THE DESK · THE RESEARCH · Nº 1311 · EDITION 1 ·Liquid error (snippets/rm-earnings-model-card line 27): comparison of String with 0 failed
LUND CARDS · THE DESKNº 1311
THE CARD AS TEXT · FOR EYES AND FOR MACHINES
THE EARNINGS MODEL CARD · the quarterly-model seat — builds forward quarters that tie to the actuals
WAKES WHEN a company's quarterly earnings need modeling forward from actuals · a person asks 'model the next four quarters', 'build the earnings model', 'project the P&L' · a forward estimate needs its assumptions visible and its lines tied
THE LOOP
anchor · the reported actuals, preserved exactly
assume · one layer: revenue growth, gross margin, opex percent
build · forward quarters where gross profit = revenue − COGS and operating income ties
stop · a missing assumption leaves the quarter [FILL]; nothing is projected on a guess
NEVER
Projects a forward quarter on a guessed assumption — a blank assumption is [FILL]
Gives investment advice or tells anyone to buy, sell, short, or trade
Presents a backtest, model, or projection as a promise of future return — unknown inputs are marked [FILL]
Front-runs, times a trade, or substitutes for a licensed professional's judgment
IT MAKES run — anchors actuals, builds forward quarters that tie, marks missing assumptions; selftest — 10 checks that prove the machine.
THE LAW A card builds and checks the analysis — the model, the screen, the thesis. It never gives investment advice, never recommends a security to buy or sell, never presents a backtest or projection as a promise of future return, never front-runs or times a trade, and never replaces the judgment and licensed oversight an investment decision needs.
PROOF SELFTEST 10/10 · witnessed in Claude 2026-10-20 on the studio’s own example inputs · the dated run in the box (RUN.md) · Edition 1.
THE SEAL 98 of 100 · LEGENDARY · WITNESSED · Trigger 5 · Machinery 5 · Law 5 · Portability 5 · Proof 5
IT CAN BE WRONG an AI reading a text file: it can be wrong and can invent a number, a rule, a name or a date; check what matters against your own records and the source; the risk is yours. LICENSE-NOTE.md rides in the packet and is the licence.
THE PUNCH · SHA-256 OF SKILL.MD · BD59D0EC68401CBB75B0D8A8
CITE THIS CARDTHE EARNINGS MODEL CARD, Edition 1. Lund Studio LLC, Westminster, Colorado. https://lundr.tech/?view=earnings-model-card. Punch BD59D0EC68401CBB75B0D8A8. Retrieved 2026-10-20.
What it is.
Builds forward quarters that tie to the actuals. Builds forward quarters that tie to the actuals. Use when a company's quarterly earnings need modeling forward from actuals. Not for buy or sell calls. For the cash flows it feeds → THE DCF CARD.
It carries a machine that shows its working: run — anchors actuals, builds forward quarters that tie, marks missing assumptions; selftest — 10 checks that prove the machine — 10 checks in its selftest, run in the open below. It never projects a forward quarter on a guessed assumption — a blank assumption is [FILL]; never gives investment advice or tells anyone to buy, sell, short, or trade; never presents a backtest, model, or projection as a promise of future return — unknown inputs are marked [FILL]; never front-runs, times a trade, or substitutes for a licensed professional's judgment.
The house law, written into the card.
It is in the card itself, so the AI follows it.
THE HOUSE LAW · THE DESKA card builds and checks the analysis — the model, the screen, the thesis. It never gives investment advice, never recommends a security to buy or sell, never presents a backtest or projection as a promise of future return, never front-runs or times a trade, and never replaces the judgment and licensed oversight an investment decision needs.
THE LIMIT, ON THE TINIt compounds the assumptions you choose; the output is only as real as the inputs. A model is a disciplined guess, not a forecast of what will happen.
The method.
Anchor. The reported actuals, preserved exactly.
Assume. One layer: revenue growth, gross margin, opex percent.
Build. Forward quarters where gross profit = revenue − COGS and operating income ties.
Stop. A missing assumption leaves the quarter [FILL]; nothing is projected on a guess.
What it does once your AI has it.
run Anchors actuals, builds forward quarters that tie, marks missing assumptions
selftest 10 checks on the studio’s own example inputs; it must print selftest 10/10
What it will never do.
It never projects a forward quarter on a guessed assumption — a blank assumption is [FILL]; never gives investment advice or tells anyone to buy, sell, short, or trade; never presents a backtest, model, or projection as a promise of future return — unknown inputs are marked [FILL]; never front-runs, times a trade, or substitutes for a licensed professional's judgment.
Where it hands off: The cash flows it feeds → THE DCF CARD. The write-up around it → THE EQUITY RESEARCH CARD.
It is an AI reading a text file: it can be wrong, so check what matters against your own records and the source. The holder brings their own AI; no endorsement by Anthropic or any other AI company is claimed. Names of other companies and standards are used only to say what the card works with.
What’s in the buy.
