at no extra effort.

Running it costs roughly what a phone plan costs, and every dollar of it goes to companies that aren't mine. There's no software of mine to rent, no server, and no account with anybody new.

Do you need a vector database or a RAG pipeline?

No. For a business of one to twenty people, a vector database solves a problem you don't have. The assistant reads the actual files, the same way you would, and navigates a well-organized folder rather than guessing at fragments of one.

I tried it. Here's why it's not in the system. Embeddings, retrieval pipelines and chunking strategies are serious engineering, and they matter at scale. At your scale they add a layer that can break, that you can't inspect, and that stands between you and your own words.

Five million words, well organized, is enough when the assistant can navigate rather than guess.

How long before any of this is useful?

It does real work on day one, because the first thing that happens is that it reads the documents you already have. It compounds at around the three-month mark, once enough has been written down that it starts answering questions out of your own history rather than out of general knowledge.

At three months you stop explaining yourself. The questions you ask move from "how do I" to "what did we decide about", and only the second kind needs a second brain at all.

Everyone wants to talk about the agent, because it feels like the future. The rules file decides whether you're still using it in three months, because it's the part that makes it yours. If you only have attention for one of the four layers, spend it there.

If you want to see one running before you decide anything, the second brain build page explains what I build, and the longer field note shows a full working day on mine. Or just get in touch.