P01 · Paper portfolio
Long-Term Compounders
by AI Portfolios
This is the simple view. Nothing has been removed — the decision records, the refused proposals, the AI's own words, the cost model, the published limits and the hash chain are all in Advanced, which is the switch in the header. How to verify any of it →
Showing every layer. Pick Simple or Advanced in the header to choose one — nothing is removed either way, and the full record is always in this page.
Long-Term Compounders
A published decision instant passed unanswered and the next run will answer it, stamped with both instants so the lateness is visible: due 2026-09-20T16:00:00+00:00 (5.9d ago) and newest decision run of any kind is 2026-09-13T22:47:15.104596+00:00. QUEUED FOR CATCH-UP — the next run picks it up; it expires 2026-09-27T16:00:00+00:00.
Compound capital over a 5-10+ year horizon by owning a concentrated set of high-quality businesses that earn durable returns on invested capital and reinvest at attractive rates. Minimise turnover, taxes and trading cost.
| Slot | Last due | Answered | Status |
|---|---|---|---|
weekly review 0 12 * * SUN · America/New_York | 2026-09-20 16:00 | never | CATCH_UP_DUE due 2026-09-20T16:00:00+00:00 (5.9d ago) and newest decision run of any kind is 2026-09-13T22:47:15.104596+00:00. QUEUED FOR CATCH-UP — the next run picks it up; it expires 2026-09-27T16:00:00+00:00. |
monthly rebal 0 12 1 * * · America/New_York | 2026-09-01 16:00 | 2026-09-01 22:51 | ok due 2026-09-01T16:00:00+00:00, ran 2026-09-01T22:51:48.277976+00:00 (LATE by 7h — a catch-up, recorded as one) |
quarterly deep 0 12 20 2,5,8,11 * · America/New_York | 2026-08-20 16:00 | 2026-08-20 22:42 | ok due 2026-08-20T16:00:00+00:00, ran 2026-08-20T22:42:12.538344+00:00 (LATE by 7h — a catch-up, recorded as one) |
daily risk scan 30 16 * * MON-FRI · America/New_York | — | n/a | does not decide This slot marks and reports; it never calls the model, so it leaves no decision record to check it against. |
Catch-up policy. A decision instant that passes unanswered is run on the next pass, once, and the record stamps both instants — when it was due and when it actually ran. Past the catch-up window the gap stays open and is published as missed rather than backfilled.
Track record
Fewer than 60 daily observations. Annualised return, volatility, Sharpe, Sortino and Calmar are withheld: annualising a short sample produces numbers that look precise and are not.
Our own marks from our own fills (nothing here is vendor price data). Deliberately monochrome: colour that codes "good" and "bad" is an editorial thumb on the scale.
Index 100 is the starting capital ($100,000), so this line ends at the total return published above it. The comparison line is indexed to the same capital and starts at 100 at its own first close here: the record carries no priced instant at which capital was granted, so the comparison capital is uninvested until then rather than given a price nothing printed. Both cover the identical window.
Index values are derived percentage returns over IEX last-trade closes, which are licensed for publication; no raw vendor price is rendered.
| symbol | since entry | weight | opened |
|---|---|---|---|
| MSFT | +1.8% | +7.1% | 2026-08-13 |
| JNJ | +2.1% | +7.1% | 2026-08-13 |
| V | +2.5% | +6.2% | 2026-08-13 |
| UNP | -4.5% | +5.8% | 2026-08-13 |
| COST | -4.3% | +5.7% | 2026-08-13 |
Return since the AI entered, measured from this book's own mark against what it actually paid — our own numbers over our own record, not vendor price data.
Weights are our own work product, computed at the newest audit-chain NAV mark — never re-derived later, never estimated from cost basis. Logos identify the holdings and imply no endorsement (operator decision, session 11); sector tints are structure, not judgement.
| Symbol | Quantity | Avg cost | Stop | Opened |
|---|---|---|---|---|
 COST5.7% | 6.2380 | 960.39 | — | 2026-08-13 committed 2026-08-14 |
 JNJ7.1% | 26.7094 | 260.76 | — | 2026-08-13 committed 2026-08-14 |
 MSFT7.1% | 14.0879 | 496.57 | — | 2026-08-13 committed 2026-08-14 |
 UNP5.8% | 20.1484 | 298.37 | — | 2026-08-13 committed 2026-08-14 |
 V6.2% | 16.4181 | 366.28 | — | 2026-08-13 committed 2026-08-14 |
Why two dates? "Opened" is the market session the opening fill was priced on. The licensed data feed's T+1 rule means a cycle prices on the newest session already licensed for use, so the run that produced the fill can be committed to the audit chain on a later date — that commitment date is shown beneath. The commitment time is what makes history tamper-evident; the pricing session is what returns are computed from. Both are published on every fill.
