US30 Short on April 13: The Trio's Dissenting Voice
SkyAnalyst AI journal entry: US30 Short on Apr 13, 2026 closed +1R on TP1. Full workspace view, decision log, and AI reasoning, unedited. SkyAnalyst AI journal.
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 transitional tape that argued both ways
US futures opened April 13 with a regime that did not pick a side cleanly. The 10-year yield was 4.321%, above its 5-day EMA of 4.312%, and had printed a fresh 5-day high of 4.363 in the early session. That alone would have been a structural drag on rate-sensitive Dow components. But the Dollar Index was 98.72, below its 5-day EMA of 98.97, and the VIX was 19.82, declining from yesterday's 20.85 EMA. Yields said one thing, dollar and vol said another. The Macro Agent's read for US30 was lean-bear at 23% confidence with tradeability scored 35 out of 100. That is the lowest macro tradeability print of the trio.
Cross-asset filled in the headwind nuance. The dominant signal was breadth. NYAD was -366 against a 5-day EMA of +307, and had printed a session low of -1,080 before recovering. Three consecutive days of negative breadth closes had taken the cumulative reading from +1,765 down to the current level, the cleanest bearish input on the chart. Oil added the wildcard: 100.53, up 6.7% day over day, an extreme cross-asset move that adds cost pressure to industrials and transports inside the Dow basket. Risk was calm but the underneath was rotating, hard.
Against that backdrop the Dow had gapped down 221 points from the prior close at 47,934, traded a session low of 47,395, and bounced 318 points from that low into a confluence of resistance: the 47,712 opening-range high, the 47,729 to 47,735 London session high, the 47,764 today's high which was also the Trend Agent's structural invalidation level. Four reference points stacked inside fifty-two points. The 60-minute structure was bearish with price sitting at the 61.8% Fibonacci retracement at 47,681. The 5-minute structure was bullish, EMAs aligned, momentum carrying the bounce. The 15-minute was the transition itself, fast EMA catching up to slow. That is what TRANSITIONING means in the workspace view: a bearish daily bias rallying into resistance with intraday momentum still bullish, and the system waiting for the rejection rather than chasing the extension.
The setup the Trend Agent flagged was a Short Rejection at the 47,712 to 47,764 Resistance Cluster. It is the inverse of the pullback longs that fired on the Nasdaq and EURUSD the same hour, run on a different instrument, against a different macro driver, with a different trigger arithmetic. Walking through it explains why the entry took eight wait cycles, why the grade stayed at C+, and why the position closed at TP1 in ninety-one minutes rather than running the full bounce-fade.
What the pattern is
Price establishes a bearish daily bias on the 60-minute timeframe: structure trading below the EMA stack, MACD line below zero, 61.8% Fibonacci retracement of the prior advance acting as the next decision zone. From that posture, the trader watches for a counter-trend bounce into a multi-confluence resistance cluster. The cluster is what defines the setup. A single resistance level is a guess. Four levels stacked inside fifty-two points is a structural cap. The entry is not the touch of the cluster. It is the 5-minute bearish reaction inside it: a rejection candle with upper wick larger than body, RSI rolling back below 60, MACD histogram turning negative, ideally with a close back below the lower edge of the cluster.
How professional traders actually use it
This is a staple of fade-the-bounce trading inside a bearish daily structure. The math favors a confirmed rejection over chasing the gap-and-go down. Shorting 47,500 after the gap has already filled half its range exposes the position to the next mean-reversion bar. Shorting 47,714 inside the resistance cluster after a confirmed bearish rejection prints, with a stop just above structural invalidation at 47,775, places the entry near the top of the next leg with eleven points of buffer above the highest reference. The R per unit of risk on the cluster fade is far better than the R per unit of risk on chasing the breakdown.
The tell on a fade is what the bounce does at the cluster. A bounce that arrives with deteriorating volume, prints an indecision body inside the zone, and gets a 5-minute close back below the lower edge of the cluster is a level holding. A bounce that punches through the upper edge with above-average volume and closes above the highest reference is a level breaking. Without the rejection candle, the pattern is noise. With it, the pattern is signal.
Why it works
Resistance clusters exist because the prior decline left resting offers behind. The first revisit tests whether those offers are still being defended. A bearish rejection with volume confirms the offers are present. The remaining supply at the cluster is structural, and the next leg lower is more probable than the prior bounce was at extension. The 47,712 to 47,764 cluster on April 13 carried four references that institutional desks defend at scale: the opening-range high, the London session high, the daily bias invalidation level, and the 60-minute Fibonacci retracement. That is a real wall.
