NAS100 Long Holds Overnight to TP2 on a VWAP-Pivot Pullback Continuation
SkyAnalyst AI journal entry: NAS100 Long on May 14, 2026 closed +1.6R on TP2. 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 macro setup the morning gave us
May 14 was a quieter session than May 13 across the bloc. The index tape was less directional, but the structural patterns on NAS100 were clean.
VWAP and pivot at two points apart
The session VWAP at 29520 and the classical daily pivot at 29518 sat two points apart on NAS100. That is an unusually tight cluster on an index instrument that typically trades in 50 to 100 point intraday swings. When two algorithmic-watched reference levels coincide within a single tick of typical noise, the cluster carries unusual order weight. The Trend Agent's gate flagged the cluster as an active support candidate before any candle had fired.
NAS100's intraday volatility profile
NAS100 averages 50 to 150 point intraday ranges depending on the macro tape. A 105-point stop on this trade sits at the lower end of acceptable risk for the instrument. The Risk Agent allowed it because the entry sat exactly at the cluster: meaningful break below 29416 would invalidate both the VWAP and the pivot simultaneously.
Why TRENDING worked here
The higher timeframes (60m, daily) were aligned bullish on NAS100 entering the May 14 session, even though shorter-timeframe momentum had been mixed. The Trend Agent's regime classification weights higher timeframes more heavily than the 5m read. The TRENDING tag mapped to 1.0 percent equity sizing. See our May 18 NAS100 short for the opposite-direction TRENDING case on the same instrument.
The pattern we were trading
This was a textbook example of what professional traders: a VWAP / daily-pivot pullback long. Two algorithmic reference levels coincide on a single line, the first pullback test holds, and the candle close back above confirms the entry.
Why VWAP plus pivot is heavier than either alone
VWAP is a session-anchored reference: a price most participants accept as fair across the current trading day. The daily pivot is computed from the prior session's high, low, and close: a level every algorithmic strategy tracks independently. When the two coincide within typical noise, the cluster carries order flow from two different communities. A failure to break the cluster on a pullback test is structurally heavy.
TRENDING regime sizing for index longs
The Risk Agent's TRENDING tag mapped to 1.0 percent equity sizing on this trade. Index longs in TRENDING regimes carry more position risk than short setups because indices can flush down faster than they melt up. The Risk Agent accepts that asymmetry as the cost of taking macro-aligned long entries in TRENDING conditions. The position scalar does not change with direction.
Why we held the position overnight
The trade entered at 14:29 UTC on May 14, hit TP1 mid-session, and was held through the European and Tokyo overnight to TP2 the next morning. The system does not flatten at the New York close. The structural thesis (the pullback into the VWAP/pivot cluster held, the higher-timeframe trend was intact, the stop was nowhere near threatened) survived the overnight test. The position ran until TP2 fired.
Index overnight risk
Index longs held overnight face two specific risk windows. The first is the post-NY close, when liquidity is thin and price can drift on light flow. The second is the Tokyo open, when Asian session flows can produce sharp moves before the European open stabilizes the tape. Both windows came and went on May 14 to 15 without threatening the 29416 stop. The Risk Agent's structural stop placement is what made the overnight hold viable.
What "pullback continuation" means at the agent level
A continuation setup is not a reversal. The higher-timeframe trend is already in place. The Trend Agent is not calling a bottom; it is timing the re-entry of an existing uptrend at the first pullback that holds the value reference. The May 14 NAS100 long is the canonical version: the higher timeframes had been bullish into the May 14 session, the pullback to the VWAP/pivot cluster was the entry trigger, and the move continued from there.
Pattern catalogue
We trade nine setups across forex and indices: NY AM continuation, NY AM session pullback, London continuation, opening-drive rejection, VWAP reclaim, range-extreme fade, breakout-retest, Asian range break, and structural failure. Each is gated by its own confluence rules. The Trend Agent does not pick a favorite. Different days produce different setups, and the system is dynamic, not dogmatic. It doesn't favor any single strategy.
Decision log
At 14:29 UTC on May 14, the GPT-5.5 Trend Agent issued the entry decision on a single trigger event. The recorded decision log shows ENTER without intermediate WAIT evaluations: the chart trigger (a 5m candle close back above the 29520 VWAP / 29518 pivot cluster after a successful pullback test) fired on the first eligible bar. The Macro Agent supplied a neutral-to-supportive backdrop for indices. The Cross-Asset Agent confirmed yields were stable, not pressuring equities. The Risk Agent computed entry 29521.3 (post-pullback reclaim), stop 29416 (below the cluster plus structural buffer), TP1 29613 (0.87R prior intraday high extension), TP2 29690 (1.6R structural target). TP3 was not tracked given the moderate macro tailwind. Final confidence: high-conviction TRENDING tag. Decision: ENTER long at 1.0 percent equity.
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 | +0.87R | +$1,740 |
| TP2 hit | +1.6R | +$3,200 |
| TP3 hit (max potential) — not tracked | +0R | +$0 |
All six agents combined.
What this trade taught us about index overnight holds
The May 14 NAS100 long ran from 29521.3 to 29690 across fourteen and a quarter hours, with the latter half playing out after the New York close. Half of the trade's full-potential R was earned overnight.
