Jun 8-14, 2026: two stops, and the patient long that came home
Three trades. Two quick stops inside six minutes each, and one GBPUSD long we left open last week. It closed +0.83R (TP1), trimming the week to minus 1.16R agai
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.
Three trades, one winner, net minus 1.16R. That is the settled scoreboard for Jun 8-14 now that the last position has closed. Through Jun 15, 2026, the system has banked +20.43R YTD from Jan 12 inception; a $100,000 simulated account at 2 percent risk per trade sits at $140,866.91 on the static path, or $146,625.69 on the compounded path. When we first published this recap, we counted two trades and no winner, and we flagged a third GBPUSD long that was still open at press time. We said it would be counted in the window it closed. It closed Sunday night at +0.83R (TP1) realized, and now the week is whole: two quick stops, one patient long that worked, and a net of minus 1.16R that a single winner pulled back from the minus 2R it stood at on Friday. The full trade-by-trade autopsy of the closer is in its own case study, the GBPUSD VWAP and EMA pullback long. This recap is the week around it.
Monday and Tuesday: the gate stayed shut
The week opened with two sessions of nothing. Candidates were flagged on both days; none cleared the confluence threshold; no entries were sized. At the desk's YTD cadence of roughly five trades a week, a two-session drought is rare enough to notice, and the temptation in a system with an audience is to manufacture activity. The system does not have that setting. The cost of a confluence gate is silence when the tape offers nothing.
Wednesday and Friday: two stops inside six minutes each
The first loss filled at 15:13 UTC Wednesday, a GBPUSD post-CPI second-chance long that stopped five minutes and thirty-six seconds later for a flat 1R. Friday at 14:40 UTC a NAS100 post-reversal continuation long stopped four minutes and forty seconds after entry, another flat 1R, and the simulated curve printed its 4 percent trough at $96,000. Both were torn down in the [Jun 8-14 weekly losses report](/en/blog/weekly-losses-2026-06-08). The common thread: each entered on a premise the tape had not yet confirmed, and each was invalidated almost immediately.
The weekend hold: the patient long that came home
The third entry filled Friday at 15:46 UTC, a GBPUSD VWAP and EMA pullback long at 1.34112. Unlike the two quick stops, it never traded against us. It matured slowly across the weekend and closed Sunday night at 1.34349, hitting TP2 for a full-potential +1.28R (TP2) and a realized +0.83R (TP1) on the books. That single winner lifted the week from minus 2R to minus 1.16R. The full decision log is in the [GBPUSD pullback case study](/en/blog/gbpusd-long-vwap-ema-pullback-06-12-2026).
Every trade the system took.
| Date | Time | Instrument | Dir | Model | Setup | Grade | R | $ Sim | Result | Details |
|---|---|---|---|---|---|---|---|---|---|---|
| Jun 10 | 15:13 UTC | GBPUSD | Long | Claude Opus 4.7 | GBPUSD Post-CPI Second-Chance at VWAP/Fib Cluster | C+ | -1.0R(SL) | -$2,000(SL) | Stop hit | Read case → |
| Jun 12 | 14:40 UTC | NAS100 | Long | Claude Opus 4.7 | NAS100 Long - Post-Reversal Continuation | C+ | -1.0R(SL) | -$2,000(SL) | Stop hit | Read case → |
| Jun 12 | 15:46 UTC | GBPUSD | Long | Claude Opus 4.7 | GBPUSD VWAP/EMA Pullback Long | C+ | +0.83R(TP1) | +$1,663(TP1) | TP2 hit · ★ Trade of the week | Read case → |
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.
Pattern of the week
The pattern this week is confirmation, or the lack of it. The two losers both entered before their move had proven itself and both stopped inside six minutes. The winner was a pullback into established structure that the tape had already validated, and it never went underwater. Same desk, same week, and the difference between the red and the green was whether the read waited for confirmation before it sized.
It is a small sample, three trades, so we hold the conclusion loosely. But it rhymes with the prior two windows, where our winners consistently entered after a confirmed continuation and our losers entered into premises that had not yet printed. Patterns that survive across windows are the ones that earn a line in the tuning queue, and confirmation discipline is now firmly on it.
Decision highlights
The stand-downs were the week's quiet wins. Monday, Tuesday, and Thursday produced no entries because nothing cleared the gate, and nobody lowered the gate to generate activity. On a week with only three trades, the discipline of not forcing a fourth is worth saying plainly.
The Risk Agent sized all three entries at the same flat 1R, including Friday's NAS100 long after the week was already 1R down, and Friday's GBPUSD long after a NAS100 stop minutes earlier. No revenge sizing, no fear discount. The give-back stayed bounded precisely because each trade was treated as statistically independent of the last.
Holding the GBPUSD long for 54 hours to TP2, rather than taking the first green after a week of stops, is the decision that turned a minus 2R week into minus 1.16R. The invalidation was never threatened and the structure stayed intact, so there was no reason to exit early. Patience on a valid thesis is its own edge.
Claude vs GPT: who led the week.
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.
- GBPUSD-0.2R · 2 trades
- NAS100-1.0R · 1 trade
Same signals, same risk framework, different foundation model.
Six instruments, six stories.
EURUSD: no trades this week. Nothing on the pair cleared the confluence threshold across five sessions, and the trader stood down.
All EURUSD this week →GBPUSD: two trades, net roughly minus 0.17R. Wednesday's post-CPI second-chance long stopped in under six minutes for minus 1R. Friday's VWAP and EMA pullback long closed +0.83R (TP1) after maturing over the weekend to TP2. A quick loss and a patient winner on the same pair.
