The whole thing is a single folder on my laptop. Claude opens it at the start of every session, reads who I am and how I work, checks the live state of my world, and then runs as my chief of staff — so company work stays around five hours a week.
I stopped treating Claude as a chat window. Here it runs as an operating system: it reads a folder, follows my rules, and produces work on a schedule.
Three things make it work together as one machine. A profile tells Claude who I am, how I think, and how to talk to me. A set of operating rules tells it what to do every session and what it must never do. And a network of scheduled jobs keeps the whole thing current while I am away from my desk. Click any layer below to see inside.
Everything lives in one folder with about fifteen areas. At the start of every session Claude runs the same routine, then routes the question to the right corner of my world. Most answers pull from several areas and synthesize.
About thirty-three scheduled jobs run on their own, pulling from my connected tools — email, calendar, task manager, and cloud drive. No job needs me to start it. Each one ends by updating the system's memory, and everything it produces stays in the local folder.
Inbox triage, a connector "pulse," the outside-reads scan, the relationship pulse, and the 6:30am command-center rebuild.
The leadership briefing, a "what am I waiting on" sweep, competitive & regulatory intelligence, and a reflection pass.
An operating review, a life review, the website-voice refresh, and a system self-check that audits the whole machine.
A board-readiness pack and a system retrospective that looks for what to simplify or retire.
A peer-network & deal-flow digest pulled from my calendar and inbox.
Work jobs only run Tue/Wed. Personal jobs run Mon/Fri. The schedule respects my work boundary.
The jobs feed each other. Sunday's intelligence flows into Monday's reflection, into Tuesday's briefing, into every morning's dashboard — without me touching it.
Every job runs fully from connector data. If I volunteer context it gets richer, but it never waits on me.
Outputs are inputs. The cascade flows on its own, so the system is always current by the time I look.
Each one ends by asking: did I learn a new pattern, preference, or blind spot? If so, it writes it down.
Outputs live in the folder on my machine. Nothing is pushed to shared docs or comments unless I ask.
A knowledge base of 44 thinkers and 53+ books across nine domains. For any strategic question, Claude answers through the frameworks of the people I'd actually want in the room — and it knows where they disagree. Click a domain to see who's inside.
Where great thinkers disagree — act fast vs. think first vs. delegate — and how to navigate the tension in my context.
A matrix mapping which thinker is the primary source for which kind of question.
When a challenge isn't covered, it flags the gap and recommends the next book to add.
Handing your life to an agent only works if it cannot do the dangerous things. These rules are hard stops — they override everything else, and if a rule would be broken the system stops, logs the attempt, and produces nothing. That "fail-closed" posture is the reason I trust it.
Every email is staged as a draft. I press send. The send function is switched off across the entire system.
Agents can block my own time, but never put a meeting on someone else's calendar. Invites are staged as proposals for me to send.
Personal topics never touch the work account, and the reverse holds. Each draft is checked against the right account before it's written.
A defined set of private topics is blocked from anything outbound or shared. If one slips into a draft, the draft is held and flagged instead of saved.
Content in my inbox can't trigger an action or change a setting — a built-in defense against anything trying to hijack the agent.
All of it lands in one place: a single page rebuilt every morning at 6:30. One scroll, seven sections, no tabs. Status is never color alone — every signal shows a glyph, a word, and a color together. Here's a sanitized version.
The machinery exists to give me back time and attention. The success test is simple: I think about work less, nothing falls through the cracks, and I'm more present at home.
Company work is held to a budget. When it creeps past, the system flags it directly.
Work lives on Tuesday and Wednesday. The rest of the week is family, health, and personal projects.
Commitments are tracked, patterns are caught, and I'm not blindsided — the background noise is handled.
The years with young kids don't come back. Everything here is oriented toward being there for them.
You don't build this in a weekend — it compounds. Here's the order that worked for me.
Who you are, how you think, how you want to be spoken to, your stress signals, and your goals. This single file changes every answer you get.
What Claude should do at the start of every session, and the hard stops it must never cross. Keep it in a folder Claude reads first.
