XAUUSD Short on March 26 - Three TP3 Winners on the Same Tape
SkyAnalyst AI journal entry: XAUUSD Short on Mar 26, 2026 closed +2.83R on TP3. Full workspace view, decision log, and AI reasoning, unedited.
Before the trade, meet the system.
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. That’s what makes the system auditable — and it’s what this case study will show, step by step, on a specific setup the trend agent almost passed on.
The morning the macro tape priced gold against itself
US futures opened March 26 with the bearish-gold macro configuration printing fresh on every confirming indicator. 10Y yields at 4.364, above the 5-day EMA at 4.341 and above yesterday's high at 4.36, the rate-driver behind a heavy hand on gold. DXY at 99.765, above the 5-day EMA at 99.482 and above yesterday's high at 99.702, the dollar-strength channel. Oil at 100.91, above its 5-day mean and above yesterday's high, activating the negative-correlation pressure the Macro Agent had registered at minus 0.5. Three confirming readings, all fresh, all aligned in the bearish-gold direction.
The complication was VIX at 26.34, elevated above its 5-day EMA at 25.95. Elevated VIX typically supports safe-haven demand for gold, but the reading sat inside yesterday's range rather than spiking to new highs. The Macro Agent gated this as priced fear rather than accelerating fear. The dominant 10Y plus DXY pair overrode the VIX cross-check.
By NY open, the 60-minute structure on XAUUSD was firmly bearish. EMAs stacked bearish (price 4462 below EMA9 4472 below EMA21 4485), MACD below zero with histogram weakening on the corrective bounce, RSI 46.2 recovering from 34 oversold but still below 50. The 15-minute showed a corrective bounce maturing into the resistance cluster, RSI 56.9 mid-range with room in both directions. The 5-minute showed the bounce in its upper 2-standard-deviation VWAP band, RSI 60.9 approaching the upper end of neutral. The Trend Agent flagged the regime as TRANSITIONING with a REDUCE_SIZE recommendation. Setup grade printed C+.
The setup at 14:41 UTC was a VWAP / London-High Rejection short. Six minutes of waiting before the trigger explains how the Trend Agent reads a corrective bounce against a multi-level resistance cluster.
What the pattern is
The trader watches an instrument that has established a session-bearish bias on the higher timeframes (60-minute EMAs stacked bearish, MACD below zero, price below VWAP) and that has just printed a sharp directional impulse from a prior session, in this case London selling XAUUSD 128 points from the Tokyo high. NY opens with a corrective bounce, and the pattern triggers when 5-minute price tags a dense resistance cluster (session VWAP plus prior-session high plus higher-timeframe EMA), prints a rejection candle that closes inside the bearish range, and 5-minute RSI rolls back from the 60 cap. The systematic version requires the rejection to close, not just wick.
Why this works on a yields-up dollar-up tape
When 10Y yields and DXY break out together on the same morning, every counter-trend bounce in gold is a positioning move, not a reversal. The bounce takes price into the zone where short-term covering exhausts and structural sellers re-engage. Selling at VWAP plus prior-session-high plus EMA gives the trade three independent invalidation lines: a clean reclaim of all three flips the bias, but on a confirmed-bearish-tape morning each level has to be taken out separately, and that is rare inside the NY AM window.
Why this graded C+ rather than B
Two things kept the grade modest. The Macro Agent posted only 15 percent confidence on its bearish bias, the structural carry-and-real-yields thesis was clear but the agent did not register a fresh near-term catalyst. And the Trend Agent flagged TRANSITIONING strength with a REDUCE_SIZE recommendation, the corrective bounce had legitimate 5-minute momentum that could extend through 4472 toward 4485-4490 before reversing. Both agents agreed on direction, but neither registered high conviction. C+ means tradeable with reduced size, not headline-worthy on the setup card.
