Recommendations
1 to acquire · 3 to dispose
| Ticker | Name | Close | Action | Action Price Where to act — a buy-limit on a pullback or a buy-stop above resistance, not the current price. Sanity-check vs Close: on a held name, an action price stranded above the close means the queued level was set when the stock was higher — stale, awaiting reprice. | Stop The risk-defined exit, set below the entry for a long (~1.2–1.8×ATR). A held long whose Stop sits at/above the Close is already below its stop — a stale box awaiting reprice. | 1wk Model estimate of the likely price at this horizon — a forward projection, not a guarantee, and separate from the trade's Action Price or Stop. Where the ML estimator is enabled these are per-ticker calibrated forecasts (~80% coverage band) that are refreshed periodically and can drift between refreshes; otherwise they're interpolated from the signal's swing target. Confirm against the settled close. | 4wk Model estimate of the likely price at this horizon — a forward projection, not a guarantee, and separate from the trade's Action Price or Stop. Where the ML estimator is enabled these are per-ticker calibrated forecasts (~80% coverage band) that are refreshed periodically and can drift between refreshes; otherwise they're interpolated from the signal's swing target. Confirm against the settled close. | 12wk Model estimate of the likely price at this horizon — a forward projection, not a guarantee, and separate from the trade's Action Price or Stop. Where the ML estimator is enabled these are per-ticker calibrated forecasts (~80% coverage band) that are refreshed periodically and can drift between refreshes; otherwise they're interpolated from the signal's swing target. Confirm against the settled close. | Rationale |
|---|---|---|---|---|---|---|---|---|---|
| VIST | Vista Energy, S.A.B. de C.V. | 70.50 | BUY | 70.50 | 68.78 | 70.80 (+0.4%) | 72.09 (+2.3%) | 75.75 (+7.4%) | Argentina's largest independent shale producer is the first genuinely cheap, quality-passing name this book has been able to buy in weeks: it trades at against an intrinsic value, ranks 10th of 52 on quality with a Piotroski F-score of 7, and Peter Thiel's Thiel Macro has just disclosed a ~1% stake worth roughly. The chart agrees — the stock reclaimed its 20-day range after a failed breakdown, closed up 3.0% on the session, and sits exactly at the model's entry price, so we are paying up for nothing. Wall Street consensus is Strong Buy with a mean target of corroborating the valuation case from an independent direction. OPS: adj conviction 78 +2 (val) -7 (FailedBreakdown_Up_20D bias) = 73, clear of the 65 floor; raw 78 also clears the L1/US-10 chase-family bar of 75, so the trap cell is passed on merit not waived. Entry_Distance_ATR 0.00 = no chase. Size 0.4924 x 200k x 20% x 1.25 (UNDERVALUED + Quality_Pass) = ->. Honours the 08-19 pre-commitment to re-arm on a live Entry_Price. Est_12W 75.75 sits BELOW the 86.44 DCF anchor - healthy direction, no overshoot flag. Target_Price 77.37 is the risk objective, distinct from the 4wk estimate. · news |
| KLAC | KLA Corporation | 185.86 | SELL 30% | 185.86 | 184.00 | 187.23 (+0.7%) | 183.54 (-1.2%) | 178.61 (-3.9%) | We are cutting a third of KLA on risk discipline, not on a view about the company. The protective stop under this position has walked down from to - a 32% retreat over seventeen sessions - while the position itself was never once reduced. A risk line that keeps stepping away from a holding that never shrinks is a risk failure, and this trim closes it. The 12-week projection has also rolled below the current price. Crucially, the drawdown is sector-wide, not company-specific: Applied Materials and Lam Research are down more than 20% on the month too, while JPMorgan raised its KLA target to and named it their top semi-cap pick and Cantor went to That is why we trim and keep rather than exit. OPS: ADR-0020 Trail Erosion -32.35%, session 17, FIRST fire on the 272.00 watermark -> VETO-IMMUNE to US-17/US-18/US-34/US-22/US-30 per US-36. DE-ESCALATED 50% -> 30% under US-32: the ADR-0012 leg is blocked by US-33 (armed via T12_Progress 104.06 limb, tick (c) reads the same metric; cv rose so no tick (b); label AVOID so no tick (d)) and the 184.00 line held today. Valuation amplify SUPPRESSED by G2 (T12 178.61 / DCF 61.80 = 2.89x). US-12/US-22 sector-washout playbook governs the retain-the-remainder call. 2nd consecutive settled close below the pre-cut 193.38 corroborates (L2). Peak Stop re-bases to 184.00 ONLY on the observed fill. · news |
| NET | Cloudflare, Inc. | 278.91 | SELL 30% | 278.91 | 283.72 | 280.65 (+0.6%) | 279.13 (+0.1%) | 287.08 (+2.9%) | Cloudflare has broken the line we committed to in advance, so we take the pre-agreed 30% off. The stock closed at, below both the protective level and, for a fourth straight session, the older line - and the model's own four-week projection is now dead flat at +0.1%. We honour the trigger rather than argue with it. Note what tonight's 4.4% drop was NOT: it was dilution read-through from Nebius pricing a $5bn convertible, not a Cloudflare event - CoreWeave held its range on the same session. Because there is no company-specific crack in the thesis, this is a trim to, not an exit. OPS: US-34 satisfied via the INVALIDATION limb (close below a pre-committed line), not a lone label flip. L3 - this card has now been re-issued twice unexecuted. Valuation amplify SUPPRESSED by G2 (T12 287.08 / DCF 29.51 = 9.73x). The monitor MISSED this breach - duplicate NET row in usportfolio.json makes the loader read / Held=N (systemic #2). Peak Stop UN-REBASED to 301.75 - the 08-19 re-base was written against a cut that never filled. · news |