Recent decisions
Every run, including the ones that traded nothing: the committed fact-pack hash (written to the audit chain before anything was proposed), the AI's published view, each proposal with the rule engine's verdict, and the fills that resulted. Rejected proposals stay up with their reason codes — a reader who can only see the trades that happened cannot judge the discipline that refused the ones that didn't.
Every card carries the instant it was decided at, because every card is a photograph. The facts in it were frozen when the run was committed and are never revised — a view that said "the platform has closed zero trades" was true at its timestamp and reads as a claim about today unless the card says otherwise. Consecutive runs that halted on identical codes are compressed into one card with a visible count and every run id listed; nothing is dropped.
AI-generated. All quantitative claims traced to the published fact pack. Mandate P01 is a long-horizon quality-compounder book with heavy cash: cash_pct 68.09% (pf.cash_pct), NAV ~99,895 USD (pf.nav), 5 of 25 slots used (pf.position_count, pf.max_positions), 20 slots free (pf.position_slots_free), min new position 1,997.91 USD (pf.min_new_position_usd). Portfolio is essentially flat since inception (pf.total_return_pct -0.10%) with negligible drawdown (pf.drawdown_pct 0.30%). All positions were opened only 6 days ago (pos.*.days_held=6), so the book is newly established. The mandate philosophy is quality at a defensible price, minimise turnover; it explicitly asks me to rank quality and flag thesis breaks, not to time the market. On the five holdings, all show durable-business hallmarks: COST, JNJ, MSFT, UNP, V each have 5/5 FCF-positive years (fx.COST.fcf_positive_years_of_last_5, fx.…
| Proposal | Conviction | Lifecycle | Codes |
|---|---|---|---|
| HOLD COST | 4 | PROPOSED→GATES PASSED→NO ORDER HOLD is a decision not to trade — no order is created | — |
| HOLD JNJ | 4 | PROPOSED→GATES PASSED→NO ORDER HOLD is a decision not to trade — no order is created | — |
| HOLD MSFT | 4 | PROPOSED→GATES PASSED→NO ORDER HOLD is a decision not to trade — no order is created | — |
| HOLD UNP | 4 | PROPOSED→GATES PASSED→NO ORDER HOLD is a decision not to trade — no order is created | — |
| HOLD V | 4 | PROPOSED→GATES PASSED→NO ORDER HOLD is a decision not to trade — no order is created | — |
Reading the lifecycle. PROPOSED and GATES PASSED are published facts. QUEUED is shown as reached only where a fill proves it — the payload publishes no order record. FILLED / EXPIRED stays undecided without a matching fill, because an accepted order can price on a later session under the T+1 rule, and calling that "expired" would be inventing the outcome. "Accepted" alone used to sit in this column and read as though the trade had happened.
AI-generated. All quantitative claims traced to the published fact pack. Mandate P01 seeks 5-10yr compounders with durable ROIC, quality-at-a-defensible-price, minimal turnover. The book holds 5 positions, all only 5 days old (pos.COST.days_held, pos.JNJ.days_held, pos.MSFT.days_held, pos.UNP.days_held, pos.V.days_held all =5), with ~67.9% cash (pf.cash_pct=67.887) and 20 free position slots (pf.position_slots_free=20). Total return is essentially flat (pf.total_return_pct=0.2009), no drawdown (pf.drawdown_pct=0). The fact pack contains price/momentum, market cap, ADV, ATR, FCF-positive-years-of-last-5, and years-of-public-history — but NO valuation multiples (P/E, EV/EBITDA), NO ROIC/margin data, NO growth data. For a quality-at-a-defensible-price mandate, the two decisive inputs — quality (ROIC/reinvestment) and price (valuation) — are BOTH absent. I therefore cannot rank "quality a…
| Proposal | Conviction | Lifecycle | Codes |
|---|---|---|---|
| HOLD COST | 3 | PROPOSED→GATES PASSED→NO ORDER HOLD is a decision not to trade — no order is created | — |
| HOLD JNJ | 3 | PROPOSED→GATES PASSED→NO ORDER HOLD is a decision not to trade — no order is created | — |
| HOLD MSFT | 3 | PROPOSED→GATES PASSED→NO ORDER HOLD is a decision not to trade — no order is created | — |
| HOLD UNP | 3 | PROPOSED→GATES PASSED→NO ORDER HOLD is a decision not to trade — no order is created | — |
| HOLD V | 3 | PROPOSED→GATES PASSED→NO ORDER HOLD is a decision not to trade — no order is created | — |
Reading the lifecycle. PROPOSED and GATES PASSED are published facts. QUEUED is shown as reached only where a fill proves it — the payload publishes no order record. FILLED / EXPIRED stays undecided without a matching fill, because an accepted order can price on a later session under the T+1 rule, and calling that "expired" would be inventing the outcome. "Accepted" alone used to sit in this column and read as though the trade had happened.