How the wait turned into the entry
The first five evaluations between 14:34 and 14:39 UTC ran 30 to 35 percent confidence, the bounce was extending and the rejection had not printed. Each cycle the system watched 5-minute price grind into the cluster, 5-minute RSI lift toward the 60 cap, and the structural shorts not yet engage. Then at 14:41 UTC the bounce stalled at 4467.48 against the London-high reference, the 5-minute candle printed a closing wick rejection at the cluster, and the next bar failed to close above 4468. Confluence math returned 62 percent on 6-of-6 confluence factors met (including both starred macro factors). Enter short at 4467.48, stop 4492, TP1 4445, TP2 4420, TP3 4398.
How the system reads this, dynamically not dogmatically
The VWAP-rejection short is one playbook of many. The same morning the Trend Agent had already entered a parallel short on US500 (which closed at +2.28R) and on EURUSD (which closed at +3.34R). On a different tape, with yields rolling over instead of breaking out, the same setup card on XAUUSD would have scored below threshold and the system would have skipped it. A long setup at 4468 (VWAP reclaim) was actively considered and rejected on the same evaluation cycle: Macro bearish, yields bearish for gold, DXY bearish for gold, 60-minute structure bearish. Only the 5-minute micro-structure supported it. Below threshold.
SkyAnalyst doesn't favor any single strategy. The confluence math picks the playbook each evaluation cycle and reads the tape first. Six waits across seven minutes, then one enter, then one hour and forty-one minutes to TP3. The four agents reading the tape in parallel each contribute a different lens. When they agree, we trade dynamically. When they do not, we sit out.
XAUUSD NY AM Session Analysis — March 26, 2026
1. Economic Calendar Gate
Unemployment Claims (8:30 AM ET): Already released. Actual 210K vs. Forecast 211K vs. Previous 205K. A marginal beat (1K below forecast), essentially in-line. Directional impact on gold: negligible/neutral. Claims ticked up from 205K prior but the miss vs. forecast is immaterial — no tradeable catalyst from this print.
President Trump Speaks (4:00 PM ET / 16:00 UTC): ~2 hours away. Medium impact, well outside our NY AM trading window. However, headline risk exists in the afternoon — any positions held into that window carry event risk. The Macro Agent flags this as high impact with partial pricing.
Calendar verdict: CLEAR to trade the NY AM session. No high-impact data pending within 30 minutes.
2. Macro Regime (Primary Filter)
| Cross-Asset Factor | Reading | Direction | Gold Impact |
|---|---|---|---|
| US 10Y Yield | 4.364 (above 5D EMA 4.341, above yesterday's high 4.36) | Rising | ⬇ Bearish gold |
| DXY | 99.765 (above 5D EMA 99.48, above yesterday's high 99.70) | Strengthening | ⬇ Bearish gold |
| VIX | 26.3 (above 5D EMA 25.94, elevated >25) | Elevated | Mixed — supports safe-haven but signals whipsaw risk |
| Breadth (NYAD) | Not available directly; US30 within range, no breakout | Inconclusive | Neutral |
| Oil | 100.91 (above 5D EMA, above yesterday's high) | Rising sharply | Confirming signal: risk-on commodity rally, not gold-specific |
Macro Classification: BEARISH GOLD
The dominant driver pair — 10Y yields rising + DXY strengthening — aligns in the bearish-gold direction. Both are printing above their respective 5-day EMAs and above yesterday's highs, indicating fresh momentum today. This is the highest-conviction macro configuration against gold.
The elevated VIX (26.3) introduces a complication: it typically supports safe-haven demand for gold. However, the VIX is within yesterday's range (not spiking to new highs), suggesting the fear is priced rather than accelerating. Oil's sharp rally aligns with the negative correlation the Macro Agent identified (-0.5 coefficient), adding a secondary bearish gold pressure.
Conviction: High on bearish macro direction. The 10Y/DXY alignment is gold's dominant headwind and both are confirming today.