It fails in the wrong regime, like every fade. A Short Rejection at Resistance inside a confirmed strong-bull regime, or against a macro tape that is actively flipping risk-on, will see the bounce reclaim the cluster and continue higher. The Macro Agent's regime read gates the pattern. On April 13 the macro was conflicted but lean-bear with low tradeability, and breadth was the deciding bear input. The grade cleared at C+ rather than B because the 5-minute structure was actively counter-trend, but the cluster math was strong enough to score the entry once the rejection finally printed.
How the system reads this, dynamically not dogmatically
SkyAnalyst does not favor the Short Rejection at Resistance as a strategy. The same hour the Trend Agent was scoring this US30 fade, the same agent was running a Bullish Pullback Long on the Nasdaq that fired six minutes earlier and would close TP3 four hours later, and a Pullback Buy at Structure on EURUSD that would fire twenty-six minutes later and close TP3 three hours after that. Two longs and one short, three different playbooks, three different triggers, all running in parallel inside the same fifty-nine-minute window.
The system reads the tape first and fits the pattern to what is actually there on each instrument independently. It does not show up to the chart with a directional bias and look for opportunities to express it. The four agents running in parallel, trend, macro, cross-asset, risk, each contribute a different lens on what kind of market each instrument is in right now. On the Nasdaq the read was a soft-dollar tape carrying a structural pullback long. On EURUSD the same soft-dollar tape was carrying a higher-quality structural breakout long. On US30 the same soft-dollar tape was running into a bearish breadth wall and a four-reference resistance cluster. Same tape, three different reads, three different positions. That is the dissenting voice this article is about, and it is why the system trades each instrument on its own confluence math rather than a unified directional thesis.
US30 NY AM Session Analysis — April 13, 2026
1. Breadth & Risk Regime
| Indicator | 5-Day Trend | Current | Assessment |
|---|---|---|---|
| NYAD (ADD) | EMA₅ +307 → Current -366 | Today low -1,080, now recovering | Contracting sharply — 3 consecutive negative closes; breadth deteriorated from +1,765 three days ago |
| VIX | EMA₅ 20.85 → Current 19.82 | Touched 18.83 yesterday, now bouncing within range | Declining but elevated — favorable for breakouts if direction confirms, but still >19 = wider stops warranted |
| US 10Y | EMA₅ 4.312 → Current 4.321 | Grinding higher from 4.283 two days ago; today high 4.363 | Modestly rising — not yet a sharp spike, but directional pressure on rate-sensitive Dow components |
| DXY | EMA₅ 98.97 → Current 98.72 | Below EMA₅, below yesterday's close 98.64 → bounced to 98.72 | Weakening dollar — mildly supportive for multinationals, but not a strong tailwind |
| Oil | Current 100.53 — was 94.25 yesterday | +6.7% day-over-day breakout, above yesterday's high by ~230 ticks | ⚠️ EXTREME MOVE — Oil surge adds cost pressure to industrials (CAT, transports); mixed for Dow |
Regime Classification: TRANSITIONAL (Lean Risk-Off)
Rationale: NYAD contracting aggressively from strongly positive to negative territory is the dominant signal — breadth does not support sustained upside for US30. VIX declining is constructive, but oil's extreme surge and rising yields create cross-currents. The dollar weakness provides a partial offset. This is not clean risk-on and not panic risk-off — it's a transitional environment where fade-the-rally setups carry more structural support than trend continuation longs.
2. Agent Synthesis
| Agent | Direction | Confidence | Key Detail |
|---|---|---|---|
| Macro Agent | US30: lean_bear (-35) | 23% (very low) | Tradeability: 35/100 (low). JPM NIM compression + CAT capex headwinds. Intraday neutral vs short-term lean bear = timeframe divergence. PPI tomorrow is the next catalyst. |
| Trend Agent | BEARISH | 61% (moderate) | Regime: TRANSITIONING. 60m bearish, 15m bullish rebound, 5m bullish cross. Invalidation: 47,764. VWAP: 47,559. Key R: 47,764 / Key S: 47,582 |
Agent Agreement Assessment
Both agents lean bearish, but with caveats:
- Macro confidence is extremely low (23%) with low tradeability (35/100)
- Trend Agent flags this as TRANSITIONING, not a clean bearish trend
- 5m and 15m show bullish rebound momentum counter to the dominant 60m bearish lean
NYAD confirms the bearish direction (contracting, currently -366). This gives us directional agreement across all three filters (Macro bear + Trend bear + NYAD contracting).