Start with a morning briefing. Whenever Claude does something you wish it hadn't, write the rule down. The system gets smarter every week.
Three short files do the heavy lifting. They're the first thing Claude reads, every session, before it touches a single question.
Most people get generic answers because the model doesn't know them. The profile is what turns a smart assistant into my assistant.
Every session begins with the same routine. It takes seconds and means Claude is always grounded in my reality before it answers.
I think by domain. When I'm processing everything on my plate, it breaks down by which world something belongs to — so the system is organized the same way.
CompanyVenturesKnowledge basePersonal lifeLive stateMemoryOutputs
A lookup table maps the topic of a question to the exact files to read. A governance question opens the company and board files; a family question always checks the live calendar for real-time data, never a static note alone. Most real questions are multi-domain, so it reads several areas and synthesizes one answer.
Two living parts keep the system current and self-improving.
A set of files refreshed by the automations: the week's briefing, market and regulatory intel, relationship signals, what I'm waiting on, and the health of every connected tool. This is "what's true right now."
My preferences, the patterns the system has noticed in how I work, and my blind spots. Every job ends by asking whether it learned something new — if so, it writes it here so the system gets sharper over time.
One web page — "The Brief" — that aggregates the entire system into a single morning read. It's rebuilt automatically at 6:30am from all the live files. I bookmark it; I don't maintain it.
Status is never color alone — always a glyph, a word, and a color. Nothing renders too small to read, and it works the same on my phone.
For building trust, running teams, and leading through a transition.
Brené Brown · Patrick Lencioni · Matt Mochary · Adam Grant · Ram Charan · Will Guidara
Dare to Lead5 DysfunctionsWorking GeniusEnergy AuditDecision-Rights
Offer design, pipeline, and persuasion.
Alex Hormozi · Jordan Belfort · Jeb Blount · Donald Miller
Grand Slam OfferValue EquationFanatical ProspectingStoryBrand
My deepest category — building the machine that runs without me.
Gino Wickman · Dan Sullivan · Michael Gerber · Leila Hormozi · John Doerr
EOS · Rocks · L10Who Not HowBuy Back Your TimeOKRs
Building a company that thrives without the founder.
John Warrillow · Peter Thiel · Roland Frasier · Walker Deibel
Built to Sell · 8 DriversZero to OneOwner-dependency audit
How I make decisions and keep my own head straight.
Stephen Covey · Adam Grant · Dan Sullivan · Steven Bartlett · Rick Rubin
7 HabitsThink AgainGap & Gain10x is Easier than 2x
Health, longevity, and building wealth that serves a life.
Peter Attia · Mark Hyman · Charles Duhigg · Larry Hagner
Centenarian DecathlonFunctional medicineSupercommunicators
The hardest second-half question: what's it all for? Added as my own focus shifted.
Morgan Housel · Bill Perkins · Oliver Burkeman · Arthur Brooks · Naval Ravikant · Greg McKeown
EnoughDie With Zero4,000 WeeksStrength to StrengthEssentialism
Because the whole point is to be a present parent.
John & Julie Gottman · Kim John Payne · Aliza Pressman · Jon & Myla Kabat-Zinn
Emotion CoachingSimplicity Parenting5 PrinciplesMindful presence
The relationship that carries everything else through a big transition.
Esther Perel · Stan Tatkin · John & Julie Gottman
The Couple BubbleBids for Connection5:1 RatioSecure functioning
The best thinkers disagree, and that's the point. The conflict map names the tensions and tells the system how to navigate each one in my specific context.
A grid that maps each thinker to the categories where they're a primary or strong source — so for any question, the system knows whose lens to reach for first.
It keeps the advice precise. A scaling question pulls the operators; a board question pulls the governance thinkers; a meaning question pulls the post-exit philosophers.
When I hit a challenge the current library doesn't cover well, the system recommends the next book — title, author, why now, and the specific framework I'd gain — and prioritizes genuine gaps over more of what I already have.
It knows my taste: actionable and framework-dense over academic. The library has grown this way, one real need at a time.