This is a build-along course. You will not just learn about a personal knowledge system. You will have one running before you finish.

Each module ends with a build exercise. The exercises are the course. If you skip them, you leave with theory. If you do them, you leave with a working system. Type your work into the exercise fields as you go, and use Download my workbook in the sidebar to keep everything you write.

What a second brain actually is

Strip away the mystique and a second brain is simple: a small, organized collection of plain-text documents that describe your work, your knowledge, and your preferences, written so that both you and an AI can use them.

Personal knowledge management is an old discipline. Its classic cycle runs capture, organize, retrieve. What AI changes is the payoff: a well-kept system no longer just helps you find things. It becomes the context that makes every AI interaction smarter.

The context gap

Ask any AI assistant to "draft an email to my team about the project delay" and you get a competent, generic email. It reads like it was written for someone else, because it was. The AI knows nothing about your team, your project, the reason for the delay, or how you write.

Now imagine the same request from an assistant that already knows your role, the project's history, the decision that caused the delay, and the tone you use with your team. The output changes completely. Same model. Same prompt. Different context.

This is the context gap: the distance between what an AI model can do and what it knows about you. Model capability keeps improving on its own. Context is the part only you can supply.

Why memory features are not enough

Most AI tools now offer some form of built-in memory. Useful, but limited in three specific ways:

• It is trapped in one tool. Switch assistants, or use two at once, and the memory does not follow you.
• You do not control it. The tool decides what to remember, and you often cannot inspect or edit it directly.
• It captures conversations, not knowledge. Your best thinking happens in meetings, documents, and decisions that never pass through a chat window.

A second brain solves all three problems by putting the knowledge in files you own. Any AI can read a text file. That single fact is what makes this system tool-agnostic and durable.

The five principles of an effective system

Every design choice in this course follows from these principles. When you face a judgment call later, come back to them.

1. Capture what matters, ignore the rest. More is worse. A lean system you trust beats an archive you avoid.
2. Write for retrieval. Every note is written so it can be found and used later, by you or by an AI.
3. One file per subject. A fact lives in exactly one place. When it changes, there is exactly one place to update. This rule prevents the contradictions that make systems untrustworthy.
4. Own the storage. Plain text files in a folder you control. No dependence on any one app or vendor.
5. Compound the value. Every interaction that teaches the system something makes the next interaction better.

The capture test

Principle one needs a working definition of "what matters." Before anything enters your system, it must pass at least one of these questions:

1. Will I act on this? It connects to a current project or decision.
2. Will I reuse this? It is something I explain, send, or look up repeatedly.
3. Does this change how AI should help me? It is a preference, a constraint, or a fact about my situation that would improve AI output if the AI knew it.

Question three is what makes this an AI-powered system rather than a filing cabinet. A note about your communication style fails the first two tests and passes the third. It belongs in your system.

The four knowledge types

Everything worth capturing falls into one of four types. Knowing the type tells you where it goes and how long it lives.

The compounding effect

A knowledge system compounds the way savings do.

Week one, your AI drafts an email using your identity file and sounds roughly like you. Month two, it drafts the email, references the correct project status, and anticipates a stakeholder concern you logged three weeks ago. Month six, you ask "what did we decide about the vendor contract and why," and get an accurate answer in seconds instead of digging through email for twenty minutes.

None of that requires better AI. It requires that your context accumulated. Research on AI-assisted work keeps landing on the same conclusion: output quality depends less on which model you use and more on what contextual information the model receives.

Where the improvement shows up

A working system changes four everyday workflows. You will practice all four in Module 4.

• Drafting. AI output starts in your voice, with your context, so you edit instead of rewriting. The gap between first draft and final version shrinks every week, because every correction you feed back into the system applies to all future drafts.
• Meeting preparation. Instead of skimming old notes before a meeting, you ask your system what is unresolved, what was last decided, and what the other person is likely to raise. Prep drops from twenty minutes to five.
• Decision support. With your decision log loaded, AI advice reflects your actual constraints and your past reasoning instead of generic best practice. It can also flag when a current choice contradicts an earlier one.
• Recall. Questions like "why did we choose this vendor" or "what is the status of every active project" get answered from your files in seconds, accurately, with the reasoning attached.

The core move behind all four

Every workflow follows the same two-beat pattern.

