Gap-down open that paid the fade, then the long side
Two dozen gap-downs on the scanner set our desk up for short-to-pop entries at the gap-close levels, and the first two worked cleanly with adds on confirmation and stops parked above the highs. As the tape firmed, the read flipped to buying pullbacks into VWAP and the open, with one memory name scaled out in thirds and a stop auto-moved to break even after the first target.
The 1h 09m session is on the other side of this.
Everything above is the write-up. This is the morning itself, with the names on every call and the room talking through it.
The premarket scan handed the desk a list of gap-downs and a plan that said short into the first pop, long only where the name had shown strength. The first fade was taken at the gap-close order level, added to once it held, with the stop placed above the session high rather than at a round number. The second fade in a broker name ran further and was scaled out in pieces on the way down, the last piece taken rather than held for more — a choice that got talked about openly afterward as the whole point of working targets.
“It turns out to be a lot harder to build a proper backtest engine with AI than I ever expected.”
He thought AI would make a backtest engine easy. 8 months and 9 rebuilds later...
Once the fades were flat, the read changed. A retail broker was bought on the flush and closed quickly, and an e-commerce name was worked off VWAP, scaled into two pieces, then stopped out on the re-entry when the low gave way — a twenty-cent stop set deliberately under the prior low, taken without a second attempt. The memory long was the cleanest expression of the day: entered off the cross with the stop under the lows, first target hit, stop auto-moved to break even, and the remainder held into a full scale-out. The short attempt in the same name afterward was sized against a stop that was too wide until a retest tightened it, missed its first target by pennies, and came off flat.
The last trade was a search-name long off the lower band after a double top and lower high had been called out on the tape, scaled out in three and closed before the desk shut down. No one chased the headline-driven pop in the AI names, which was noted, mocked, and left alone.
The morning in figures
Net points are per share. Apply your own size to get your own number: at 1,000 shares, 5.14 points is $5,140.00. At 100 shares it is $514.00. At one share it is $5.14. The desk publishes the move, not a dollar result, because the dollars depend entirely on how you size, and that is your decision rather than ours.
Every trade called that morning
Losers included. Rows with more than one leg were scaled out; open any row to see each exit.