Signal strength: MODERATE — All three agree bearish, but Macro tradeability is very low and the Trend Agent is only 61% confident with a TRANSITIONING regime + REDUCE_SIZE recommendation. I'll present setups but with capped confidence at Medium-High and require strong technical confluence.
3. Gap & Session Context
| Reference | Level | Current Price (47,713) |
|---|---|---|
| Previous Close | 47,934.1 | -221 pts below |
| Yesterday's Low | 47,838.8 | -126 pts below |
| Yesterday's High | 48,277.9 | -565 pts below |
| Today's High | 47,764 | -51 pts below |
| Today's Low | 47,395 | +318 pts above |
| 5-Day EMA | 47,665 | +48 pts above |
Gap quantification:
- 60m ATR: ~99–107 pts. Daily implied range is wider.
- Gap down from previous close: -221 pts ≈ 2.1x hourly ATR → This is a significant gap.
- Price is trading below yesterday's entire range — a breakaway gap structure.
Gap Assessment: The gap-down exceeds 1.5x ATR, price is below yesterday's low, and NYAD is negative. This favors a gap-and-fade (continuation short) rather than gap-fill. However, price has already bounced ~318 pts from today's low (47,395), so the easy short money may have been made during London. The current question is: Does the bounce stall near resistance and offer a short re-entry, or does it reclaim the gap?
4. Multi-Timeframe Technical Read
60-Minute (Dominant Trend)
- EMA Stack: Price (47,707) > EMA fast (47,666) but < EMA slow (47,727) → No clean alignment; stalled between EMAs
- RSI: 50.2 — dead neutral, no momentum edge
- MACD: Line -76.3, histogram +16.2 (rising but still below zero line) — bearish structure with improving momentum
- Fibonacci: 61.8% retracement at 47,681 (nearly tested); next major = 50% at 47,794
- VWAP: 47,561 — price is well above → extended on the intraday bounce
- Verdict: Bearish trend intact but momentum is improving. Price is in the 61.8% fib zone — classic rejection area for bearish retracements.
15-Minute (Intermediate Structure)
- EMA Stack: Price (47,707) > EMA fast (47,599) > still < EMA slow (47,624) → Fast EMA is catching up; trend is below but narrowing
- RSI: 62.0 — moderately bullish, not overbought
- MACD: Line +10.9, signal -13.0, histogram +23.9 (strongest reading in the data set) → Bullish momentum on 15m
- VWAP: 47,557 — price above VWAP, holding in upper 1SD band
- Verdict: 15m is building a bullish rebound structure. The conflict between 15m bullish and 60m bearish = the transition the Trend Agent flagged.
5-Minute (Entry Precision — Last 10 Candles)
| Time (UTC) | Open | High | Low | Close | Key Signal |
|---|---|---|---|---|---|
| 13:35 | 47,521 | 47,558 | 47,505 | 47,548 | Volume spike, below VWAP |
| 13:40 | 47,551 | 47,567 | 47,537 | 47,564 | Building base, still below VWAP |
| 13:45 | 47,537 | 47,693 | 47,526 | 47,692 | Breakout candle, RSI hit 71.5 OB, broke above VWAP |
| 13:50 | 47,710 | 47,712 | 47,611 | 47,622 | Rejection from 47,712 (session high) |
| 14:00 | 47,680 | 47,686 | 47,630 | 47,643 | Above VWAP, holding gains |
| 14:05 | 47,659 | 47,689 | 47,649 | 47,649 | Testing support cluster 47,648-49 |
| 14:10 | 47,663 | 47,684 | 47,647 | 47,684 | Bullish EMA cross, trend_direction = above |
| 14:15 | 47,657 | 47,677 | 47,647 | 47,674 | Volume spike, holding above EMAs |
| 14:20 | 47,675 | 47,696 | 47,659 | 47,693 | Fib 100% reached (bullish pivot) |
| 14:25 | 47,681 | 47,703 | 47,679 | 47,702 | At resistance cluster 47,712-729 |
| 14:30 | 47,711 | 47,735 | 47,706 | 47,707 | New session high 47,735, fading off top |
5-Minute Summary:
- EMA alignment: BULLISH — EMA fast (47,614) > EMA slow (47,586), price above both ✅
- VWAP position: Price at 47,707 vs VWAP 47,618 — above VWAP but extended (upper band) ✅
- RSI: 67.2 — approaching overbought but not there
- MACD: Line +49, histogram +14.7, decelerating from peak — momentum slowing
- Key observation: Price is pressing into the 47,712–47,735 resistance cluster (session high, 5m pivot high, and approaching the Trend Agent invalidation level of 47,764). The NY session high of 47,735 was just printed at 14:30 UTC (10:30 ET).