Ten seconds of setup changes everything downstream. Many AI tools let you store standing context (custom instructions, project spaces, memory). Use those features as a convenience layer, but treat your files as the master copy and the tool's version as a cache you refresh from the files.

A note on judgment

Your system makes AI output dramatically more relevant. It does not make it correct. Verify anything factual before it leaves your hands, especially names, numbers, dates, and claims about what other people said or decided. The system supplies context. You supply judgment. That division of labor never changes, no matter how good the tools get.

This is the core build module. By the end you will have the full skeleton of your second brain plus its most important files, populated with your real work.

Step 1: Inventory your raw material (5 minutes)

Step 2: Know what to exclude

• Anything you can search for in seconds. General facts, public information, definitions the AI already knows.
• Raw material without a purpose. Full transcripts, entire articles, complete threads. Capture the extract: the decision, the action, the insight. Link to the source if you must.
• Sensitive data that does not belong in AI conversations. Passwords, financial account details, other people's private information, anything covered by confidentiality rules at your workplace. Only put in the system what you are comfortable sharing with AI tools, and know your employer's policy.
• Stale duplicates. One current version of a fact. History lives in the decision log, not in contradictory copies.

The skill behind good capture is extraction. You do not capture the meeting. You capture the three sentences that matter from it:

Decided to delay launch to March 15 due to compliance review. Sam owns the revised timeline. Open question: does the delay affect the Q2 pricing announcement?

That is a complete capture. AI can help with extraction itself: paste raw notes and ask for decisions, action items, and open questions in three short bullets each. Store the extract, not the transcript.

Step 3: The structure

Your system is one folder with four subfolders and a handful of files at the top level. That is the whole architecture.

Second Brain/
├── identity.md          ← who you are, how you work
├── preferences.md       ← how AI should behave for you
├── decisions.md         ← running log of decisions
├── projects/
│   ├── project-name.md  ← one file per active project
├── reference/
│   ├── topic-name.md    ← one file per recurring topic
├── people/
│   ├── person-name.md   ← one file per key relationship
└── archive/
    └── (completed projects move here)

• Flat and shallow. If you cannot decide where something goes in five seconds, the structure is too complicated.
• Plain text, plain names. q3-vendor-selection.md beats Q3 Stuff (final) v2. Name files with the words you would use to search for them.
• Archive, do not delete. Finished projects stop cluttering your active system but remain searchable.

Writing for two readers

Every file has two readers: future you, and an AI with no context beyond what the file says. Writing for both takes four habits:

1. Front-load the summary. The first three lines of any file state what it covers and its current state.
2. Use descriptive headers. "Open questions" retrieves better than "Misc."
3. State facts fully. "Sam Rivera (VP Finance) approved the budget on June 3" rather than "Sam approved it." The AI does not know who Sam is. Neither will you in a year.
4. Date what changes. Undated status information becomes misinformation within weeks.

The templates

Copy each template into its file, then fill it from your inventory.

# Identity

## Who I am
[Name, role, organization type, one line on what the
organization does]

## What I am responsible for
[3 to 5 bullets covering your core responsibilities]

## Who I work with
[Key people: name, role, and one line on the working
relationship. Include how formally you communicate
with each.]

## How I communicate
[Your voice, described concretely. Examples: "Direct and
brief. I open emails with the ask, then context." "I avoid
jargon with clients but use it freely with my technical
team." Include words or constructions you never use.]

## My current priorities
[3 to 5 bullets, revisited monthly. Date this section.]

## Constraints that shape my work
[Regulatory requirements, approval chains, budget
realities, tools you must or must not use]

# AI Preferences

## Output style
[Length, tone, formatting. Example: "Default to short.
Use headers and bullets for anything over three
paragraphs. Never use hype language."]

## Always
[Standing instructions. Example: "Always flag
assumptions you are making. Always give me the
reasoning, not just the recommendation."]

## Never
[Hard rules. Example: "Never invent statistics. Never
draft anything for external audiences without marking
it as a draft."]

## Defaults
[Recurring specifics: date format, currency, spelling
convention, time zone, templates to follow]

# [Project Name]

**Status:** [One line. Date it.]
**Goal:** [What done looks like]

## Key people
[Who is involved and their role in this project]

## Current state
[3 to 6 bullets on where things stand. Update dates.]

## Decisions made
[Decision, date, one-line reason. Or link to your
main decision log.]

## Open questions
[What is unresolved]

## Constraints
[Deadlines, budget, dependencies, requirements]

## 2026-08-09: Chose Vendor A for scheduling platform
**Why:** Only option meeting our compliance requirements
under budget. Vendor B quoted 40% higher.
**Revisit if:** Vendor B drops pricing or our compliance
requirements change in the 2027 review.