All GBPUSD this week →US30: no trades this week. The index never fit the setup criteria; no entry was flagged past threshold.
All US30 this week →NAS100: one trade, net minus 1R. Friday's post-reversal continuation long stopped in four minutes and forty seconds at the reversal structure, printing the week's equity trough.
All NAS100 this week →USDJPY: no trades this week. The pair offered no read that cleared the gate, and the trader stood down.
All USDJPY this week →US500: no trades this week. The trader flagged nothing past threshold; the index sat outside our criteria all window.
All US500 this week →Win of the week: GBPUSD Long · +0.83R
Loss worth learning from
Both of the week's losses are torn down in full in the [Jun 8-14 weekly losses report](/en/blog/weekly-losses-2026-06-08), published alongside this recap. The short version: Wednesday's GBPUSD post-CPI long died on a stop placed five pips from entry in post-data tape, inside the session's noise band, so the thesis was never tested. Friday's NAS100 continuation long placed its stop at real structure but entered before the continuation confirmed, and the speed of the stop says the problem was timing, not stop placement.
The contrast with the week's winner is the lesson. The same GBPUSD trader that lost a quick post-CPI read on Wednesday won a patient pullback on Friday, and the difference was confirmation: the Friday long waited for price to ease back into established VWAP and EMA support before sizing, while the Wednesday and NAS100 entries chased a move that had not yet printed.
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 |
|---|---|---|
| Window netActual | -1.16R | −$2,320 |
All six agents combined.
From the desk
A $100,000 simulated account at 2 percent risk per trade sits at $140,866.91 on the static path through Jun 15, 2026, and at $146,625.69 on the compounded path. The compounded figure runs about $5,759 ahead of static, the receipt for sizing each trade off a growing balance across 110 trades since Jan 12. A minus 1.16R week trims both paths by roughly the same $2,320 on the static line, a normal give-back against a year still firmly positive.
The honest note this week is about the trade we held back. When we first published, this GBPUSD long was open and we refused to book it, because an unrealized position is not a result. It has now closed at +0.83R (TP1), and we have folded it into the week's numbers and written it up on its own in the [GBPUSD pullback case study](/en/blog/gbpusd-long-vwap-ema-pullback-06-12-2026). Two quick stops and one patient winner is a thin week, and the process held through all of it: the gate stayed shut when the tape was empty, the sizing stayed flat, and the one trade worth holding got held.
— The SkyAnalyst Team
What we're tuning
The cooldown gate we floated in the weekly losses reports, a half-grade downgrade on a same-instrument, same-direction re-entry within 72 hours of a stop, just met its most interesting test case. Friday's winning GBPUSD long was filled roughly 48 hours after Wednesday's GBPUSD stop, in the same direction. The proposed gate would have flagged it, and it won. That does not kill the idea, but it does complicate it: a rule that would have penalized this winner needs to clear a high bar on the full back-test before it ships. We let the ledger, not a single outcome, decide.
The other item from this window is a stop-width floor keyed to session volatility, motivated by the two sub-six-minute stops. Both remain in back-test against the YTD record, and we publish why a rule ships or dies rather than quietly changing the engine.
At a Glance
Week at a glance
Why is the week still negative when one trade won?
Because the two losses were a flat minus 1R each and the winner was logged at +0.83R (TP1). Add them and the net is minus 1.16R across three trades. The winner pulled the week back from the minus 2R it sat at on Friday, but one sub-1R winner does not fully offset two full-1R losses. The week was a small, bounded give-back, not a green week.
What happened to the open GBPUSD trade from last week's recap?
It closed Sunday night, June 14, at 1.34349, hitting TP2 for a full-potential +1.28R (TP2) and a realized +0.83R (TP1) that we logged to the track record. We deliberately excluded it from the first version of this recap because it was still open. Now that it has resolved, it is counted in this window and written up in full in its own case study.
Why does the YTD figure differ from when this recap first published?
The first version read +19.60R YTD because the GBPUSD long was still open and uncounted. With that trade now closed and logged at +0.83R, the year-to-date figure is +20.43R across 110 trades at a 58.18 percent win rate. The ledger updates when a trade resolves; that is the point of counting only settled results.
Is the +20.43R YTD figure based on TP1 exits or full-TP exits?
TP1 baseline. Winners are credited at the TP1 R distance and losers at minus 1R, so the periods stay comparable across the year. The single-trade case studies publish full-TP figures for the same trades, which is why the GBPUSD long shows +1.28R (TP2) in its case study but is logged at +0.83R (TP1) here.
Get next week’s trades before they print.
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.
From the SkyAnalyst Journal
GBPUSD: the patient VWAP pullback that took two sessions
Cable stopped us out earlier the same week. The next read, a VWAP and EMA pullback long, needed 54 hours to mature, never traded against us, and closed TP2 at +1.28R full potential.
Weekly Losses: two stops and under eleven minutes in the market
Two closed trades all week, both C+ longs, both stopped inside six minutes of entry. The desk gave back 2R against a +19.60R YTD line, and a third entry was still open when this report went to press.
Jun 1-7, 2026: a Monday hole, a Friday recovery on NAS100
Seven trades. Three losses inside the dollar bid that broke our Monday open and Wednesday cable. One bounce-rejection short on NAS100 that paid the week. A 57.1 percent win rate that owes most of its margin to one outlier.