5. Key Levels & Calendar
Opening Range (9:30–10:00 ET = 13:30–14:00 UTC)
| Level | Value |
|---|---|
| OR High | 47,712 (from 13:45–13:50 candles) |
| OR Low | 47,505 (from 13:30 candle) |
| OR Midpoint | ~47,609 |
Confluence Level Map
| Zone | Level(s) | Confluences |
|---|---|---|
| Resistance Cluster | 47,712–47,764 | OR High (47,712), Today's High (47,764), Trend Agent Invalidation (47,764), London Session High (47,729–47,735), 60m Fib 61.8% (47,681) just below, 5m S/R Resistance (47,712, 47,714, 47,729) |
| Pivot Zone | 47,648–47,661 | 5m S/R cluster (47,648/49/44), Daily Pivot (47,649), 15m Fib 23.6% (47,652) |
| VWAP Zone | 47,555–47,618 | 5m VWAP (~47,618), 15m VWAP (47,557), 60m VWAP (47,561), 15m Fib 50% (47,565), 60m S/R Support (47,582) |
| Support Cluster | 47,500–47,520 | OR Low (47,505), Previous daily low (47,503), 15m Fib 78.6% (47,471), 60m Fib 78.6% (47,521) |
| Major Support | 47,395–47,401 | Today's Low (47,395), 15m S/R (47,401), 60m Fib 100% pivot low (47,316) |
Calendar Check
- No high/medium impact USD events scheduled for today. ✅ Clear to trade.
- Tomorrow 8:30 AM ET: PPI data (high impact) — this creates end-of-day positioning risk but does not affect AM session setups.
6. Setup Construction
Confluence Checklist Applied to the Current Environment
The dominant trade idea, given all filters pointing bearish and price rallying into resistance, is a short at the resistance cluster.
PRIMARY SETUP: Short Rejection at 47,712–47,764 Resistance Cluster
Thesis: Price has bounced ~318 pts from today's low into the densest resistance confluence on the chart — the OR high, London high, today's high, and the Trend Agent's bearish invalidation level. With NYAD contracting, both agents bearish, and this being a retracement within a larger bearish 60m structure, a rejection here offers a high-probability short with structural definition.
Confluence Score: 4 of 5 ✅
| # | Confluence | Status |
|---|---|---|
| (a) | EMA alignment on 5m supports trade direction | ❌ — 5m EMAs are bullish (opposing short) |
| (b) | NYAD directional agreement | ✅ — NYAD -366, contracting, supports shorts |
| (c) | Both AI agents aligned with trade direction | ✅ — Macro lean_bear + Trend bearish |
| (d) | Price on correct side of VWAP | ✅ — For a short, price above VWAP = selling from premium (price at 47,707 vs VWAP 47,618) |
| (e) | Entry near daily S/R, Fib, or OR boundary | ✅ — OR High 47,712, Today's High 47,764, 60m Fib 61.8% 47,681, London High 47,729 |
4/5 confluences met. This exceeds the 3/5 standard minimum and meets the 4/5 threshold appropriate for a transitional regime.
