Paper Trader — tempo

Mandate

A systematic momentum book that separates the two decisions most strategies fuse. Which names to own is cross-sectional momentum, the same blended 12-1 / 6-month / 3-month score the Fable account uses, top eight with a trend filter and hysteresis so winners are not churned at the rank edge. How MUCH of them to own is a separate, deterministic answer: the whole book is geared to a 22% volatility target, so exposure rises toward a 1.90x ceiling when the market is calm and falls to cash when it is not. The gearing uses the higher of a 20-day and a 60-day volatility estimate, which makes it deliberately asymmetric — the book de-levers as soon as the fast measure moves and cannot re-lever until the slow one agrees. Idle capital sits in cash rather than Treasuries, and the only diversifier is gold, both for the same measured reason: this contest credits no dividends, so a bond fund would hand back its entire return.

How it was decided

Eric's mandate of 2026-09-01 — 'I want AI to be the creator of the 5th strategy, your sole goal is to beat the other strategies over 1, 3, 5 and 10 year horizons.' Designed by Claude Opus 5 and chosen by measurement rather than argument: eight strategy families were built and raced against backtested reconstructions of the other books, through one engine on one dataset, over two windows so the answer could not be fitted to a single regime. The families that lost are published beside the one that won.

Symbol	Market Value	Unrealized
GLD	$14,425	-0.00%
INTC	$11,483	+12.38%
AMD	$11,406	+11.62%
CAT	$10,487	+2.63%
CSCO	$10,328	+1.08%
GOOGL	$9,948	-2.65%
MRK	$9,941	-2.71%
LLY	$9,871	-3.40%
TGT	$9,769	-4.40%

FRTB Capital · standardised approach · 2026-09-10

What a bank would have to hold in capital against this exact book, under the Basel market-risk rules (BCBS d457 (MAR20-MAR23, MAR32-MAR33)). Recomputed every session from live positions; nothing here is visible to the agent while it trades.

Capital requirement

$35,893

SbM + DRC + RRAO

Of equity

35.4%

capital / portfolio value

Market-risk RWA

$448,664

capital × 12.5

Overstated. 1 name(s) (GLD) could not be classified from reference data and fell to the "other sector" bucket at a 70% risk weight — the regulation's own fail-closed rule. The number above is safe-direction wrong.

Components, buckets, and why DRC is the interesting line

Component	Charge	Share
SbM delta · high correlations bind	$21,246	59.2%
SbM vega · no optionality in the book	$0	0.0%
SbM curvature · linear payoff	$0	0.0%
DRC — jump to default · LGD 100%	$14,648	40.8%
RRAO · no exotic underlyings	$0	0.0%
Total capital requirement	$35,893	100%

Equity buckets · MAR21.72

Bucket	Risk weight	Names	Net value	K_b
8	50%	AMD, CSCO, INTC	$33,224	$12,232
11	70%	GLD	$14,425	$10,098
5	30%	LLY, MRK, TGT	$29,570	$6,529
6	35%	CAT, GOOGL	$20,431	$5,794

Why the second-biggest line is the interesting one. The DRC is jump-to-default: the issuer disappears overnight. Equity has no recovery, so Basel sets loss-given-default at 100% and charges an unrated name 15% of its market value — 41% of the requirement here, and nothing about hedging, forecasting or diversification reduces it. That the high correlation scenario binds is itself a readout: a long-only book is dearest when correlations rise, a hedged one when they fall.

Value at Risk · historical simulation · 2026-09-10

The loss this book exceeds on the worst few days in a hundred, measured by replaying 501 days of its own constituents' returns through today's positions. Recomputed every session; nothing here is visible to the agent while it trades.

VaR 99% · 1 day

$2,928

worst 1 day in 100

Of equity

2.88%

loss / portfolio value

ES 97.5%

$3,171

average of the tail beyond

VaR 99% · 10 day

$7,495

regulatory horizon

Quantiles, component VaR, the backtest, and what VaR will not tell you

Confidence	Historical	Of equity	Parametric	Gap	Tail pts
95%	$1,888	1.86%	$2,223	−15.1%	25
99%	$2,928	2.88%	$3,144	−6.9%	5
ES 97.5%	$3,171	3.12%	the average of the tail, not its edge

Why the 10-day figure is measured, not scaled. The textbook shortcut multiplies the one-day VaR by √10, which assumes daily returns are independent. Here that gives $9,259 against a measured $7,495 — 23.5% too high. Overlapping windows cost nothing to compute and need no such assumption.

