How It Works

A consolidated, daily-updated brain for the whole family balance sheet — the public-market accounts, the boat dealership, and the real estate, all in one place. It runs on four kinds of input, each listed in full in the Data Sources section below: a curated roster of macro and sector experts whose new interviews and two paid letters are ingested every morning; live market and economic data refreshed daily (prices, fundamentals and analyst estimates from Financial Modeling Prep; macro series from the Federal Reserve's FRED; Bitcoin on-chain feeds), with prices going live on the page; a daily event layer (news on every holding, the US economic calendar, marine-industry headlines); and the family's own books, syncing on different clocks — the brokerage every morning, the asset roll-up whenever it changes, the dealership statements as they are filed. The experts' views are distilled into a single Living Thesis with explicit probabilities, and that one worldview is applied across every asset: which stocks screen well, where the dealership's next dollar earns most, whether a property's return beats the alternatives. The division of labor is the same everywhere — the experts and the data shape the view, the numbers do the ranking and the math, and the family makes the decisions. Every figure is checked against the live number rather than a stale quote or memory, and the system builds the case rather than making the call.

We track 22 YouTube channels, 15 named guest voices, two paid newsletters, and individual research voices on X. The channels split into tier 1 (core macro and sector voices, fully transcribed every run) and tier 2 (high-volume channels like Bloomberg Technology and a16z that are keyword-filtered so we only ingest the clips that touch our themes). Guest voices (Lyn Alden, Gromen, Bianco, Visser, Gundlach, Druckenmiller, Lacy Hunt, Raoul Pal and others) are caught by name whenever they appear on any tracked show. The two paid newsletters (Lyn Alden premium and Northstar & Badcharts) are pulled from email and read in full through an authenticated browser, never scraped. Individual X voices, like Peter Mantas for biotech, are pulled on demand. The roster is curated, not comprehensive: quality of thinking over volume of noise.

Each morning the system reads every channel's feed, pulls the transcripts of new videos, summarizes each one, and grounds the numbers against live market data before anything reaches the thesis. Transcripts are fetched through a residential proxy, because YouTube rate-limits the unattended run's shared server IP; the proxy gives each request a fresh address so the pull actually lands. If a must-have episode still resists, a fallback reads the transcript straight from the rendered page in a logged-in browser. Every run also reports exactly which transcripts came through and which were blocked or failed, so a missed source is never invisible.

The roster supplies opinions; a separate event layer supplies facts. Each morning the system also pulls the last day's news for every holding, a general feed filtered against the standing theses and the family business, the week's economic calendar, and any upcoming earnings dates for names we own. The discipline is strict: every item must map to a thesis, a trigger level, a holding, or the dealership, or it is dropped — and a headline alone never moves a probability. News raises questions; the data and the tracked analysts answer them. The exception is hard fact: a central-bank decision, a signed agreement, an earnings report. Those update the record immediately.

The third input, alongside the experts and the events, is hard data — and we verify rather than trust. Prices, fundamentals, and analyst estimates come from Financial Modeling Prep; macro series like CPI and fed funds from the Federal Reserve's FRED; Bitcoin on-chain metrics from dedicated feeds; and the authoritative MicroStrategy and STRC figures from the company's own dashboard at strategy.com. When an expert cites a level or a multiple, we check it against the live number before it informs the thesis — and the macro series are themselves the basis for the consumer and housing theses, where the data leads and no expert is needed.

The thesis is the brain of the system. Each day's synthesis updates a small set of core theses, each carrying an explicit conviction percentage, the experts who support it, the dissent against it, and the specific signal that would change our mind. Disagreement is preserved rather than averaged away, because the disagreements are usually where the information is. A revision log records what changed each day and which sources drove it, newest first.

Two standing rules shape it. For the MicroStrategy and STRC leverage read we lean hardest on the quantitative risk experts at True North (Jeff Walton), while the broader Bitcoin cycle view still draws on the full roster. And the thesis is written to be right, never to be shareable: the marketing function reads it but can never edit it.

One scheduled job runs at 6am: it ingests the roster, syncs the live portfolio, pulls the event layer (news and calendars), updates the Living Thesis and every page's view block, writes the day's briefing, then fetches fresh market data, rebuilds all eleven pages, and publishes the site. A Sunday review goes deeper: it re-scores every conviction from scratch, consolidates the week's prose, audits the charts, and publishes a state-of-the-thesis note. Scheduled jobs run while the app is open; if it is closed, they run on the next launch.

