Nine trades, five winners, four losses, +1.21R net at the TP1 baseline. Three winners ran the full ladder to TP3 on Mon and Tue, then four Wed-Fri stops trimmed
SkyAnalyst is not one AI trader. It is four specialist agents — each with its own data pipeline, each maintaining state between evaluations, and each required to agree before a position is sized. They don’t chat in prose. They write structured messages to a shared state object that each reads on every evaluation cycle.
Nine trades, five winners, four losses, +1.21R net on the TP1 baseline. That is the scorecard for Apr 13-19, 2026, and it is the median weekly outcome at our published expectancy. Cumulative equity climbed from $100,000 to $107,358 by Tuesday afternoon, gave back to $99,358 by Friday afternoon on a four-trade losing streak, then closed the week at $102,418 on the Friday US30 long that broke the streak. The three TP3 winners that carried the early arc are published in parallel as case studies: the Apr 13 NAS100 long ran +2.22R to TP3, the Apr 13 EURUSD long ran +3.15R, and the Apr 14 XAUUSD long ran +2.84R. The companion drawdown report walks the four losing trades. Last week's recap sits at the Apr 6 recap; March's monthly recap covers the longer window.
Mon Apr 13 produced three trades inside 60 minutes, all winners. NAS100 Long at 14:21 UTC ran a bullish pullback to TP3 for +0.71R at the TP1 baseline. US30 Short at 14:49 UTC ran a rejection at the 47,712 to 47,764 resistance cluster to TP1 for +1.00R. EURUSD Long at 15:20 UTC ran a pullback buy at structure to TP3 for +1.15R at baseline. Monday closed +2.86R cumulative, with equity at $105,715.
Tue Apr 14 opened with the third TP3 winner. XAUUSD Long at 14:47 UTC ran a pullback to a breakout/retest zone to TP3 for +0.82R at baseline. Equity peaked at $107,358. Forty minutes later, EURUSD Long at 15:27 UTC on a pullback to session support stopped at -1R when the support shelf failed inside the first hour. Tuesday closed +2.68R cumulative.
Wed Apr 15 was a zero-trade day. Thu Apr 16 brought a NAS100 Short at 14:31 UTC on a VWAP rejection that stopped at -1R. Fri Apr 17 brought three trades. EURUSD Long at 14:29 UTC stopped at -1R. XAUUSD Long at 15:19 UTC stopped at -1R, and equity touched the trough at $99,358. Six minutes later, US30 Long at 15:25 UTC on a bullish pullback to micro-support cleared confluence and ran to TP1 for +1.53R. Friday closed at $102,418.
| Date | Time | Instrument | Dir | Model | Setup | Grade | R | $ Sim | Result | Details |
|---|---|---|---|---|---|---|---|---|---|---|
| Apr 13 | 14:21 UTC | NAS100 | Long | Claude Opus 4.6 | NAS100 Bullish Pullback Long | C+ | +0.71R | +$1,416 | TP3 hit | - |
| Apr 13 | 14:49 UTC | US30 | Short | Claude Opus 4.6 | Short Rejection at 47,712-47,764 Resistance Cluster | C+ | +1.0R | +$2,000 | TP1 hit | - |
| Apr 13 | 15:20 UTC | EURUSD | Long | Claude Opus 4.6 | EURUSD Pullback Buy at Structure | C+ | +1.15R | +$2,299 | TP3 hit | - |
| Apr 14 | 14:47 UTC | XAUUSD | Long | Claude Opus 4.6 | XAUUSD pullback to breakout/retest zone | B | +0.82R | +$1,643 | TP3 hit | - |
| Apr 14 | 15:27 UTC | EURUSD | Long | Claude Opus 4.6 | Buy EURUSD on Pullback to Session Support | C+ | -1.0R | -$2,000 | Stop hit | - |
| Apr 16 | 14:31 UTC | NAS100 | Short | Claude Opus 4.6 | VWAP Rejection Short | C+ | -1.0R | -$2,000 | Stop hit | - |
| Apr 17 | 14:29 UTC | EURUSD | Long | Claude Opus 4.6 | EURUSD Pullback Long | C+ | -1.0R | -$2,000 | Stop hit | - |
| Apr 17 | 15:19 UTC | XAUUSD | Long | Claude Opus 4.6 | Bullish Pullback to NY Session Support | C+ | -1.0R | -$2,000 | Stop hit | - |
| Apr 17 | 15:25 UTC | US30 | Long | Claude Opus 4.6 | Bullish Pullback to Micro-Support (Primary) | C+ | +1.53R | +$3,060 | TP1 hit · ★ Trade of the week | - |
Dollar figures are simulated on a $100,000 account at 2% risk per trade. Actual subscriber P&L varies with account size. Past performance is not a guarantee of future results.