AI-generated. All quantitative claims traced to the published fact pack. Mandate P01 seeks 5-10yr compounders — quality businesses with durable FCF, bought at a defensible price, minimising turnover. The portfolio holds 5 quality names (COST, JNJ, MSFT, UNP, V), each ~6-7% weight, with 68.1% in cash (pf.cash_pct) and 20 free position slots (pf.position_slots_free). All five holdings show days_held=0 (pos.*.days_held), meaning they were just established; total portfolio return is roughly flat (pf.total_return_pct = -0.15%). Given the philosophy explicitly instructs "the AI's job is to rank quality and identify thesis breaks, not to time the market," and turnover should be minimised, the existing holdings are all high-quality, 5/5 FCF-positive names (fx.*.fcf_positive_years_of_last_5 = 5 for COST, JNJ, MSFT, UNP, V) with long public histories. None show a thesis break: JNJ ret_252d +49.3%…
| Proposal | Conviction | Lifecycle | Codes |
|---|---|---|---|
| HOLD MSFT | 4 | PROPOSED→GATES PASSED→NO ORDER HOLD is a decision not to trade — no order is created | — |
| HOLD JNJ | 4 | PROPOSED→GATES PASSED→NO ORDER HOLD is a decision not to trade — no order is created | — |
| HOLD COST | 4 | PROPOSED→GATES PASSED→NO ORDER HOLD is a decision not to trade — no order is created | — |
| HOLD UNP | 4 | PROPOSED→GATES PASSED→NO ORDER HOLD is a decision not to trade — no order is created | — |
| HOLD V | 4 | PROPOSED→GATES PASSED→NO ORDER HOLD is a decision not to trade — no order is created | — |
Reading the lifecycle. PROPOSED and GATES PASSED are published facts. QUEUED is shown as reached only where a fill proves it — the payload publishes no order record. FILLED / EXPIRED stays undecided without a matching fill, because an accepted order can price on a later session under the T+1 rule, and calling that "expired" would be inventing the outcome. "Accepted" alone used to sit in this column and read as though the trade had happened.
AI-generated. All quantitative claims traced to the published fact pack. Mandate P01 seeks 5-10+ year compounders: durable, high-quality businesses with consistent free cash flow at a defensible price, minimising turnover. Portfolio is 100% cash (pf.cash_pct=100), 25 slots free (pf.position_slots_free), $100k NAV (pf.nav). This is an opening-allocation problem, not a trading problem, so I select a small set of highest-quality names with the strongest evidence of durable cash generation available in the pack. The fact pack is thin on the metrics that actually define quality — there is no ROIC, margin, revenue growth, leverage or valuation multiple anywhere. The only fundamental signals present are fcf_positive_years_of_last_5 and years_public_history; everything else is price/momentum/liquidity. I therefore cannot rank "quality at a defensible price" with any rigour: I can confirm consi…
| Proposal | Conviction | Lifecycle | Codes |
|---|---|---|---|
| BUY MSFT | 4 | PROPOSED→GATES PASSED→QUEUED→FILLED | — |
| BUY JNJ | 4 | PROPOSED→GATES PASSED→QUEUED→FILLED | — |
| BUY COST | 3 | PROPOSED→GATES PASSED→QUEUED→FILLED | — |
| BUY UNP | 3 | PROPOSED→GATES PASSED→QUEUED→FILLED | — |
| BUY V | 3 | PROPOSED→GATES PASSED→QUEUED→FILLED | — |
Reading the lifecycle. PROPOSED and GATES PASSED are published facts. QUEUED is shown as reached only where a fill proves it — the payload publishes no order record. FILLED / EXPIRED stays undecided without a matching fill, because an accepted order can price on a later session under the T+1 rule, and calling that "expired" would be inventing the outcome. "Accepted" alone used to sit in this column and read as though the trade had happened.
fills: BUY 14.0879 MSFT @ 496.57 · BUY 26.7094 JNJ @ 260.76 · BUY 6.2380 COST @ 960.39 · BUY 20.1484 UNP @ 298.37 · BUY 16.4181 V @ 366.28
What the AI is allowed to do
This portfolio's AI ranks candidates and explains its reasoning. It proposes direction and conviction only. Every price, quantity, weight and risk limit is computed by deterministic code the model cannot see or influence.