3. Agent Signal Synthesis
Macro Analysis Agent
- Bias: Lean bearish (score -35, confidence 15%)
- Tradeability: Moderate (62/100) — not low enough to force a tier reduction, but the very low confidence (15%) is a red flag
- Bearish catalysts: Real yields at 43-year highs (+2.03%), oil-gold negative correlation active
- Risk events: Trump speech (~2h), UoM Sentiment (~20h)
- Assessment: Bearish bias aligns with the macro regime, but the extremely low confidence (15%) reflects uncertainty. Tradeability at 62 is passable — no forced tier reduction, but we respect the ambiguity by not over-sizing
Trend Authority Agent
- Direction: BEARISH (60% confidence)
- Strength: WEAK
- Regime: TRANSITIONING
- Recommendation: REDUCE_SIZE
- Key levels: R = 4489.67 (pivot/invalidation) | S = 4413.70 | VWAP = 4468.14
- Invalidation: Sustained reclaim above 4489–4494 flips bias neutral-to-bullish
- Context: 60m bearish, 15m showing corrective bounce (short-covering), expects two-way volatility around VWAP (4468) and pivot zone (4485–4490)
Agent Agreement Assessment
Both agents agree on bearish direction, though both with relatively low confidence (Macro 15%, Trend 60%). The agreement on direction is meaningful, but the weak confidence from both prevents a "strongest signal" classification. The Trend Agent's TRANSITIONING regime and REDUCE_SIZE recommendation reinforces trading smaller. Since both agents agree on direction (bearish) and the macro regime confirms, I maintain the bearish bias but acknowledge the reduced confidence warrants disciplined execution and tighter risk management.
4. Structural Framework
Key Reference Levels
| Level | Price | Significance |
|---|---|---|
| Yesterday's High | 4602.42 | Major resistance (far above) |
| Yesterday's Close | 4506.27 | Gap reference — price gapped down significantly |
| Daily Pivot | 4489.67 | Critical resistance / Trend Agent invalidation |
| 5D EMA | 4469.80 | Dynamic resistance |
| Session VWAP | 4468.14 | Key intraday resistance — capping rallies |
| Yesterday's Low | 4456.13 | Near-term resistance (broken below, now overhead) |
| Today's Daily Open | ~4476.62 | Gap-fill level |
| London Session High | 4468.67 | NY AM ceiling reference |
| 60m Fib 61.8% | 4462.83 | Bearish fib resistance |
| 15m Resistance | 4461.76 | Structural resistance |
| Current Price | ~4462 | Between London high and session supports |
| London Session Low | 4413.70 | NY AM floor reference |
| Today's Low | 4412.82 | Day low / major support |
| 60m Support | 4413.70 | Structural pivot low |
| Deeper Support | 4351.70 | Next major structure below |
Session Context
London sold off hard from the Asia/Tokyo high of 4542.30 down to 4413.70 — a massive 128-point London decline. NY has opened with a corrective bounce, rallying from the 4430 zone toward 4468. Price is now near the London session high (4468.67) and VWAP (4468.14), which is a critical decision zone.
5. Multi-Timeframe Analysis
60-Minute (Trend Bias)
- EMA alignment: Price (4462) below EMA9 (4472) below EMA21 (4485) — firmly bearish alignment
- RSI: 46.2 — neutral, recovering from 34 low. Corrective bounce territory, not yet overbought
- MACD: Line -21.9, below signal and zero — bearish, though histogram weakening (from -14 to -4.5) confirming the corrective bounce
- VWAP: Price just touched VWAP (4468.14) from below — first test of the day
- Verdict: Bearish trend with corrective bounce approaching key resistance at VWAP/EMA9
15-Minute (Swing Structure)
- EMA: Price (4462) above EMA9 (4443) but below EMA21 (4461) — still bearish structure, testing EMA21
- RSI: 56.9 — mid-range, room in both directions
- MACD: Below zero but histogram positive (4.25) — corrective bounce confirmed, not yet a trend reversal
- VWAP: Below at 4470 — price still under session VWAP on 15m
- Fibonacci: Bearish fib from 4452.08 to 4420.25: price has broken above the pivot high (4452.08), suggesting the corrective leg is extending
- Verdict: Short-covering rally testing overhead resistance cluster. The bounce is maturing but has not reversed the 60m trend
5-Minute (Entry Timing)
- EMA: 9 (4447) above 21 (4443) — bullish micro-structure since the NY open bounce
- RSI: 60.9 — approaching the upper end of neutral, momentum is with buyers short-term
- MACD: Positive and histogram expanding (1.3) — near-term buying pressure
- VWAP: Price at 4462 vs 5m VWAP 4440 — price is in the upper 2SD VWAP band, suggesting overextension from the intraday mean
- Session context: NY high is 4468.67 (matches London high), NY low is 4430.27. Price is near the top of the NY range
- Key observation: Price has rallied ~$50 from the London low (4413.70) to 4462 and is now approaching the confluence resistance zone of 4468 (VWAP) / 4469.80 (5D EMA) / 4472 (60m EMA9)
London Trap Reversal Check
NY opened and price initially dipped to 4430.27 in the first 30 minutes, then bounced. London's direction was bearish (sold from 4542 to 4413). NY is bouncing against London's direction and has reclaimed the 5m session VWAP. However, this bounce has NOT reclaimed the 60m VWAP (4468) — the critical test is happening right now. A failure at VWAP would confirm London's direction continues. A sustained hold above 4468–4470 would be a London trap reversal signal. Currently: not yet confirmed as a reversal — price is testing the boundary.
