HYPOTHETICAL PERFORMANCE These are paper-trading portfolios. No client money is invested, no orders are routed to any venue, and no result shown here was achieved with real capital. Hypothetical results have inherent limitations and do not reflect the effect of real order flow on price.
Transparent AI Investment Platform
Home / portfolios / P07

Claude Discretionary

P07experimentalhigh riskrulebook v1.2.1rank and explain
EXPERIMENTAL. This portfolio is not experimental because of the risk it takes; it is experimental because of what it is testing. Every other mandate here hands the model a thesis to work inside. This one removes the thesis and lets the model select freely, to find out whether a language model can pick equities at all. The answer may well be no, and that is a publishable result. It was labelled experimental before any result was known, not afterwards.

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.

Follow Claude Discretionary's trades →Decisions post to the channel when they're made — before settlement, refusals included.

Track record

Total return
+0.00%
net of modelled costs
Max drawdown
−0.00%
Days live
0
1 observations
Cost drag
0.00%
$0 in explicit fees
Sharpe
withheld
below 60 observations
Gross return
0.00%
before costs

Fewer than two NAV observations. No statistics are meaningful yet.

Starting capital
$100,000own work — never restated
Benchmarks
SPY · RSP, QQQ, P02_AI_SWING_TRADER
Mandate hash
d46cec952b8f5c68b2a48979296ea777c5da966c8880b659fbb54db0374fee7e

Recent decisions

Every run, including the ones that traded nothing: the committed fact-pack hash (written to the audit chain before the model was called), the model'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.

2026-08-09 12:35Zpost closeabstainedclaude-sonnet-4-5

The fact pack for P07 Claude Discretionary is structurally deficient for decision-making. As of 2026-08-06, the portfolio holds 100% cash (pf.cash_pct = 100 pct, pf.cash = 100,000 USD) with zero positions (pf.position_count = 0 count) at inception (pf.starting_capital = 100,000 USD, pf.total_return_pct = 0 pct). However, the ELIGIBLE SYMBOLS list contains zero tickers, making it impossible to propose any BUY or other equity actions. The mandate requires a broad liquid universe for discretionary selection, but none has been provided. Without price data, fundamental metrics, sector information, volatility measures, or any market context beyond portfolio ledger entries, no investment thesis can be evaluated. The absence of eligible symbols is a critical data gap: I cannot rank opportunities that do not exist in the fact pack. This is not a market condition requiring patience; it is a struct

fact pack 5f8864510b8ac754… · run run_0c2fdc82b18b4f16

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.

It may propose

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.

It cannot
  • 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 either 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.

exposure
LimitValueEnforced by
Maximum gross exposure100.0%gate 2 — size_order
Maximum single sector35.0%gate 2 — size_order
permissions
LimitValueEnforced by
Shortingprohibitedgate 1 — proposal validation
Derivativesprohibitedgate 1 — proposal validation
Marginprohibitedgate 1 — proposal validation
Leverageprohibitedgate 1 — proposal validation
sizing
LimitValueEnforced by
Minimum new position2.0%gate 2 — size_order
Maximum order as % of ADV0.5%gate 2 — size_order
loss limits
LimitValueEnforced by
Monthly loss limit15.0%gate 3 — HALT_MONTHLY_LOSS_LIMIT
Single-day loss alert6.0%gate 3 — alert
data integrity
LimitValueEnforced by
Stale-data halt36 hoursgate 3 — HALT_STALE_DATA
drawdown ladder
LimitValueEnforced by
At −12.0% drawdownalert, publish_commentarygate 3 — drawdown ladder
At −20.0% drawdownalert, pause_new_positions_days:10, mandatory_deep_reviewgate 3 — drawdown ladder
At −30.0% drawdownalert, pause_new_positions_days:30, publish_commentarygate 3 — drawdown ladder
At −45.0% drawdownsuspend_portfolio, graveyard_reviewgate 3 — drawdown ladder
turnover
LimitValueEnforced by
Max trades per month20entry block — PAUSE_TURNOVER_CAP_REACHED (never blocks an exit)
Min holding period days5entry block — PAUSE_TURNOVER_CAP_REACHED (never blocks an exit)
circuit breakers
LimitValueEnforced by
Halt trading if price gap unexplained pct25gate 3 — circuit breaker
Halt trading if factpack hash mismatchtruegate 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

Cost profile
zero_commission_us
Fill convention
vwap_window
Decision → order latency
60s
VWAP window
15 minutes

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

JobCronTimezoneMakes a decision
weekly selection0 12 * * SUNAmerica/New_Yorkyes
monthly review0 12 1 * *America/New_Yorkyes

Published on a fixed, regular schedule. Never event-triggered — no "market is crashing, sell now" alerts, deliberately.

Machine-readable mandate: config/portfolios/P07_claude_discretionary.yaml · human rulebook: docs/portfolios/P07_claude_discretionary.md · effective from 2026-08-06 · payload b618c290568f

Follow the record.Every decision, fill and refusal, as it is published — including the ones that lose money.Join on Telegram →

Crypto market data Powered by CoinGecko · Logos provided by Logo.dev · Company logos identify holdings only and imply no endorsement.