Setup Details
| Parameter | Level | Notes |
|---|---|---|
| Entry Zone | 47,712 – 47,745 | Between OR High and London session high; wait for price to enter this zone |
| Entry Trigger | Bearish rejection candle (5m): upper wick ≥ body, close below 47,712; OR a 5m bearish engulfing pattern within the zone; OR failure to hold above 47,735 with volume decline | Do NOT short the first touch — require a confirmed rejection candle |
| Stop Loss | 47,775 (11 pts above the Trend Agent invalidation of 47,764 = buffer for slippage) | Structural: above today's high + invalidation. Risk = ~55–65 pts from mid-entry zone |
| TP1 | 47,648–47,653 (Pivot cluster) | ~65 pts from entry ≈ 1.0–1.1R — structural level with 5m S/R confluence |
| TP2 | 47,582–47,560 (VWAP / 60m Support) | ~145–160 pts from entry ≈ 2.3–2.6R — strong structural zone |
| TP3 | 47,503–47,505 (OR Low / Previous Daily Low) | ~210 pts from entry ≈ 3.4R — full retracement of the bounce |
R:R Profile
| Target | Distance | R Multiple |
|---|---|---|
| TP1 (47,650) | ~65 pts | 1.05R |
| TP2 (47,570) | ~145 pts | 2.35R |
| TP3 (47,505) | ~210 pts | 3.40R |
TP1 at ~1.05R is at a genuine structural level (pivot cluster 47,648-53). TP2 at the VWAP zone provides 2.3R+. Minimum 1.5:1 R:R easily achievable. ✅
Trade Management
- At TP1: Take partial profits (50%), move stop to breakeven
- At TP2: Take additional partial (30%), trail stop above TP1
- TP3: Runner (20%) with trail above TP2
SECONDARY SETUP (Conditional): Long at VWAP Zone if Short Triggers First
This setup only activates if the Primary Short triggers, price reaches TP2 zone, and shows bullish reversal signals at VWAP.
Thesis: If price sells off from resistance back to the VWAP cluster (47,555–47,618), this is the prior bounce origin area. A bounce here could set up a second-chance long — but only with a 5m bullish reversal candle and if NYAD improves intraday.
Confluence Score: 3 of 5 (Conditional — may reach 4 if 5m EMAs flip bearish then re-cross bullish)
| Parameter | Level |
|---|---|
| Entry Zone | 47,555 – 47,590 |
| Entry Trigger | 5m bullish engulfing or hammer at VWAP, with MACD histogram turning positive |
| Stop Loss | 47,495 (below OR Low 47,505 - 10 pt buffer) |
| TP1 | 47,650 (Pivot cluster, ~65 pts = 1.1R) |
| TP2 | 47,712 (OR High, ~130 pts = 2.1R) |
⚠️ Lower conviction. This is a counter-trend bounce in a bearish environment. Use reduced position size (0.5% risk max). Only valid if NYAD shows improvement from -366 levels and 5m structure confirms.
Warnings & Risk Notes
| Warning | Detail |
|---|---|
| ⚠️ Transitional Regime | Trend Agent recommends REDUCE_SIZE. Both agents are low-confidence. Use 0.5%–0.75% risk instead of standard 1%. |
| ⚠️ 5m EMAs Oppose Primary Short | The 5m trend is currently bullish — the short setup requires price to stall and reverse at resistance. If price blasts through 47,764 with strong volume, the short thesis is invalidated. |
| ⚠️ Oil Surge | Oil +6.7% is extreme and creates unpredictable cross-asset flows. This can amplify Dow volatility in either direction (energy names benefit, industrials/transports suffer). |
| ⚠️ Pre-PPI Positioning | Tomorrow's PPI at 8:30 AM ET is high-impact. Some institutional positioning may begin in the PM session, adding noise. AM session should be cleaner. |
| ⚠️ Session Timing | It is currently ~10:30 AM ET. The opening range is already set. The ideal AM session window (9:30–11:00 ET) has about 30 minutes remaining. If the short doesn't trigger within the next 30–45 minutes, consider the setup stale for the AM window and re-evaluate at the 2:00–3:30 PM close window. |
| 🔍 NAS100 Divergence | No NAS100 data provided — cannot confirm or flag rotation divergence. Monitor independently. |
Summary Decision Matrix
| Factor | Reading | Implication |
|---|---|---|
| NYAD | Contracting (-366) | Bearish filter ✅ |
| VIX | 19.82, declining | Normal stops, breakout-capable |
| Agents | Both lean bear | Directional agreement ✅ |
| Gap | -221 pts (>1.5x ATR) | Fade-continuation favored |
| 60m Trend | Bearish, price at 61.8% fib | Classic rejection zone |
| 5m Momentum | Bullish, extended near resistance | Need reversal confirmation |
| Primary Setup | Short 47,712–47,745 | Confidence: Medium-High |
| Trigger Required | Bearish rejection candle | Do not front-run |
Bottom Line: The environment supports shorting US30 into the 47,712–47,764 resistance cluster, but the setup requires patience for a confirmed rejection. The bounce from today's low has been strong and 5m momentum is still bullish — an aggressive fade without a trigger is not recommended. If price cleanly breaks and holds above 47,764, the bearish thesis is invalidated and no short should be taken. In that scenario, stand aside — there is no high-probability long setup above the Trend Agent's invalidation in a negative-breadth environment.