6. Setup Construction
Given the analysis, the primary opportunity is a short at the resistance cluster where the corrective bounce meets the dominant bearish trend. I also evaluated a long continuation but rejected it (see below).
Long Setup — REJECTED
A long above 4468 (VWAP reclaim) was considered but fails the confidence gate: Macro Agent bearish, 10Y yields bearish for gold, DXY bearish for gold, 60m EMA structure bearish. Only the 5m micro-structure and the bounce off London lows support it. This fails to meet the minimum 4-of-6 confluences including a starred factor.
Directional Bias: Bearish Volatility: High (VIX 26.3, 5m ATR expanding to $10.36, wide daily range of $111)
Setup #1: XAUUSD SHORT — VWAP / London High Rejection
Thesis: The corrective bounce from the London low is reaching exhaustion at a dense resistance cluster. The dominant 60m bearish trend, bearish macro regime (rising yields + strong DXY), and both agents' bearish alignment favor a resumption of selling from this zone. The Trend Agent explicitly flags VWAP (4468) as a cap on rallies.
- Entry Zone: 4466–4472 (between the London session high 4468.67 and the 60m EMA9 at 4472)
- Entry Trigger: Bearish rejection candle on the 5m chart within the entry zone — look for a wick above 4468 followed by a close below 4466, OR a failed retest of 4468 with a lower high on 5m. Must show clear rejection, not just a touch.
- Stop Loss: 4492.00 (above the daily pivot 4489.67 + $2.33 buffer ≈ 0.24x 5m ATR for slippage; this respects the Trend Agent invalidation at 4489.67 — a close above this flips the bias. The stop is placed just beyond invalidation to avoid premature exit in whipsaw conditions)
- Risk (entry at 4469): ~$23
- Targets:
- TP1 = 4445.00 (~1.04R) — NY session low zone / 5m Fib 50% support cluster / 15m pivot area
- TP2 = 4420.00 (~2.13R) — London session low zone / 15m S/R support at 4420.25
- TP3 = 4398.00 (~3.09R) — projected daily range extreme / 60m ATR 1.5x extension from VWAP
- R-Multiples: TP1 ≈ 1.0R, TP2 ≈ 2.1R, TP3 ≈ 3.1R
- Position Management: Close 40% at TP1, move stop to breakeven. Close 30% at TP2. Trail remaining 30% toward TP3 with a $10 trailing stop.
Quality Score: 6.5/10
Confidence: Medium — The setup has the right directional alignment and structural location, but the Trend Agent's WEAK strength and TRANSITIONING regime, combined with the low confidence from the Macro Agent (15%), prevent a High rating. The REDUCE_SIZE recommendation is respected.