Component VaR · at 99% · sums to the total

Name	Market value	Weight	Component	Share
INTC	$11,488	11.8%	$856	27.2%
AMD	$11,412	11.7%	$797	25.4%
CAT	$10,487	10.7%	$378	12.0%
GOOGL	$9,945	10.2%	$225	7.2%
CSCO	$10,329	10.6%	$225	7.1%
TGT	$9,769	10.0%	$186	5.9%
LLY	$9,871	10.1%	$184	5.8%
GLD	$14,426	14.8%	$178	5.7%

These are allocations, not a ranking. Each name's number is the dollars of VaR it is responsible for, and they sum exactly to the total — which is what lets one go negative: a position that offsets the rest of the book reduces total risk, and no ranking by position size would ever show it.

The part that makes it a measurement. Over 251 out-of-sample days the 99% threshold was breached 1 time(s) against 2.5 expected — Kupiec p = 0.276, verdict consistent with the model, Basel traffic light green. The traffic light only punishes too many breaches; Kupiec is the test that also catches a model being too conservative, which is why both are shown. Each day's threshold is fitted on the prior 250 days only, so it is never tested on data it has already seen.

Not yet. VaR on the account's own equity curve needs more sessions: 11 daily observations, need 20.

What VaR will not tell you. It names a threshold and says nothing about how far past it a bad day goes — make the tail twice as deep without moving the cutoff and VaR does not move at all. That blind spot is why Basel replaced it with Expected Shortfall for capital, and why ES is quoted beside it above.

Counterparty Risk · SA-CCR · 2026-09-10

Market risk is symmetric — the price moves, you win or you lose. Counterparty exposure is one-sided: the market value clipped at zero, so it exists only when a trade has moved in your favour and the other side still owes you something. A fully-paid share bought on an exchange has none of that. You paid cash, it cleared, it settled, and nobody owes you anything — so the charge below is zero because the trade is over, not because nothing was measured.

SA-CCR EAD

α × (RC + PFE) · 0 derivative(s)

CVA capital

spread risk, not default

Settlement in flight

T+1

Custodial concentration

100%

one broker, everything

The derivation: SA-CCR terms, what was excluded, settlement, leverage and concentration

SA-CCR term	Value
Derivative trades in the netting set	0
Replacement cost · max(V − C, 0)	$0
Add-on aggregate · supervisory factors	$0
PFE multiplier · floored at 5%	1.0000
PFE · multiplier × add-on	$0
α · CRE52.1	1.4
Exposure at default	$0
CVA capital · CRE55, BA-CVA reduced	$0

Why · what never reaches SA-CCR

Kind	Positions	Market value	Reason
cash equity long	9	$97,677	fully-paid long share: bought for cash, centrally cleared and settled — no open obligation, so no counterparty exposure

Settlement is the one that is genuinely live. US equities settle T+1, so a fill from this session is a commitment against a leg that has not been delivered yet: $0 in flight, $0 past due, capital charge $0. Basel charges a delivery-versus-payment trade only once it is five business days overdue (CRE70), so in-flight exposure is disclosed at a zero charge rather than hidden at zero exposure.

Leverage · capability vs utilisation

Provisioned	Margin debit	Short value	Gross	Net
4× · shorting on · options L3	$0	$0	0.96×	0.96×

Fully funded. This is what makes the zeros above readable as a fact about today's positions rather than about the account's permissions: the book is provisioned for 4× margin, shorting and options, and is currently using 0.0% of the first and 0.0% of the second. The first short or written option moves the exposure above off zero on its own.

The counterparty that does exist. Alpaca (paper) holds $3,828 of cash and $97,677 of securities — 100% of the book, by construction. Not an SA-CCR figure and not a capital charge, but a counterparty report that omitted the only counterparty there is would be worse than no report at all.

What this is really measuring. Alpaca simulates the fills, so there is no real counterparty behind these positions. What is measured is the SHAPE of the book — the counterparty profile it would carry if the trades were real.

Latest Review · 2026-09-10

Trades

No trades this session — held all positions.