Every page holds one writing standard: the reader is a smart business executive, not a market professional. People are introduced with a role on first mention, every term of art is explained inline the first time it appears, and every data point carries its implication in the same sentence — the numbers are never dumbed down, only the jargon. In the Briefing, any mention of a standing thesis is a click-to-open popup showing that thesis's full current text, parsed live so it can never go stale.

The anchor is the power-law trend: over its full history, Bitcoin's price tracks a straight line against time on a log-log scale, which gives a long-run fair value. Today's price against that line is the first read. We then blend a composite z-score across the Mayer multiple, MVRV, the Puell multiple, the fear and greed index, and a net-liquidity measure. Negative means cheap, positive means expensive. The composite buy trigger sits around minus 1.3 standard deviations and the trim zone around plus 2. The MicroStrategy and STRC leverage complex is tracked separately, because the fragility there is the leverage and the dollar-reserve runway, not spot Bitcoin.

The AI, Oil & Gas, and Biotech pages all use the same engine. Each name is scored within its own layer of true peers, apples to apples, on five axes: Value, Quality, Trend and entry, Analysts, and Roster conviction. The scores are robust z-scores built from the median and median absolute deviation and winsorized, so a single outlier can't distort a small layer. Within a layer, a score at or above plus 0.5 sigma screens BUY and at or below minus 0.5 sigma screens TRIM. It is a relative ranking and a long-horizon entry tool for one-to-five-year holds, not a trading signal.

• Value: cheapness on the metrics that fit the sector.
• Quality: durable profitability and a sound balance sheet.
• Trend and entry: long-term relative strength counts for it, while being stretched above the 200-day moving average counts against it, so the axis rewards pullback entries rather than chasing.
• Analysts: price-target upside, the net buy-versus-sell rating, and estimate revisions.
• Roster: a conviction tilt from the tracked experts, kept deliberately sparse and small so it informs the score without dominating it.

A market-temperature gauge at the top of each page shows how extended the whole universe is right now, as context, separate from the per-name scores.

The valuation column always leads with the best available, sector-appropriate multiple rather than forcing one template on every name:

• AI and tech: forward P/E and PEG, with PEG built on a multi-year EPS growth rate for a long-horizon view.
• Energy: EV/EBITDA and free-cash-flow yield, which is what the sector actually trades on.
• Biotech commercial names: P/E where it exists, otherwise EV/EBITDA.

Forward P/E is deliberately not the headline everywhere. It requires both analyst coverage and positive earnings, so it is blank for a large share of names, and a P/E on a tiny positive number is distorted anyway. We lead with whatever is available and keep forward P/E as a secondary line. In the scoring it is only one of several value inputs and is dropped when missing, so a blank never biases the result.

Most of biotech is pre-revenue, so P/E and margins are meaningless there. We split each name by stage. Commercial, profitable names keep full fundamentals. Clinical, pre-revenue names are scored on real balance-sheet survivability instead, with two repurposed columns:

• Pipeline: enterprise value measured against cash on hand. Cheaper is lower, and below net cash means the market is assigning the pipeline negative value, which is either deep value or distress.
• Survival: cash runway, the months of cash left at the current burn rate, and share dilution, the year-over-year growth in the share count.

Cash runway is the single most important objective number for a clinical biotech, because it decides who can reach their next catalyst without a dilutive raise. This keeps the read honest: a name a roster voice is passionate about can still rank Screen− if it is the most expensive and most dilutive of its peers. The planned next upgrade adds a catalyst axis from clinicaltrials.gov, using each program's trial phase and expected readout date, since biotech is driven by binary events. True risk-adjusted NPV needs paid pipeline data, so for now we approximate it with these objective proxies and say so plainly.

Every page opens with a view block, rewritten each morning from the updated thesis so the data and the narrative always agree. It is structured, not prose: a one-line stance, the conviction percentage, a short read, the live trigger levels with what a break of each would mean, the named voices and the named dissent, what would change the view, and when it last changed — every level checked against live data at write time. The discipline: a view you cannot reduce to a stance, a number, and a falsifiable trigger is not yet a view. The Macro page is the exception — its block is a fresh analysis of that day's data, not the thesis, covered above. The thesis text itself states the current view only; its history and conviction paths live in the Revision Log and the Daily Briefings, and the Sunday review re-scores every conviction from scratch and publishes a one-page state-of-the-thesis note.