Confluence Checklist
| # | Factor | Met? |
|---|---|---|
| ⭐ | Macro Agent bias aligns (lean bearish) | ✅ |
| ⭐ | 10Y yield direction supports short (rising) | ✅ |
| 3 | DXY direction supports short (strengthening) | ✅ |
| 4 | Trend Agent direction aligns (bearish, 60%) | ✅ |
| 5 | Price at key level (VWAP 4468 + London high + 60m EMA9) | ✅ |
| 6 | EMA alignment on 15m or 60m confirms | ✅ (60m firmly bearish) |
Result: 6 of 6 met, including both starred factors. This passes the confidence gate.
Risk Factors
- Corrective bounce momentum: The 5m is bullish with expanding MACD. Entry requires patience for a clear rejection signal — do not front-run
- VIX-driven whipsaws: Elevated VIX means wide intraday swings. The $23 stop accounts for this but expect noise
- Trump speech at 4 PM ET: Any leaked headlines could spike gold. Trail stops or close before 3:30 PM
- Short-covering can extend: If price breaks cleanly above 4472 (60m EMA9), the corrective move may push to 4485–4490 before reversing. This would test but not invalidate the setup if the stop holds
- Position sizing: Per the Trend Agent's REDUCE_SIZE recommendation, use 50–75% of normal risk allocation (e.g., 0.5–0.75% of equity rather than the standard 1%)
What Would Change the Outlook
- Bullish invalidation: A sustained close above 4490 on the 15m or 60m would flip the intraday bias to neutral-bullish. Long setups would then be evaluated on a pullback to 4470–4475
- For higher-confidence shorts: Need price to fail clearly at VWAP with a bearish engulfing on 5m, ideally with VIX ticking higher simultaneously
- For long setups to qualify: Would need 10Y yields to reverse lower AND DXY to weaken — currently both are moving against gold. A VIX spike above 28 with risk-off equities could override via safe-haven flows, but that's not the current condition
Bottom line: The macro and technical alignment favors shorts from the 4466–4472 resistance cluster, targeting a retest of the London session low. Execute with reduced size per Trend Agent guidance, require a clear 5m rejection trigger, and respect the 4492 stop as the line in the sand.
Decision log
14:34 UTC, 35 percent confidence, WAIT. NY had opened thirty minutes earlier and the corrective bounce off the 4413.70 London low was active, price at 4451 with 5-minute MACD positive and expanding. The structural premise was bearish but the trigger zone was 15 to 20 points overhead. Macro Agent confirmed lean-bearish at 15 percent confidence. Trend Agent posted bearish 60 percent with TRANSITIONING. Wait for the bounce to reach the cluster.
14:35 UTC, 30 percent confidence, WAIT. Price ticked to 4456, 5-minute RSI lifted toward 58. The bounce was still building, no resistance test yet. Confluence math dropped slightly because the LTF entry-zone factor remained inactive (price below the cluster). The macro and HTF inputs unchanged. Wait.
14:37 UTC, 35 percent confidence, WAIT. Price at 4461, brushing the 60-minute Fibonacci 61.8 percent resistance at 4462.83 and the 15-minute structural resistance at 4461.76. The first test of the cluster floor, but no rejection candle yet. The 5-minute body closed at 4461 with a small upper wick, body inside the cluster floor. Wait for a closing rejection deeper into the cluster or a clean tag of 4468.
14:38 UTC, 35 percent confidence, WAIT. Price retreated briefly to 4458 then ticked back up to 4463. The 5-minute showed indecision at the cluster floor, RSI 59.1. The Trend Agent registered the indecision as inconclusive: a tag of the floor without a tag of the ceiling (4468 VWAP) is not the trigger. Wait.
14:39 UTC, 35 percent confidence, WAIT. Price extended to 4466, the 5-minute RSI brushed 60. The bounce was approaching the VWAP test, the trigger condition was forming. Confluence math added the LTF entry-zone factor as conditional. The next candle would either confirm rejection at 4468 or extend the bounce through the cluster toward 4472-4485. Wait one more cycle.
