P07 · Paper portfolio
Claude Discretionary
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.
Claude Discretionary
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 2026-09-13T22:48:39.833256+00:00. QUEUED FOR CATCH-UP — the next run picks it up; it expires 2026-09-27T16:00:00+00:00.
Test, in public and with realistic execution costs, whether a large language model given a broad liquid universe and no style constraint can select equities that outperform a passive benchmark over a multi-year horizon.
| Slot | Last due | Answered | Status |
|---|---|---|---|
weekly selection 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 2026-09-13T22:48:39.833256+00:00. QUEUED FOR CATCH-UP — the next run picks it up; it expires 2026-09-27T16:00:00+00:00. |
monthly review 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) |
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 |
|---|---|---|---|
| FTNT | +2.6% | +6.5% | 2026-08-13 |
| MRK | +4.5% | +5.9% | 2026-08-14 |
| HPE | -6.6% | +5.9% | 2026-08-14 |
| LRCX | -17.5% | +5.1% | 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 |
|---|---|---|---|---|
 FTNT6.5% | 36.2669 | 165.93 | 143.16 | 2026-08-13 committed 2026-08-14 |
 HPE5.9% | 102.0918 | 59.31 | 48.59 | 2026-08-14 committed 2026-08-17 |
 LRCX5.1% | 17.8036 | 331.69 | 252.76 | 2026-08-13 committed 2026-08-14 |
 MRK5.9% | 39.2069 | 138.55 | 135.75 | 2026-08-14 committed 2026-08-17 |
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.
fills: SELL 11.2246 AMAT @ 429.66
fills: SELL 17.6809 FDX @ 318.34
fills: SELL 16.6371 GE @ 333.21 · SELL 14.1683 JBHT @ 256.19
fills: SELL 15.5979 PANW @ 330.08
fills: SELL 26.8817 RTX @ 210.27
AI-generated. All quantitative claims traced to the published fact pack. Portfolio is down modestly (pf.total_return_pct -2.64%, pf.drawdown_pct 3.10%) with 45.7% cash (pf.cash_pct) and 10 of 15 slots used (pf.position_count, pf.max_positions), so 5 slots and ~$44.5k are deployable (pf.position_slots_free, pf.cash). The book is 6 days old — no round trips closed yet — so the primary question is whether existing positions are behaving and whether new deployment is warranted. Held positions: all 10 are underwater except MRK (+10.36% unrealised, pos.MRK.unrealised_pct), which is riding strong momentum (px.MRK.ret_20d +14.19%, ret_60d +24.45%, ret_5d +9.92%) — a clear HOLD/leader. The recently-bought tech/semi names are showing sharp 5-day drawdowns: HPE -11.58% (px.HPE.ret_5d), PANW -11.73% (px.PANW.ret_5d), FTNT -8.86% (px.FTNT.ret_5d), LRCX -7.86% (px.LRCX.ret_5d), AMAT -7.17% (px.AMAT.…
| Proposal | Conviction | Lifecycle | Codes |
|---|---|---|---|
| ADD MRK | 3 | PROPOSED→GATES PASSED→QUEUED→FILLED | — |
| HOLD HPE | 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.
fills: BUY 9.7909 MRK @ 149.18
AI-generated. All quantitative claims traced to the published fact pack. P07 is a wide-universe, no-style experimental mandate. NAV is 99,896.87 (pf.nav), 66.54% cash (pf.cash_pct), with 6 held names each near 4-6% weight (pos.*.weight_pct) and 9 free position slots (pf.position_slots_free). All 6 holdings were opened today (pos.*.days_held=0), so this is a fresh book with headroom. Total return is essentially flat (-0.10%, pf.total_return_pct) and drawdown trivial (0.58%, pf.drawdown_pct). No pending orders (pf.pending_order_count). Since the task is rank_and_explain of the eligible set with realistic costs, I focus on high-conviction, liquid, positive-FCF trend names that would diversify away from the current semis/industrials tilt (AMAT, LRCX, GE, FDX, JBHT, FTNT). Candidates screened on strong 252d momentum with confirmed 5-yr FCF and deep liquidity: HPE (r252 172.31%, r20 28.13%, …
| Proposal | Conviction | Lifecycle | Codes |
|---|---|---|---|
| BUY HPE | 3 | PROPOSED→GATES PASSED→QUEUED→FILLED | — |
| BUY PANW | 3 | PROPOSED→GATES PASSED→QUEUED→FILLED | — |
| BUY RTX | 3 | PROPOSED→GATES PASSED→QUEUED→FILLED | — |
| BUY MRK | 2 | PROPOSED→GATES PASSED→QUEUED→FILLED | — |
| HOLD AMAT | 3 | PROPOSED→GATES PASSED→NO ORDER HOLD is a decision not to trade — no order is created | — |
| HOLD GE | 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.