| GOOGL | Alphabet, Inc.- Class A | 340.67 | SELL 30% | 340.67 | 332.73 | 341.43 (+0.2%) | 341.82 (+0.3%) | 369.61 (+8.5%) | Banking a third of a position that has more than doubled - up 177% on cost - while the signal has gone silent for seven straight sessions. Alphabet has just announced a sweeping overhaul of its AI leadership including the departure of Jeff Dean, and lifted 2026 capex guidance to -205bn with more flagged for 2027; the stock now trades below its 10-day average and its volume-weighted price at a neutral RSI of 44. That is a genuine margin overhang on a name that has stopped advancing. We are taking profit, not exiting: the 12-week projection is still +8.5% and consensus sits at with 58 buy ratings and no sells, so stay on. OPS: ADR-0012 armed via the Gain_ATR limb (31.35) NOT the T12 limb, so US-33 does not apply and US-26 is satisfied (Gain_ATR +31.35 AND Unreal_PnL +176.97%, both positive). Fire tick (d): seven consecutive NO TRADE. Tick (c) does NOT fire - T12 369.61 > 1.02 x 340.67 = 347.48. Single soft tick -> profit_take_1 = 30%; US-19 execute the FIRST fire, no day-by-day escalation. MoS -0.68 is above the -3 amplify threshold so no tier bump. This card was displaced to queue position 4 on 08-19 with an explicit promise of 'first card next session' - deferring again would be the exact US-37 stalemate. Trail held 332.73. · news |
| NVDA | NVIDIA Corporation | 216.85 | HOLD | — | 217.07⚠ | 217.58 | 218.52 | 233.08 | Holding NVIDIA through its earnings on 26 August rather than trimming into the print. The position has reached 93% of its 12-week objective and the signal has gone quiet, which would normally argue for taking something off - but with results four sessions away and a plausible 6.75% move in either direction, cutting now is a coin-flip dressed up as discipline. The close of is a tenth of a percent under our trailing stop: technically through it, but not decisively. OPS: ADR-0012 armed via T12_Progress 93.04 + tick (d) two consecutive NO TRADE - FIRE SUSPENDED by the CLAUDE.md catalyst-aware hold (earnings 2026-08-26, 4 sessions, horizon band +/-6.75%, stance hold-through). PRE-COMMITTED: a DECISIVE settled close below 217.07 fires SELL 30% immediately, catalyst hold notwithstanding. Avg_Cost blank in usportfolio.json so the US-26 arm verification cannot be completed by hand - fill the. |
| OKTA | Okta Inc. | 134.16 | NO ACTION | — | 140.55⚠ | 134.78 | 142.92 | 150.77 | Okta closed 4.6% below its protective stop and the signal flipped to no-trade, which is a real warning - but it is the first such print, and the model still projects the stock 6.5% higher in four weeks and 12.4% higher in twelve. This book's most expensive repeated error is selling on a single bad session into a flush, so we decline tonight and commit the trigger in writing instead. Nothing has cracked in the business: revenue guidance of -794m is intact, the stock is still up 70% this year, and Q2 results land on 26 August. OPS: US-18/US-34 primary gate - single settled print, forward view alive, so L2's stop-break-plus-NEGATIVE-12wk combo is NOT met. Event Horizon carries a trim-into stance on the 08-26 earnings (+/-10% band) - advisory, overlay/CLAUDE.md catalyst-hold outranks. Valuation WOULD have amplified here - MoS -5.01 with T12 150.77 / DCF 107.59 = 1.40x, the ONLY name tonight where G2 does not suppress - and the amplify is declined on single-print grounds. PRE-COMMITTED TRIGGER (US-35): a 2nd consecutive settled close below 140.55, OR any settled close below tonight's 133.12 low, fires SELL 30% immediately. Trail held 140.55; queue position 4. · news |
| MU | Micron Technology, Inc. | 974.33 | HOLD | — | 929.07 | 983.53 | 1030.66 | 1203.49 | Micron was the one line carrying the book tonight, up 4.0% to on high-bandwidth memory demand while everything else gave ground. It is the highest-quality name we own on the fundamental screen - ranked 1st of 52 - sits 13% above cost, and the model still projects 23% upside over twelve weeks. We are not touching the position; we are raising the protective stop under it to, exactly today's low, so the gain is progressively locked in. OPS: trail RAISED 921.42 -> 929.07; US-29 permits tightening, refuses loosening. No Exit_Warning, Gain_ATR 1.96, T12_Progress 80.96 - not armed. ADR-0020 erosion 0%. |
Outcome & track record
Accuracy at the time of this record.
149 Graded decisions Past recommendations old enough to score against what actually happened (target hit / stopped out / closed). This is the evidence base — the bigger the number, the more history behind the calls. Click to inspect every one. See the decisions →
-0.148 1-week calibration How much of the eventual 4-week move typically shows up in the first week (0 = almost none, 1 = most of it). Use it to read the 1-week estimates: a low number means prices drift toward the target slowly, so don't over-read a soft week-1.
52 Published records How many dated end-of-day verdicts exist for this book — the length of the public track record you can browse in the Archive below.