14:41 UTC, 62 percent confidence, ENTER. Price stalled at 4467.48 against the London-high reference at 4468.67 and session VWAP at 4468.14. The 5-minute candle printed a closing wick rejection at the cluster, the body closed at 4464 with a clean upper wick to 4467.48. The 5-minute RSI rolled back from 60.9 toward 55, and the next bar failed to close above 4468. Macro Agent confirmed lean-bearish with both starred factors aligned (10Y yields rising plus Macro bias bearish), HTF bias decisively bearish. Confluence math returned 6 of 6 confluence factors met on a C+ grade. I entered short at 4467.48, stop 4492, TP1 4445, TP2 4420, TP3 4398. Position size reduced to 0.5 to 0.75x normal per the REDUCE_SIZE flag.
On a $100k account at 2.0% risk per trade.
Each trade risks +$2,000 (1R). The system's actual scale-out behavior may differ, see disclaimer.
| Scenario | R-multiple | Profit on $100k |
|---|---|---|
| Stop hit (invalidated) | -1R | −$2,000 |
| TP1 hit | +0.92R | +$1,840 |
| TP2 hit | +1.94R | +$3,880 |
| TP3 hit (max potential)Actual | +2.83R | +$5,660 |
All six agents combined.
What this trade teaches
The sixth leg of the seven-trade streak ran 69.48 points to TP3 in one hour and forty-one minutes with zero recorded drawdown, closing at +2.83R. This was the third TP3 winner of the same morning, alongside the +2.28R US500 short and the +3.34R EURUSD short, all three reading the same dollar-strength tape from different angles.
That outcome traces to two things, neither of which is the system claiming a hidden edge. First, the wait. Six evaluations across seven minutes is not the system being slow; it is the system refusing to enter on a tag of the cluster floor without a closing rejection at the cluster ceiling. The Trend Agent watched the bounce approach the resistance from 4451 to 4467.48, evaluating the trigger condition on every five-minute candle. The 14:41 UTC ENTER was the first moment all six confluence factors aligned on the same candle.
When the macro tape prices three different instruments into the same direction, you do not need a high-conviction setup card. You need the wait, the trigger, and the discipline to honor REDUCE_SIZE. - From the desk - March 26, 2026
Second, the cross-asset alignment. The same C+ grade on XAUUSD against a chop-tape macro would have stopped at 4492 in two hours. What turned this into a clean 1h 41m run was the same yields-up dollar-up macro that simultaneously priced US500 short into +2.28R and EURUSD short into +3.34R. The system places the stop above structural invalidation, sets targets at the next three structural references, and lets the position run until the tape rolls.
The seven-trade streak that bracketed this trade documented the value of cross-asset confirmation. When the Macro Agent registers the same regime read across multiple instruments and the Trend Agent posts directional confluence on each, the same morning can produce three independent TP3 winners from three independent setup cards. The week's full context lives in the week-of-March-23 recap, with the parallel EURUSD short that closed +3.34R from the same tape.
From the desk
What is worth holding onto is that this trade did not look special on the setup card. A C+ grade. A 62 percent confluence score. Six evaluations across seven minutes with the first five returning waits. The Macro Agent at 15 percent confidence on the bearish bias, the Trend Agent flagging TRANSITIONING and recommending REDUCE_SIZE. None of those numbers, on their own, would have any reader marking this as the third TP3 winner of the morning.
What separated it from the routine fades that stopped earlier in the quarter was the cross-asset alignment of the macro and the rejection on the same candle. We do not say "this will run 69 points clean to TP3 in 1h 41m." We say "10Y yields breaking out, DXY breaking out, oil rallying with negative correlation, the 5-minute bounce just printed a closing rejection at the VWAP-London-high cluster, every floor clears, confluence returns 62 percent." The system places the stop above structural invalidation at 4492, sets targets at the next three structural references, and lets the position run.
The third TP3 winner of the morning coming on a C+ is not a contradiction. It is the structure of the system's expectancy when the macro reads cleanly across multiple instruments at the same time. The grade describes the setup at entry, not a forecast. Above the threshold floor on a confirmed cross-asset tape, the variance favors continuation through every target.
From the SkyAnalyst Team.