Decision log
14:37 UTC, 52% confidence. Price has bounced 318 points from today's low and is pressing into the 47,712 to 47,764 resistance cluster. Four reference levels stack inside the zone: opening-range high at 47,712, London session high at 47,729 to 47,735, today's high at 47,764, and the structural invalidation level at 47,764. The 60-minute structure is bearish, NYAD is contracting at -366, both agents lean bearish. The setup grade is C+. But the immediate context is counter-trend bullish: 5-minute EMA fast above slow, RSI 67.2 approaching overbought, price extended on the upper VWAP band. The trigger I require is a 5-minute bearish rejection candle inside the cluster with upper wick larger than body and a close back below 47,712. Price is at the cluster but the rejection has not printed. Declining this evaluation.
14:38 UTC, 48% confidence. One minute later and the picture has weakened slightly. Price ticked up to 47,712 and is testing the lower edge of the cluster, but the 5-minute candle in motion is still building a body, not yet a wick. Volume on the approach is at the 60-period average, neither confirming a stall nor confirming a breakout. RSI has lifted to 68. Confidence drops four points because the immediate momentum is now slightly more bullish than the prior cycle. The cluster is being tested but not defended. Declining.
14:40 UTC, 45% confidence. Price has reached 47,735, inside the cluster, at the London session high. The 5-minute bar that just closed printed a small body with both wicks, indecision rather than absorption. RSI has held at 67. Cross-asset is neutral: DXY flat, breadth still red at -360 area. The structural premise has not changed since two minutes ago, the cluster math is still intact, but the rejection signature I require has not printed. Price is testing the second of four references. Two more remain above. Declining this evaluation.
14:41 UTC, 45% confidence. Price holding 47,711 to 47,735, the upper end of the cluster, the candle that just closed was another indecision body. No directional commit either way. The 5-minute MACD histogram is decelerating from its peak, an early hint the bounce is losing momentum, but the rejection candle has not printed. The system requires the actual evidence, not the inference from declining momentum. Declining.
14:42 UTC, 45% confidence. Price has tested 47,735 again, the third repeated test of the London session high inside this cluster, and the 5-minute body printed slightly red with the upper wick now meaningfully larger than body. This is the first whiff of the rejection signature, but a single bar with mild characteristics is not sufficient. The pattern requires the close back below 47,712, the lower edge of the cluster, with confirming volume on the rejection. Neither has printed. Confidence holds at 45%. Declining this evaluation.
14:43 UTC, 40% confidence. Price has lifted again to 47,720, retesting the cluster, and the 5-minute candle has not yet decided. Volume on the latest approach has dropped slightly, possibly the early participation fade I want to see, but the close is still inside the upper half of the cluster. The system has now scored six wait cycles in seven minutes against this setup. Confidence is dropping rather than rising because the cluster has held but has not yet rejected with the structural close I require. The pattern is intact, the trigger is missing. Declining.
14:46 UTC, 35% confidence. Three minutes since the last evaluation, and confidence has dropped to its session low. Price has held 47,712 to 47,735 for the better part of fifteen minutes now. The cluster is acting as a cap but not as a rejection. RSI on 5-minute is at 65, MACD histogram is at +14.7 and decelerating. The longer the price holds inside the cluster without the rejection candle printing, the higher the probability that consolidation resolves with a breakout above 47,764 rather than a rejection below 47,712. The system is now actively considering whether to abandon the setup if the cluster is not defended in the next ten minutes. Declining this evaluation.
14:47 UTC, 40% confidence. Confidence ticks back up four points. The 5-minute candle that just closed printed at 47,711, fractionally below the lower edge of the cluster, with a body that closed in the bottom third and upper wick reaching 47,724. This is the structural pattern I have been waiting for. But the close is at the very edge, not decisively below, and the volume on this bar was only at the 60-period average rather than above it. The rejection signature is forming. The volume confirmation is still absent. The pattern's discipline is to wait for both. Declining.
14:49 UTC, 66% confidence. The 14:48 5-minute bar closed at 47,704, decisively below the 47,712 lower edge of the cluster, printing a bearish body with the upper wick reaching 47,732 and a tail volume spike that lifted the bar's volume meaningfully above the 60-period average. Both confirming components, the close below structural support and the volume confirmation, printed inside the same 5-minute window. RSI rolled below 60 for the first time in twenty minutes. MACD histogram turned negative on this bar. Cross-asset confirmation: DXY just printed a fresh 5-minute lower low, and breadth ticked weaker to -380. The structural premise has not changed since twelve minutes ago. What changed is that every required confirmation finally printed inside the same bar. Confluence math returned 66% on a C+ grade, above the entry floor. Entering short at 47,714, stop 47,775, TP1 47,653.
