Auctus Sapiens is a daily market briefing in the register of a serious financial daily — markets, the calendar, deep dives, insider and congressional flow, a transparent paper-trading book, and one contrarian essay a day. Assembled by an agentic pipeline while you sleep, typeset as a broadsheet, and delivered before the bell.
Founding rate fixed while the reader list is small. Seven issues a week, including a Saturday Edition and a long Sunday essay. A research publication — not investment advice.
Data collection, chart rendering, the paper-trading engine, the layout, the PDF, the delivery — all of it is committed, testable software that runs the same way every morning. It caches a decade of history so it can date its own claims, fails softly when a source goes dark, and notes the gap in the issue rather than papering over it.
The product improves by commit, not by prompt-tinkering. New sections, new rituals, new checks are added to the engine — and the writer inherits them automatically.
A single language model reads the morning's assembled evidence and the editorial brief the engine prints for it, then writes the issue: the headline, the things you need to know, the forty-second summary, and every department in the house voice. It is the only non-deterministic step in the whole system — and the only one that needs to be.
That is the cleanest picture of agentic AI there is: a narrow, well-bounded act of reasoning, wrapped in machinery that handles everything reasoning should not.
A weekday issue runs to a dozen-plus sections in a fixed order, gated by the day of the week — oil on Tuesday, credit on Thursday, the trade deficit on Friday, a single long essay on Sunday. A representative few:
The session read in one table — index, VIX, the dollar, the curve — then the macro calendar: what printed against consensus, and what the week is waiting on. When a data feed fails, the issue says so rather than inventing a number.
Two mechanical screens swept daily across ~1,050 names — value and quality — with the overlap deep-dived: valuation models, a Graham check, technicals, and the insider tape, reconciled into a single read.
Real parsed Form 4 filings and STOCK Act disclosures, flagged for 52-week extremes and clustered conviction. Open-market executive buying — cash, at the prevailing price — gets the weight it deserves.
A standing $100,000 simulated portfolio. Orders fill at the next session's observed price plus slippage and a ticket — never a price already known. Stops walk real daily bars. The book can go bust, and the record never resets.
The briefing grades its own published calls against later prices, citing publication dates. Last night's tripwires are scored this morning — hit, miss, or untestable. Never silently dropped.
One heresy a day: a single contrarian thesis, argued in character from the day's data and the old books, and built to be falsified — each one closes with the observations that would prove it wrong.
Weekend Edition · the Sunday essay
Need to know
“The index barely moved this week — but underneath it the composition changed decisively. The keystone was oil. A slide of that size in WTI cooled the inflation story, gave bonds permission to rally and havens a reason to be sold, and the cash that left the inflation trade went looking for risk. What the barrel gave up, the rest of the market spent.”
The same issue grades its own record without flinching: “A perfect record over a handful of barely-moved, days-old calls is not evidence of skill; it is evidence that we have not yet held a position long enough to be wrong. Honesty over comfort: ask again in a month.” That self-scrutiny is engineered in, not improvised.
The scavenging that a research desk would spread across a morning happens in a single overnight run. Four stages, every day, hands-free:
Before dawn, the pipeline sweeps markets, macro releases, filings, and a wide equity universe — pulling, cleaning, and caching the day's raw material.
It renders the day's figures itself, choosing the front-page lens from a rotating set so no two issues open the same way.
A single agent reads the collected evidence and the editorial brief, then composes the issue — headline, summary, every department, in house voice.
The markdown is typeset into a broadsheet PDF, archived to version control as the publication of record, and emailed — on your screen before the open.
It is a deliberately simple workflow — and that is the point. It shows what agentic AI actually does when it is pointed at real work: read how the 4 a.m. process works →
A newsletter written by a language model only earns a reader by being auditable. These commitments are enforced by code, not promised by a byline:
The paper book fills tomorrow at tomorrow's price, with slippage and a ticket charge. No back-fitting, no trading a level the system has already seen.
“The lowest in years” is banned unless the pipeline can date it against a decade of cached data. Unverifiable claims are dropped, not softened.
Every tripwire set tonight is graded tomorrow. Every call carries a publication date. The scorecard is shown even when it is thin and flattering — honesty over comfort.
Every issue carries a six-part legal notice: deliberate use of a language model, hallucination risk, named-perspective caveats. The machine's voice is labelled as such.
$25/mo
Seven issues a week · before the open
The founding rate is held for founding members while the reader list is deliberately small. You get every issue — the weekday briefings, the Saturday Edition, and the long Sunday essay — as both an email and a printable broadsheet PDF. No annual plan yet; month to month, cancel anytime.
A research and commentary publication. Not investment advice; no warranties. Every issue carries the full notice.
Founding membership is $25/mo while the room is small. Claim a seat and the next briefing lands in your inbox before the bell.