Agent Reasoning

Not a rebalance day — book held as-is, no trades executed. TEMPO rebalances on a 21-calendar-day cycle (last: 2026-09-02), so today's action is to hold per the plan, not to trade turnover into the book. Book: $101,493 equity, 9 positions plus $3,828 cash. Winners are the semis (INTC +12.4%, AMD +11.6%) and CAT (+2.6%); laggards are TGT (-4.4%), LLY (-3.4%), MRK (-2.7%), GOOGL (-2.6%), with GLD flat. Gearing looks roughly fully invested (~96% in equities/gold, no leverage drawn against the $288.8k buying power). Market context: Broad tape is soft today — SP500 -0.46%, Nasdaq -0.62%, Dow -0.28% — with VIX up 7.7% to 17.7 (still well below the 30 defensive / 40 freeze thresholds, so regime is normal). Drawdown from HWM is 1.4%, nowhere near the 30% breaker. Action taken: none. No closes, trims, or buys — per contract, non-rebalance days mean hold. No vetoes needed (no news-driven fact breaks in the book), and no orders were submitted to the risk desk today.

2026-09-09 $103,022.86 — 0 trades

No trades this session — held all positions.

TEMPO — 2026-09-09: Not a rebalance day, holding as-is. Today is not a rebalance day (last rebalance 2026-09-02, cycle is 21 calendar days), so per the plan no trades are made. Book stands at $102,992 equity across 9 names, led by INTC (+15.9%) and AMD (+13.7%), with GOOGL, LLY, TGT and MRK modestly negative; overall gearing/exposure unchanged from the prior rebalance. Markets were soft today (S&P -0.24%, Nasdaq -0.32%, Dow -0.60%) with VIX ticking up to 16.2 (+2.8%) — still well below the 30 defensive / 40 freeze thresholds, so no regime-driven action is triggered. No trades executed, no vetoes needed, nothing sent to the risk desk.

2026-09-08 $102,055.85 — 0 trades

No trades this session — held all positions.

TEMPO — 2026-09-08: Not a rebalance day. No trades executed. Book stands at $102,012.65 equity across 9 names (GLD 14.2%, INTC 11.3%, AMD 10.7%, CAT 10.6%, CSCO 10.1%, MRK 9.9%, GOOGL 9.9%, TGT 9.8%, LLY 9.7%), cash $3,828. Winners since entry: INTC +12.4%, AMD +6.9%, CAT +5.9%; laggards: LLY -3.2%, TGT -1.8%, GOOGL -1.1%, MRK -0.7%, GLD/CSCO roughly flat. Broader market is soft today (S&P -0.39%, Nasdaq -0.43%, Dow -0.83%) with VIX at 15.4, well below the 30 defensive threshold, so no regime-driven resizing applies. Next scheduled rebalance is 21 calendar days from 2026-09-02. Per the execution contract, holding as-is is the plan — no closes, trims, or buys today, and no veto conditions present (no fraud/halt/delisting/restatement news flagged on any held name).

2026-09-02 $99,990.71 — 9 trades

Action	Symbol	Amount
BUY	GLD	$14,426
BUY	INTC	$10,218
BUY	AMD	$10,218
BUY	CAT	$10,218
BUY	TGT	$10,218
BUY	CSCO	$10,218
BUY	MRK	$10,218
BUY	GOOGL	$10,218
BUY	LLY	$10,218

Session Summary — TEMPO 2026-09-02 Gearing & vol: Book volatility 20.4% vs 22% target → gearing 0.99x (well inside the 1.90x cap). Regime is calm (VIX 15.4, well below the 30/40 defensive/freeze thresholds), so no size throttling applied. Eligibility: 41 of 80 names scored; today's plan carried 9 positions (8 equal-weight ranked names + GLD as the diversifying/defensive rank). Veto review: Checked news on all 9 planned names. Nothing rose to fact-based veto criteria (no fraud, halts, delistings, or closed-gap acquisitions). Note for the record: CSCO disclosed a "Fire Ant" cyber-espionage campaign targeting its IOS XR routers — a risk item worth monitoring, but not an investability-breaking fact, so the order proceeded per the no-discretion mandate. Executed — all 9 orders filled, in plan order: | Symbol | Target $ | Filled | |---|---|---| | GLD | 14,425.79 | ✅ | | INTC | 10,218.27 | ✅ | | AMD | 10,218.27 | ✅ | | CAT | 10,218.27 | ✅ | | TGT | 10,218.27 | ✅ | | CSCO | 10,218.27 | ✅ | | MRK | 10,218.27 | ✅ | | GOOGL | 10,218.27 | ✅ | | LLY | 10,218.27 | ✅ | Rejections: None. All orders cleared the risk desk (position sizes ~10–14.4% of equity, all under the 25% position / 22% order caps; well within the 0/14 daily buy count). End state: Equity $99,978.74, cash $4,057.04 (~4.1%), fully deployed per plan at 0.99x gearing. No closes/trims were needed — book started flat. No discretionary adjustments made.