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 hitActual | +1R | +$2,000 |
| TP2 hit — not tracked | +0R | +$0 |
| TP3 hit (max potential) — not tracked | +0R | +$0 |
All six agents combined.
What this trade teaches
The April 13 trio is a clean illustration of the system's instrument-independent confluence logic. Three trades fired inside fifty-nine minutes. Two long, one short. Same macro state object, same agent coordination, three different reads. The Nasdaq saw a soft-dollar tape carrying a structural pullback long and ran TP3 in four hours thirty-three minutes at +2.22R (TP3). EURUSD saw the same soft-dollar tape carrying a higher-quality structural breakout long and ran TP3 in three hours eleven minutes at +3.15R (TP3). US30 saw the same tape running into a four-reference resistance cluster behind a contracting NYAD reading and a lean-bear macro, and the system shorted the rejection.
The R-multiple difference is structural. The two longs cleared their entry thresholds on confirmed pullback triggers inside multi-confluence support zones, with TP3 at the next major reference level above. This US30 short cleared its entry threshold on a confirmed rejection trigger at a four-reference cluster, but with TP1 at the pivot zone only sixty-one points away. The TP1 distance from entry was sixty-one points against a stop distance of sixty-one points. A clean structural 1:1 setup, sized at 0.75% risk rather than the standard 1% because the regime read was TRANSITIONING with REDUCE_SIZE flagged. The trade closed at +1R (TP1) for +$2,000 (TP1) in one hour and thirty-one minutes.
Three trades fired inside fifty-nine minutes on April 13. Two longs ran to TP3 on the soft-dollar tape. One short, this one, was the dissenting voice the system sized smaller into and clipped at TP1. - From the desk - April 14, 2026
The eight wait cycles between 14:37 and 14:47 are the structural lesson. A discretionary trader watching the same fifteen-minute window would have shorted the first test of 47,712 at 14:37 when both agents were already lean bear and price was at the densest resistance confluence on the chart. The first three wait cycles saw the touch without the reaction. Cycles four through seven saw the cluster hold but no rejection close. Confidence dropped to its session low of 35% at 14:46 because the longer price held inside the cluster without rejecting, the higher the probability of an upside breakout rather than a downside fade. The 14:48 bar finally printed both confirming components inside the same window. The system is not waiting for confidence. It is waiting for the specific confirming evidence. The same-day EURUSD long ran on the same trigger discipline, six minutes earlier on a different instrument with different mechanics. The same-day NAS100 long ran on the same trigger discipline twenty-eight minutes before that. The week's full arc is documented in the April 13 weekly recap.
The April month-to-date tally entering this trade was -5.96R across 9 trades at an 11.1% win rate. April had been the worst month of the year up to this point, and April 13 was the day the rolling tally turned. Adding the +1R (TP1) here, plus the +2.22R (TP3) on the Nasdaq twenty-eight minutes earlier and the +3.15R (TP3) on EURUSD twenty-six minutes later, lifted the April MTD to roughly +0.41R across 12 trades inside the same trading session. That is the asymmetric arithmetic at work: a clean trio firing inside fifty-nine minutes carrying the rolling expectancy from negative to positive in a single afternoon.
From the desk
The interesting thing about this trade is what it reveals about agent coordination across simultaneous setups on different instruments. The Nasdaq pullback long entered at 14:21 UTC and was running, already past its first take-profit. While that position was open, the Trend Agent began evaluating this US30 short at 14:37 UTC and the EURUSD long at 15:09 UTC in overlapping cycles. Three live evaluations on three instruments in different directions, each scoring against its own confluence math, each gated by the same shared Macro and Cross-Asset state.
A discretionary trader running these three setups would have been pulled hard toward the longs and away from the short. Two of the three positions on a soft-dollar tape were carrying immediate paper gains. The instinct would have been to size up on those and skip or shrink the short. The system did the opposite arithmetic. The Risk Agent enforces a fixed 1% per trade by default and gated this US30 entry to 0.75% on the TRANSITIONING regime read with the REDUCE_SIZE recommendation. The Nasdaq and EURUSD entries took full 1% on their cleaner regime reads. That is not the system being timid on the short. That is the system reading the regime quality on the specific instrument and sizing accordingly.