The site opens on the day's Briefing. Beyond the Thesis (described above) and the four model pages (Bitcoin, AI, Oil & Gas, Biotech, described below), the data and family tabs are:

• Briefing — each morning's full briefing (TL;DR, what changed, market snapshot, themes, book, lessons, what to watch) in a readable layout; day-by-day history lives in the Notion briefings database. The run also files the day's best durable lessons into a running ledger.
• Macro — the conditions dashboard: every indicator must feed a thesis, mark a trigger, or be one of the roster's named tells (policy and liquidity, rates, inflation, labor, credit, dollar and hard assets, energy), each with 2/5/10/20-year charts and a ten-year range gauge. Its centerpiece is the trigger board: every falsifiable thesis level as a live ARMED/TRIGGERED row, so the page answers "which conviction is the market voting on right now" rather than "what is macro doing." Data from FRED and FMP; a throttled source carries its last-good value rather than failing the page.
• Family — every family asset rolled up against a target allocation, plus a net worth chart that tracks the four asset classes year by year, a liquidity ladder, owner and manager breakdowns, and a standing action queue. The math runs on the investable base; personal residences are shown but excluded (a home is consumption, not a position), and real estate splits into dealership, investment, and personal so each is judged on its own job.
• ACM — the boat dealership as a capital-allocation problem: nine years of statements in four pictures (revenue, profit, inventory versus floor plan debt, return on equity), the current balance sheet, an Industry watch of demand-driver news (gas, consumer credit, rates, marine results), and a standing view on where the next dollar earns most. Financials update when new statements arrive.
• Portfolio — the live book: NAV and P&L on live prices, factor-cluster exposure (positions that crash together counted as one), allocation versus target with the dollars to close each gap, every holding joined to its model signal so conflicts are visible at a glance, and a flags panel. The sheet stays the source of truth for targets.

Family and ACM carry the same redactions as everywhere: category and entity labels, never account numbers or property addresses. Charts follow one rule across the site — macro composites come from Caliban (3Fourteen Research), the Bitcoin visuals are generated natively from our own model, and every chart must support the specific claim beside it or it comes out.

Risk is measured in factor clusters rather than account sleeves, because positions that crash together count as one exposure: MicroStrategy, the spot Bitcoin ETF and the STRC preferred are a single Bitcoin-complex position, not three diversified holdings. The daily run recomputes cluster exposures and a small set of explicit stress scenarios (the betas live in an editable config file) against the live book, and every briefing carries them, so concentration is always visible next to the day's views. Target weights in the portfolio sheet remain the allocation authority; a fuller framework of binding limits exists in draft and is parked by choice. The name-level diligence checklist is live (described below); a signal track-record ledger is the planned next layer.

A June 2026 recalibration made the division of labor explicit. The sector models are SCREENS — relative rankings whose labels read SCREEN+ and SCREEN−, never buy/sell verdicts — and their job is triage: deciding which of ~110 names earns deeper work, gating clinical biotech on survivability math, and flagging divergences between the model and the tracked experts (the highest-information rows on the site). The Bitcoin model is the exception that keeps verdict language, because it is a single-asset valuation framework with a structural anchor and explicit thresholds rather than a cross-sectional ranking.

When a name graduates from the screen, it goes through the name-level diligence checklist (knowledge/diligence.md) — a Third Point-style baseline gate of 14 universal points plus a sector module (about 20 to 26 per sector): the differentiated claim with a number, business quality, what the price implies, dated catalysts, regime and cluster fit, the steelmanned bear case, management's say-do record, and a pre-committed invalidation. The output is a one-page memo that doubles as the decision-journal entry. Decisions themselves are made at the sleeve level, where the thesis, the cluster lens, and the sheet's targets live.

This is not investment advice. Conviction is a probability-weighted synthesis of other people's views, not an independent forecast unless noted, and disagreement is preserved rather than resolved. The sector models are relative-ranking screens and long-horizon entry tools, not market timing. Risk-adjusted NPV for biotech and a full catalyst calendar require data we do not yet pay for, and the pages flag where we approximate. The scheduled jobs only run when the app is open. The system is built to be transparent about all of this on purpose: a screen you can audit is worth more than a black box you have to trust.

Everything the system reads, grouped by the role it plays. The rule: a source earns its place by feeding a thesis, a model, a trigger, or the family balance sheet — and this registry is updated in the same change whenever a source is added or removed.

Opinion layer — what smart people think

Curated experts whose reasoning feeds the Living Thesis. Disagreement is preserved, never averaged away.

Data layer — what the numbers say

Hard market and economic data; used to verify every expert-cited figure and drive the models.

Event layer — what just happened

Facts to test against the theses, never a second opinion stream. Map-or-drop: every item must tie to a thesis, trigger, holding, or the dealership. Headlines alone never move a probability.

Family layer — our own numbers

Private data; the only sources the outside world cannot give us. Drives the Family, ACM, and Portfolio pages.