At a Glance
What this teaches about AI-driven trading
How can three TP3 winners hit on the same morning across three different instruments?
When the macro tape prices a single direction across multiple correlated instruments, the same direction-read translates into independent setup triggers on each one. On March 26 the bearish-gold tape (yields up, DXY up, oil up) was simultaneously the bullish-dollar tape (US500 short via fade-of-counter-trend-squeeze, EURUSD short via VWAP rejection, XAUUSD short via London-high rejection). Three independent setup cards, three independent rejections, three TP3 outcomes. Cross-asset confirmation is one of the system's confluence factors, not a coincidence.
Why did the Trend Agent run six evaluations on this trade?
The wait-and-confirm discipline applies when the structural premise is complete but the LTF trigger has not printed. On March 26 between 14:34 and 14:39 UTC, the 60-minute EMA stack was firmly bearish and price was below VWAP, but the 5-minute corrective bounce was still extending toward the resistance cluster. The trigger required a closing rejection candle at the cluster ceiling (VWAP plus London high plus 60-minute EMA9) with RSI rolling back from the 60 cap. That printed at 14:41 UTC, and the system entered. Five waits, one enter.
What does the "REDUCE_SIZE" flag mean and why did it not block the trade?
The Trend Agent flags REDUCE_SIZE when the regime is TRANSITIONING rather than firmly trending. It is a sizing instruction, not a veto. The system enters at 50 to 75 percent of normal risk allocation rather than full size, accepting that a corrective bounce with legitimate 5-minute momentum can produce shakeouts even on the right direction. The position still gets the same stop at structural invalidation and the same three targets; only the dollar exposure is reduced.
How does this trade fit into the seven-trade streak it was part of?
This was the sixth leg of a seven-trade winning streak that ran across the last week of March. Three of the seven were TP3 winners on confirmed-trend continuation tapes. On March 26 alone the streak posted three TP3 winners (US500 +2.28R, EURUSD +3.34R, XAUUSD +2.83R) reading the same yields-up dollar-up tape from three angles. The streak's arithmetic depended on the macro reading cleanly across instruments rather than on any single high-grade setup.
Run your markets with SkyAnalyst
Seven-day free trial. No credit card. Full access to the Trend Agent, Macro Agent, and six-factor confluence scoring.
Trading involves substantial risk of loss. Past performance is not indicative of future results. The analysis shown was produced by an AI model operating on SkyAnalyst’s live trading infrastructure; it is shared for educational and research purposes only and is not financial advice. About reported results. Each model outputs three take-profit targets (TP1, TP2, TP3) per trade. In live execution, models typically scale out at TP1 for risk management — the broker position records this as a TP1 exit. The R-multiples and dollar returns shown in this article reflect the full potential of the trade: where the market actually traveled to (the highest take-profit hit, or stop loss) before the setup was invalidated or exhausted. This lets readers see the complete arc of each setup, not just where the position was closed. Simulated returns in this article are calculated against a hypothetical $100,000 account at 2% risk per trade (1R = $2,000). These are educational reference figures and do not reflect any specific account or broker execution. Your actual result depends on your position size, your risk parameters, and live market conditions.
From the SkyAnalyst Journal
March 2026 Monthly Recap: 42 Trades, Variance Both Directions, Break-Even Net
Forty-two trades. Twenty-two winners, twenty losers, 52.4 percent win rate. Net minus 0.13R, essentially flat on a TP1 baseline. The month produced both the deepest published drawdown and the bumper week of the record.
USDJPY Short on March 31 - Closing the Month on a TP3 Winner
A pullback short on USDJPY entered at 159.23 ran to TP3 at 158.75 in 2h 32m, closing at +3.20R. The closing-day winner of a March that finished -0.13R / 22W-20L on the TP1-baseline tally.
EURUSD Long on March 31 - Second of Two Same-Day TP3 Winners
A Bullish Pullback long on EURUSD entered at 1.1520 ran to TP3 at 1.1558 over four hours and seventeen minutes, closing at +1.58R. The second of two TP3 winners on the closing day of a near-flat March.