A reasonable question by now is whether a retail trader with ChatGPT and three charts open could reproduce this. They cannot, and not because of model quality. On April 13 the Macro Agent had written its conflicted lean-bear read on US30 with low tradeability into the shared state at 09:00 UTC and had not updated it since. The Trend Agent's nine evaluations on US30 between 14:37 and 14:49 read that same state object, used it to gate the setup grade at C+ rather than the higher conviction the technical picture alone might have justified, and used it to flag the REDUCE_SIZE recommendation that the Risk Agent then enforced on entry. If the Macro Agent had been chatting in prose about a mixed tape, the Trend Agent would have had to interpret the tone three times across three instruments running in parallel. It does not, so it did not. The coordination between the four agents is the product. That is what a chat interface cannot simulate, and it is what this case study shows in practice on the dissenting voice of the trio.
The next case study returns to the larger week of April 13 to 19. We will continue working through the month the same way.
From the SkyAnalyst Team.
At a Glance
What this teaches about AI-driven trading
How can the system trade a short and two longs on the same day on the same macro tape?
The four agents run continuous evaluation cycles across all six covered markets in parallel. The Macro and Cross-Asset states are shared across all instruments, but the Trend Agent scores each instrument independently against its own structural picture. On April 13 the same soft-dollar tape was carrying the Nasdaq into a bullish pullback, EURUSD into a bullish breakout pullback, and US30 into a four-reference resistance cluster behind contracting breadth. The macro alone does not pick the direction. The Trend Agent's structural read on each instrument plus the confluence math determines the trade direction.
Why did the US30 trade size at 0.75% risk while the same-day Nasdaq and EURUSD trades took 1%?
The Risk Agent reads the Trend Agent's regime classification and the Macro Agent's tradeability score before sizing. On April 13 the US30 regime was flagged as TRANSITIONING with a REDUCE_SIZE recommendation, and the macro tradeability score was 35 out of 100, the lowest of the trio. The Nasdaq and EURUSD regimes were cleaner intraday-trend classifications with macro tradeability scores in the higher range. The Risk Agent enforces standard 1% sizing on cleaner regime reads and reduces to 0.75% on TRANSITIONING regimes. That sizing rule applied here.
What does the rolling tally mean for context with this trade?
The rolling tally tracks month-to-date, quarter-to-date, and year-to-date net R alongside trade count and win rate. Entering this trade the April MTD was -5.96R across 9 trades at an 11.1% win rate, the worst month of the year up to that point. The April 13 trio added +1R (TP1) on this US30 short, +2.22R (TP3) on the same-day NAS100 long, and +3.15R (TP3) on the same-day EURUSD long. Across that fifty-nine-minute window the rolling MTD lifted from -5.96R to roughly +0.41R across 12 trades. Publishing the tally with every case study keeps the reporting honest: readers see the rolling expectancy emerging from a mix of outcomes.
When does a Short Rejection at Resistance fail and what happens if it does?
The pattern fails when the resistance cluster does not hold. On April 13 the stop was 47,775, eleven points above the Trend Agent's structural invalidation at 47,764. A 5-minute close above 47,775 would have invalidated the structural premise and closed the position at -1R. The system does not adjust the stop based on developing information once the position is open. The stop is the line at which the structural premise is invalid, and the trade closes mechanically at that line. The same arithmetic applied to all three trades in the April 13 trio, and the same rule would have closed any of them mechanically had the structural premise broken.
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.
Del diario de SkyAnalyst
The Year SkyAnalyst Learned to Trust Claude: 99 Trades, +16.57R YTD
Ninety-nine trades since launch on Jan 12, 2026. Plus 16.57R net at a 58.6 percent win rate. The headline isn't the number — it's how a desk that opened with three trades in January became a system holding expectancy across four months.
US500 Short on March 19: A Failed Bounce Inside the Deepest Drawdown Week
A SHORT at 6596.9 into VWAP and prior-day-low resistance, four waits and one enter at 74 percent confidence, a 3h 55m hold to TP1 for +1.18R inside the worst week of the published record.
XAUUSD Short on March 19: A Bearish Gold Setup Six Hours Before FOMC for +1R
A SHORT into the 4618 to 4643 NY rebound resistance, eighteen evaluations before the trigger printed at 66 percent, a 3h 59m ride to TP1 for +1R inside the worst weekly stretch of the published record.