fills: BUY 102.0918 HPE @ 59.31 · BUY 15.5979 PANW @ 384.17 · BUY 26.8817 RTX @ 223.02 · BUY 29.4160 MRK @ 135.01
AI-generated. All quantitative claims traced to the published fact pack. Fresh 100% cash portfolio (pf.cash_pct=100, pf.position_count=0), 15 slots free (pf.position_slots_free), high-risk unconstrained mandate. Task is to select equities likely to outperform SPY, whose trailing return is r252=21.04% (px.SPY.ret_252d). I favor names combining durable long-term momentum, sustained free-cash-flow generation (fcf_positive_years_of_last_5=5), and positive intermediate momentum, while avoiding overheated single-day-move risk. My picks: AMAT (ret_252d 183.65%, ret_60d 29.25%, FCF 5/5), LRCX (ret_252d 220.11%, ret_60d 21.24%, FCF 5/5), FDX (ret_252d 82.77%, ret_20d 6.65%, FCF 5/5), JBHT (ret_252d 97.66%, FCF 4/5), FTNT (ret_252d 110.83%, ret_60d 30.78%, FCF 5/5), GE (ret_252d 28.97%, ret_60d 26.10%, FCF 5/5). All are large-cap and highly liquid (ADV well above any sizing need vs pf.nav 100k). …
| Proposal | Conviction | Lifecycle | Codes |
|---|---|---|---|
| BUY AMAT | 3 | PROPOSED→GATES PASSED→QUEUED→FILLED | — |
| BUY LRCX | 3 | PROPOSED→GATES PASSED→QUEUED→FILLED | — |
| BUY FDX | 3 | PROPOSED→GATES PASSED→QUEUED→FILLED | — |
| BUY JBHT | 2 | PROPOSED→GATES PASSED→QUEUED→FILLED | — |
| BUY FTNT | 3 | PROPOSED→GATES PASSED→QUEUED→FILLED | — |
| BUY GE | 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 11.2246 AMAT @ 498.67 · BUY 17.8036 LRCX @ 331.69 · BUY 17.6809 FDX @ 339.40 · BUY 14.1683 JBHT @ 280.18 · BUY 36.2669 FTNT @ 165.93 · BUY 16.6371 GE @ 362.66
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 · TIGHTEN_STOP · FLAG_THESIS_BREAK
At most 6 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 P07-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 | 35.0% | 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 |
| Leverage | prohibited | gate 1 — proposal validation |
| Limit | Value | Enforced by |
|---|---|---|
| Maximum positions | 15 | gate 3 — BREACH_MAX_POSITIONS (portfolio limit check) |
| Minimum new position | 2.0% | gate 2 — size_order |
| Maximum order as % of ADV | 0.5% | gate 2 — size_order |
| Limit | Value | Enforced by |
|---|---|---|
| Monthly loss limit | 15.0% | gate 3 — HALT_MONTHLY_LOSS_LIMIT |
| Single-day loss alert | 6.0% | gate 3 — alert |
| Limit | Value | Enforced by |
|---|---|---|
| Stale-data halt | 36 hours | gate 3 — HALT_STALE_DATA |
| Limit | Value | Enforced by |
|---|---|---|
| At −12.0% drawdown | alert, publish_commentary | gate 3 — drawdown ladder |
| At −20.0% drawdown | alert, pause_new_positions_days:10, mandatory_deep_review | gate 3 — drawdown ladder |
| At −30.0% drawdown | alert, pause_new_positions_days:30, publish_commentary | gate 3 — drawdown ladder |
| At −45.0% drawdown | suspend_portfolio, graveyard_review | gate 3 — drawdown ladder |
| Limit | Value | Enforced by |
|---|---|---|
| Max trades per month | 20 | entry block — PAUSE_TURNOVER_CAP_REACHED (never blocks an exit) |
| Min holding period days | 5 | 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 factpack hash mismatch | true | gate 3 — circuit breaker |
Disclosures specific to this portfolio
These render on the page itself rather than in a footer, because without them the numbers actively mislead.
- The instrument selection in this portfolio is made by a large language model with no style mandate constraining it. Position sizes, stop levels and every risk limit are computed by deterministic code the model cannot see or influence.
- This portfolio is labelled EXPERIMENTAL from inception. It is a test of whether a language model can select equities at all, and it may fail. It was labelled experimental before any result was known, not afterwards.
- The model identity and prompt version are published, and any change to either is recorded as a MODEL_CHANGE event in the audit chain. Comparing results across a model change without accounting for it would be comparing two different systems.
- Its deterministic baseline shadow is published alongside it. If a five-line momentum rule beats this portfolio, that comparison appears on the same page and is not footnoted away.
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
Every other mandate on this platform encodes a human thesis and asks the model to work inside it. This one removes the thesis. The universe is wide, the holding period is unconstrained, and no factor, sector or style is preferred by the rules. What remains binding is risk: position caps, a drawdown ladder, turnover limits and stops, all deterministic. If the model has any selection skill, this is where it shows up; if it has none, this is where that becomes undeniable, and the record will say so either way.
Review schedule
| Job | Cron | Timezone | Makes a decision |
|---|---|---|---|
| weekly selection | 0 12 * * SUN | America/New_York | yes |
| monthly review | 0 12 1 * * | America/New_York | yes |
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/P07_claude_discretionary.yaml · human rulebook: docs/portfolios/P07_claude_discretionary.md · effective from 2026-08-06 (wall clock) · record starts 2026-08-13 (pricing session) · payload 06ec491b8950…