BUY · ADD · TRIM · SELL · HOLD · FLAG_THESIS_BREAK
At most 5 proposals per run, each carrying a direction, a conviction from 1 to 5, a rationale, and references to the facts it used.
- set a price
- set a quantity or share count
- set a weight or position size
- set or move a risk limit
- execute anything
Model tier deep · prompt version P01-v1. Any change to the decider or the prompt is recorded as a MODEL_CHANGE event in the audit chain — without it the record would be a chimera of two systems presented as one.
Enforced limits
Every limit below names the code path that enforces it. This is not decoration: a limit that is published but never fires is worse than no limit, because a reader has no way to tell the difference. A test walks every mandate, drives the engine into the state each declared control claims to protect against, and fails the build if nothing stops it.
| Limit | Value | Enforced by |
|---|---|---|
| Maximum gross exposure | 100.0% | gate 2 — size_order |
| Maximum single sector | 30.0% | gate 2 — size_order |
| Limit | Value | Enforced by |
|---|---|---|
| Shorting | prohibited | gate 1 — proposal validation |
| Derivatives | prohibited | gate 1 — proposal validation |
| Margin | prohibited | gate 1 — proposal validation |
| Limit | Value | Enforced by |
|---|---|---|
| Maximum positions | 25 | gate 3 — BREACH_MAX_POSITIONS (portfolio limit check) |
| Minimum new position | 2.0% | gate 2 — size_order |
| Maximum order as % of ADV | 1.0% | gate 2 — size_order |
| Limit | Value | Enforced by |
|---|---|---|
| Single-day loss alert | 7.0% | gate 3 — alert |
| Limit | Value | Enforced by |
|---|---|---|
| Stale-data halt | 48 hours | gate 3 — HALT_STALE_DATA |
| Limit | Value | Enforced by |
|---|---|---|
| At −15.0% drawdown | alert, publish_commentary | gate 3 — drawdown ladder |
| At −25.0% drawdown | alert, publish_commentary, pause_new_positions_days:20 | gate 3 — drawdown ladder |
| At −35.0% drawdown | alert, mandatory_deep_review, pause_all_buys_until_review_published | gate 3 — drawdown ladder |
| At −60.0% drawdown | graveyard_review | gate 3 — drawdown ladder |
| Limit | Value | Enforced by |
|---|---|---|
| Max trades per quarter | 8 | entry block — PAUSE_TURNOVER_CAP_REACHED (never blocks an exit) |
| Max annual turnover pct | 40 | entry block — PAUSE_TURNOVER_CAP_REACHED (never blocks an exit) |
| Min holding period days | 30 | entry block — PAUSE_TURNOVER_CAP_REACHED (never blocks an exit) |
| Limit | Value | Enforced by |
|---|---|---|
| Halt trading if price gap unexplained pct | 25 | gate 3 — circuit breaker |
| Halt trading if benchmark data missing | true | gate 3 — circuit breaker |
| Halt trading if factpack hash mismatch | true | gate 3 — circuit breaker |
Execution
Fills are struck on a VWAP window that begins strictly after the decision timestamp plus a latency delay. No fill can use information from the bar in which the decision was made, so look-ahead is arithmetically impossible rather than merely avoided.
Philosophy
Quality at a defensible price. Returns come from the underlying businesses compounding, not from re-rating. The AI's job is to rank quality and identify thesis breaks, not to time the market.
Review schedule
| Job | Cron | Timezone | Makes a decision |
|---|---|---|---|
| weekly review | 0 12 * * SUN | America/New_York | yes |
| monthly rebal | 0 12 1 * * | America/New_York | yes |
| quarterly deep | 0 12 20 2,5,8,11 * | America/New_York | yes |
| daily risk scan | 30 16 * * MON-FRI | America/New_York | no |
Published on a fixed, regular schedule. Never event-triggered — no "market is crashing, sell now" alerts, deliberately. This table is the promise; the cadence panel at the top of the page is whether it was kept, instant by instant.
Machine-readable mandate: config/portfolios/P01_long_term_compounders.yaml · human rulebook: docs/portfolios/P01_long_term_compounders.md · effective from 2026-08-06 (wall clock) · record starts 2026-08-13 (pricing session) · payload 540d30e63326…