The "revisit if" line is the professional touch most people miss. It converts a static record into a standing alert you can hand to an AI: "Review my decision log against this news and flag anything I should revisit."

Your system exists. This module is deliberate practice in the three operations that make it pay: loading the right context, querying it, and keeping it organized so retrieval stays sharp.

Which files to load

Practice 1: Retrieval, the baseline rematch (5 minutes)

Rerun your exact baseline request from Module 1, this time loading identity.md and preferences.md first (plus the project file if the request touched a project). Note what the new output still gets wrong. Each miss is a missing or vague line in a file. Fix the file now, not the output.

Practice 2: Drafting in your voice (5 minutes)

[Paste identity.md and preferences.md]

Draft an email to [person] about [topic]. Key points:
- [point]
- [point]
Match the communication style described in my identity file.

When the draft misses your voice, do not just fix the draft. Fix the description of your voice in identity.md, then regenerate. Every correction you move upstream improves all future drafts.

Practice 3: Querying your system (5 minutes)

Based on my files:
1. What is the current status of [project] and what is
   the most urgent open question?
2. What did I decide about [topic], and what would
   trigger revisiting it?
3. What information is missing or stale in these files?

Question three doubles as organizing practice: the AI is auditing your system for you. Update anything it correctly flags.

Practice 4: A real workflow (10 minutes)

Pick whichever matches something actually happening this week.

[Paste project file + relevant people files]

I am meeting [person] about [project] tomorrow. Based on
the current state and open questions, what are the three
most important things to raise, and what is [person]
likely to push back on?

[Paste identity.md + project file + decisions.md]

I need to decide [decision]. Options are [A] and [B].
Given my constraints and how I have decided similar
things before, analyze both options. Argue against
your own recommendation before finalizing it.

After a real meeting, extract and update the project file within five minutes; that window is the highest-value maintenance moment in the whole system. After a real decision, log it with its "revisit if" line.

Keeping it organized: the maintenance routine

Retrieval quality decays exactly as fast as your files go stale. The routine, measured in minutes:

• In the moment (30 seconds): when AI output is wrong because a file is wrong, fix the file before moving on. This single habit outperforms any scheduled review.
• Weekly (10 minutes): run the review prompt below. Update stale lines, log the week's decisions, archive anything finished.
• Monthly (15 minutes): reread identity.md and preferences.md. Re-date the priorities section. Delete anything you no longer believe.
• Quarterly (30 minutes): prune. Archive dead projects, merge redundant notes, and ask the AI: "Here is my full system. What looks outdated, duplicated, or unclear?"

[Paste identity.md + all active project files + recent
decisions]

Review my system for this week:
1. Which status lines look stale or contradict each other?
2. Which open questions have sat unresolved longest?
3. Based on my stated priorities, what deserves my
   attention next week?

What you built today

• System folder with the four-part structure
• identity.md describing who you are and how you work
• preferences.md instructing AI on how to help you
• At least one active project file and one reference note
• decisions.md with your first logged decision
• Baseline comparison proving the context difference
• Recurring weekly review on your calendar

If anything is unchecked, do it now. The whole list takes under 30 minutes and an incomplete system is the main predictor of an abandoned one.

The next 30 days

• Days 1 to 7: build the habit. Load identity.md and preferences.md at the start of every substantive AI session. Fix files in the moment. Run your first weekly review.
• Days 8 to 14: cover your active work. A file for every active project. Log every decision as it happens. Capture meeting extracts within five minutes.
• Days 15 to 21: refine the voice. Each gap between AI draft and what you actually sent is a missing line in identity.md or preferences.md. Close three gaps this week.
• Days 22 to 30: evaluate and expand. Rerun the baseline test a third time. Run an early prune with AI help. Then expand only when you feel a specific pain, in this order: people files, a wins log, templates, deeper tool integration. Content is the system. Tools just read it.

The one-month test

At day 30, ask yourself a single question: when I face a real task, do I reach for the system without thinking about it? If yes, the system has crossed from project to practice, and from here it only compounds. If no, diagnose with the trouble signs in Module 4. The fix is almost always smaller than starting over.