SKILL.md — the door your AI reads first: when it wakes, when it does not, the loop, the never-lines, the house law
CARD.md — the whole card in ten sections, §0 to §9 · TIN.md — what is on the tin, in nine lines
scripts/earningsmodel.py — the machine, Python standard library only, offline; selftest 10/10
RUN.md — the dated run: the selftest as it printed when the card was cut, with the date and the host
references/THE-METHOD.md — the method in plain words, in the card’s own voice
START-HERE.md and system/short-prompt.md — the doors, for any AI with or without skills
MY-LEDGER.md — the card’s memory, on your own machine · LICENSE-NOTE.md — the licence
PROOF · SELFTEST 10/10 · AUDIT 12/12 · WITNESSED IN CLAUDE 2026-10-20 ON THE STUDIO’S OWN EXAMPLE INPUTS · THE TEST PROMPTS IN FRESH CHATS OWED · EDITION 1 · PUNCH BD59D0EC68401CBB75B0D8A8
ON EVERY DOOR · A CARD FOR YOUR AI, A FILE FOR YOUR COMPUTER
In Claude: turn on code execution under Settings › Capabilities, then Customize › Skills › + › Create skill, and upload the zip as it is — START-HERE.md in the box walks you through it, and tells you how to keep the ledger. In ChatGPT, Gemini and the rest: a Project, a GPT or a Gem with the card’s files attached and the short door in the box pasted as its instructions. The words run anywhere an AI reads Markdown; the machines run wherever the host runs Python. Witnessed in Claude only. The host marks →
Take it.
Nº 1311 —Liquid error (snippets/rm-earnings-model-card line 116): comparison of String with 0 failed
Sold as is under the term printed. A card instructs an AI you operate; results depend on your model, your files and your judgement. Not medical, legal, tax or financial advice, never the person’s boss, and not a licence to practise. Not investment advice, not an appraisal and not an offer to sell securities. The terms →
One payment. The file is yours to keep and keeps working at its edition; new editions issued in the year after you buy reach you by email as replacement files. Tax is added at checkout where it applies. Nothing auto-renews.
AFTER YOU PAY · SIGN IN WITH THE EMAIL YOU PAID WITH · THE CARD OPENS ON MY CARDS → · CHECKED AGAINST ITS FINGERPRINT · NOTHING TO WAIT FOR
A TERM, NOT A SUBSCRIPTION: NOTHING RENEWS ITSELF AND NOBODY IS CHARGED AGAIN. WHEN A TERM ENDS THE FILES STAY ON YOUR COMPUTER AND STAY READABLE — FREEZE, NOT LOSS.
THE MACHINE · IN THE OPEN · FROM THE STUDIO’S RUN OF 2026-10-20
earningsmodel.py, showing its working.
A small Python program, standard library only. Your AI runs it; you can too. The block below is the machine’s selftest as it printed when the studio ran it from inside the packet, in Claude, on 2026-10-20.
run
anchors actuals, builds forward quarters that tie, marks missing assumptions · run ACTUALS.csv [ASSUMPTIONS.txt]
selftest
10 checks that prove the machine; it must print selftest 10/10
selftest · AS PRINTED
$ python3 scripts/earningsmodel.py selftest
wrote EARNINGS-MODEL.md — 2 actual + 2 forward quarters
wrote EARNINGS-MODEL.md — forward blocked, missing ['gross_margin', 'opex_pct']
REFUSED: quarter Q1 has no revenue
REFUSED: quarter Q1 is missing COGS or opex ([FILL]) — an actual is never guessed; a blank is not treated as zero (that would fake the gross profit)
REFUSED: no actual quarters
wrote EARNINGS-MODEL.md — 2 actual + 2 forward quarters
wrote EARNINGS-MODEL.md — 2 actual + 2 forward quarters
selftest 10/10
THE SELFTEST RUNS ON THE STUDIO’S OWN EXAMPLE INPUTS, INVENTED FOR THE TEST; NO REAL COMPANY, PERSON OR ACCOUNT IS NAMED.
QUESTIONS AT THE TABLE
Asked before the wire.
What does it need from me?
Your own files and figures, on your own disk. It starts by asking for them: the reported actuals, preserved exactly. If something it needs is missing, it marks it and says so — it never fills a gap with a guess.
Does it send anything anywhere?
No. The machine is a standard-library Python program that runs on your own computer and sends nothing anywhere; the words run wherever an AI reads Markdown. No server, no account, no key.
What is on the record?
The machine's selftest (10/10), run from inside the packet in Claude on 2026-10-20 on the studio's own example inputs and printed below as it ran; the twelve-check audit (AUDIT.md, 12/12); MANIFEST.md with every file hashed. RUN.md in the box is that run, dated. Still to come, as the next receipt: the card's test prompts asked in fresh chats with the card installed. The punch on the face is the SHA-256 of SKILL.md, so a downloaded copy can be checked against this room.
Can it be wrong?
Yes — it is an AI reading a text file: it can be wrong and can invent a number, a rule, a name or a date; check what matters against your own records and the source; the risk is yours. It compounds the assumptions you choose; the output is only as real as the inputs. A model is a disciplined guess, not a forecast of what will happen.
What will it never do?
It never projects a forward quarter on a guessed assumption — a blank assumption is [FILL]; never gives investment advice or tells anyone to buy, sell, short, or trade; never presents a backtest, model, or projection as a promise of future return — unknown inputs are marked [FILL]; never front-runs, times a trade, or substitutes for a licensed professional's judgment.