TP1 closes at the broker, TP2 plays on the chart
Once price first crossed 29613, the broker closed 100 percent of the position. The realized +0.87R (TP1) was locked in. The chart then continued to 29690 by the next morning, producing the +1.6R full-potential reading we report as the hero figure. The reader sees both numbers; only the realized R funds the next position. The gap between TP1 and TP2 lived only as chart data, not as broker book.
Why we do not re-enter for TP2
When TP1 closes at the broker, the position is done. We do not re-enter to chase TP2. Re-entry introduces spread cost, slippage, and the moral hazard of revenge trading. The system's edge depends on letting closed trades stay closed. The reported full-potential R is for the reader's understanding of the move's arc, not for our re-entry decision. See our May 13 USDJPY long for a TP1-only counterpart that showed the same broker-close discipline on a smaller move.
What the overnight hold actually risks
The position carried roughly $2,000 of theoretical drawdown risk per 1R against the stop. The deepest pullback during the overnight was to roughly 29495, about 26 points below entry, which translates to roughly -0.25R unrealized. Modest in absolute terms, but it happened in the thin Tokyo session when most retail desks have closed. The Risk Agent's stop at 29416 was never threatened. The structural stop placement is what allows the system to sleep through the overnight without intervention.
What we changed in our notes after this trade
Two adjustments from the May 14 NAS100 post-trade review.
Tight-cluster setups get a tag
VWAP and daily pivot coinciding within five points on an index instrument is rare. We are tagging trades that key off two-reference clusters within tight bounds as "tight-cluster" in internal metadata. The hypothesis is that tight-cluster setups have higher TP2 hit rates than wider-cluster setups, because the level holds more reliably on the test. The May 14 NAS100 is an early entry in that log.
Index-long overnight policy
We are formalizing the rule that index longs in TRENDING regimes carry through the overnight by default. The exception is when a high-impact USD event is scheduled within the overnight window; the Macro Agent can flag the position for early close in that case. On May 14, no such event was scheduled, and the position ran cleanly.
One number you do not see in the journal
The deepest pullback during the overnight (roughly 29495) was visible on the chart but never reached the structural stop at 29416. That is the typical shape of a successful overnight hold: the chart tests the trade but never threatens the read. The 78 points of breathing room between the deepest pullback and the stop is what made the overnight hold psychologically and structurally viable.
At a Glance
What this teaches about AI-driven trading
How does VWAP plus daily pivot become a heavier signal than either alone?
VWAP is anchored to the current trading session and reflects where most participants have transacted today. The daily pivot is computed from yesterday's high, low, and close. The two levels come from independent calculations and are watched by different algorithmic communities. When they coincide within a few ticks, the cluster has order flow from both systems simultaneously. A failure to break the cluster on a test is structurally heavier than a failure at either level alone.
Why are TRENDING index longs sized at 1.0 percent?
The Risk Agent's position scalar table maps TRENDING regimes to 1.0x base risk regardless of direction. We do not reduce size on long index entries despite the asymmetric volatility profile of indices. Long entries carry the same percent-of-equity exposure as shorts. The scalar table is structural, not adjustable for situational comfort. The trade-off is accepted as part of the system's design.
What does "pullback continuation" mean for entry timing?
Pullback continuation entries are not reversal calls. The higher-timeframe trend is already in place; the entry is timed to the first pullback that holds the value reference (VWAP, EMA cluster, daily pivot). The Trend Agent waits for the test of the level, the hold on the test, and the candle close back above the level before issuing ENTER. A pullback that breaks the cluster is a SKIP, not a different entry.
When does a NAS100 long get vetoed on a pullback setup?
When the macro tape turns risk-off. Sharp VIX spikes, a sudden DXY rally, or yields reversing aggressively can all veto index longs even when the chart structure looks supportive. The Macro Agent runs alongside the open position and can flag mid-trade regime changes. On May 14, the macro tape stayed neutral-to-supportive for indices throughout the holding period.
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. Every AI Trader publishes three take-profit targets (TP1, TP2, TP3) per trade. The broker closes 100% of the position at TP1, so two distinct R-multiples appear in this article. The hero R-multiple is the full-potential R: where the market actually traveled (the highest take-profit hit, or the stop loss) before the setup was invalidated or exhausted. The realized R, shown on the TP1 row of the simulated returns panel, is TP1’s R (or -1R on a stop out). The realized R is what we log to our running track record. Both numbers are honest. Showing both is what lets readers see the full arc of the move and the conservative ledger entry it produced. 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
US500 Long Waits for the Conditional Reclaim Before Buying the Dip
GPT-5.5 refused four times before entering US500 long at 7487.2. The Trend Agent required a reclaim of the opening-range breakdown zone, not the VWAP touch. TP1 booked +1.15R.
Eleven stops, one tape: the week structure refused to confirm
Eleven losses, nine R given back, a peak-to-trough drawdown of 10.81 percent and a longest losing streak of four. The honest portfolio view: what each stop taught us, and what the curve says about a week the structure refused to confirm.
May 18-24, 2026: A Seven-Eleven Week That Closed -2.82R Across Claude and GPT
Eighteen trades, seven winners, eleven losers, -2.82R net at TP1 baseline. Claude opened Monday with two early wins, GPT carried the index side mid-week, and a Friday cluster netted both sides back toward flat without crossing it.