The week's recurring pattern was front-loaded asymmetry, then mean reversion of the recap signal. Three TP3 winners landed inside the first 26 hours. Four consecutive losses followed. The Friday US30 long broke the streak at the trough.
Inside the nine trades, US30 carried the winners on direction-agnostic structure reads, while EURUSD split 1-2 across pullback longs at three different support zones. US30 netted +2.53R; EURUSD netted -0.85R.
The Apr 13 NAS100 long, the Apr 13 EURUSD long, and the Apr 14 XAUUSD long all ran the full TP1 to TP3 ladder. Each cleared confluence on a different instrument with no shared regime tag. The Cross-Asset Agent did not throttle any of the three. Three TP3 winners inside 26 hours is variance landing on the right tail.
The Monday decision to take three trades inside 60 minutes across NAS100, US30, and EURUSD is the cleanest cross-asset judgment of the week. Three different instruments, three different setup families, all cleared their own confluence reads independently. Two of the three ran to TP3.
The Friday decision to take a US30 long six minutes after the XAUUSD long had stopped is the trade that defined the week's net. The four-trade losing streak had pulled equity to $99,358 and the drawdown gate fired. The gate held threshold steady at 55 percent. The US30 setup scored above the threshold the morning's losers had used. The trade ran to TP1 for +1.53R and pulled the week green.
The Thursday NAS100 short at 14:31 UTC was the loss that opened the streak. VWAP rejection short at C+ confluence, macro gated bearish-equities on bid bonds. The trade stopped inside the hour as NAS100 reclaimed VWAP through the New York cash open.
SkyAnalyst runs multiple foundation models in parallel across its four-agent system. When two models trade the same instrument in the same week, the results are directly comparable. This is that comparison.
Same signals, same risk framework, different foundation model.
EURUSD took three trades for 33.3 percent win rate and -0.85R net. The Apr 13 pullback long ran to TP3 for +1.15R at baseline. Tuesday and Friday entries on the same setup family stopped on session-support failures inside the first hour each.
All EURUSD this week →XAUUSD took two trades for 50 percent win rate and -0.18R net. The Apr 14 pullback to breakout/retest ran to TP3 for +0.82R. The Friday long stopped on a buyer-stack sweep the volume model under-weighted.
All XAUUSD this week →US30 took two trades for 100 percent win rate and +2.53R net. The Apr 13 short at 47,712-47,764 resistance ran to TP1 for +1.00R. The Apr 17 long at micro-support broke the four-trade streak and ran to TP1 for +1.53R, the largest TP1-baseline winner of the week.
All US30 this week →NAS100 took two trades for 50 percent win rate and -0.29R net. The Apr 13 bullish pullback long ran to TP3 for +0.71R. The Apr 16 VWAP rejection short stopped as the index reclaimed VWAP through the cash open.
All NAS100 this week →US500 was inactive. The index consolidated with no patterns scoring above threshold.
All US500 this week →Win of the week: US30 Long · +1.53R
All four losses cleared the published confluence threshold at trigger. The Tuesday EURUSD long was a clean session-support read; the Thursday NAS100 short was a textbook VWAP rejection; the Friday XAUUSD long was the highest-grade loss, with three agents aligned on a bullish-gold regime that had held two sessions.
Nothing in the entries themselves. All four share a regime-shift sensitivity the exit logic does not address: the local tape repriced inside the trade lifecycle, and the stop was the only exit. The Friday XAUUSD loss surfaces a specific item: the volume model under-weighted a buyer stack built above the support shelf earlier in the day without recent price interaction.
Each trade risks +$2,000 (1R). The system's actual scale-out behavior may differ, see disclaimer.
| Scenario | R-multiple | Profit on $100k |
|---|---|---|
| Window netActual | +1.21R | +$2,420 |
The honest reading is that the week front-loaded its asymmetry, gave most of it back across a four-trade losing streak, and closed green by a single trade on the Friday US30 long. Five winners, four losses, 55.6 percent win rate, +1.21R net. The median outcome at our published expectancy.
The architecture point is the Friday US30 long at 15:25 UTC. The trade was sized identically to Monday's first NAS100 entry and scored above the same 55 percent threshold the morning's losers had cleared. A discretionary trader on a four-trade losing streak would have widened the floor or sat the afternoon out. The system did not. The drawdown gate fired and held threshold steady; the rules ran as written. The +1.53R that broke the streak ran on the same arithmetic that produced the four losers.
The TP1-baseline reading of +1.21R undercounts the broker fills on three winners. Subscribers running scale-out at TP1, TP2, and TP3 booked more on the same ladder. From the SkyAnalyst Team.
The Friday XAUUSD long is the most actionable loss in the cluster. Sub-hour volume aggregation under-weights orders that have rested for hours when price has not interacted with them recently. A fix is in testing. Initial backtests show a 6 to 8 point reduction in confluence score on similar scenarios, which would have moved the XAUUSD setup below threshold. The other three losses do not share this artifact.
The three TP3 winners on Mon and Tue are not a tuning signal. The companion drawdown report walks the equity-curve impact in detail.
Three TP3 winners on Mon and Tue banked +3.68R cumulative by Tuesday afternoon. Four consecutive stops on Wed through Fri gave back -4R. The Friday US30 long at 15:25 UTC ran to TP1 for +1.53R and pulled the cumulative net to +1.21R.
Single-model windows occur naturally when one family's confluence math clears threshold and the other does not on the same setups. Nine trades is too small a sample to read model dispersion. The longer-window head-to-head lives in March's monthly recap.
Recap R-multiples use a TP1-baseline projection on every winner. The Apr 13 NAS100 long ran the full ladder, so the baseline reads +0.71R while the case study documents the full +2.22R TP3 ladder. Subscribers running scale-out booked closer to the case-study figure.
The gate fires when cumulative equity drops a configured percentage below a recent peak. It fired Friday afternoon after the XAUUSD stop pulled equity from $107,358 to $99,358. Once fired, it prevents the Trend Agent from lowering the confluence threshold. The Friday US30 long triggered on the same threshold the morning had used.
Sub-hour volume aggregation under-weights orders that have rested for hours without recent price interaction. A fix is in testing that reduces confluence score by 6 to 8 points on similar scenarios. Backtests show the XAUUSD setup would have moved below threshold.
Subscribers receive the same pre-trade AI analysis three minutes before entry.
We project the recap totals using a TP1 exit on every winning trade. This is the simplest baseline for comparing across periods. Traders running their own scale-out, trail, or TP2/TP3 hold strategies will see different totals. Dollar figures are simulated on a $100,000 account at 2% risk per trade. Actual subscriber P&L varies with account size and execution. Past performance is not a guarantee of future results.
Three losses, all at minus 1R. Net minus 3R for the loss-side ledger. Longest streak of 1. Original printed 4 losses and a streak of 2; the cancelled-trade fix dropped one phantom NAS100 row from Feb 26.
Seven trades, four winners, three losses, +1.21R net on a TP1 baseline. Original printed nine trades and +0.80R; the cancelled-trade fix dropped one paused NAS100 row from Feb 26. Corrected ledger.
Twenty-one trades, thirteen winners, eight losers, +4.41R net on a TP1 baseline. Original published as 24 trades and +6.64R; the cancelled-trade fix dropped 3 paused rows the dashboard never had.