AI Stock Picks — FTSE 100

Monday, September 14, 2026  ·  Five AI analysts screened this index for stocks with the best shot at gaining +5% within 30 days

Today's Market Mood

Cautious  Normal choppiness · VIX 16.7

The FTSE 100 is in a broad, sharp risk-off rout, with UK domestic cyclicals (housebuilders, REITs, banks, retailers, defense) down double digits, consistent with sterling weakness and/or fiscal/gilt-market stress rather than a stock-specific issue. Against that backdrop, energy majors, dollar/euro-earning defensives, and a handful of names sitting near their 52-week highs are showing genuine relative strength.

UK domestic risk-off crushing housebuilders, REITs, banks and retailers, likely tied to sterling weakness or fiscal/gilt concernsEnergy majors rallying on rising oil prices, decoupled from the domestic selloffFlight to dollar/euro-earning defensives (tobacco, pharma, staples) as sterling-sensitive multinationals outperformA small group of names holding near 52-week highs signals institutional accumulation even as the broader index falls

Today's Actionable List

Which of today's picks to actually take, and at what size, given what you are already holding. Each pick's own Suggested Allocation sizes it in isolation; this table applies the portfolio limits — at most 20 open positions and 60% of the portfolio committed in total. Run with --capital 25000 to see these sizes as order amounts rather than percentages.

0 of 2
0%
99 · 785.7%
785.7% / 60%
0 of 20
RankStockActionSizeEntry → TargetNotes
#1 SHEL.L SKIP — £3,582.00 → £3,761.10
stop £3,313.35
 Position cap reached — 99 of 20 slots in use.
#2 TSCO.L SKIP — £480.90 → £504.94
stop £444.83
 Position cap reached — 99 of 20 slots in use.

Already open: CPAY (to Sep 16), GPN (to Sep 16), STT (to Sep 16), STJ.L (to Sep 16), SCHW (to Sep 17), TRGP (to Sep 17), AV.L (to Sep 17), PSN.L (to Sep 17), SMT.L (to Sep 18), ABBV (to Sep 19), EOG (to Sep 19), VRTX (to Sep 19) … and 87 more. Symbols you already hold were excluded from this run's candidates rather than re-picked.

Position-sizing guidance only — half-Kelly per pick, bounded by the limits above. Not personal investment advice.

Behind the scenes: how each AI analyst did
Aria
2 picks
Blaze
2 picks
Nova
No picks
Every candidate's news search returned only generic, unrelated market headlines rather than any company-specific event, and the one truly empty case (AstraZeneca) failed the price-action fallback due to negative recent momentum. Without a verifiable catalyst, none of these FTSE 100 names meet the bar for a news-driven pick this cycle, even where broader price action looks resilient.
Orion
2 picks
Quinn
4 picks

2 Stock Picks

#1 SHEL.LShell plc
4/5 Agents Agree  Risk 4/10  ⚠ Conflicting Signals
Strong conviction · 62%

Shell is one of the world's biggest oil and gas producers. Its shares have surged over the past month and now sit right at their highest point in a year, and energy companies are one of the few groups holding up while the rest of the UK market sells off on currency and government-debt worries. The main risk is that the stock has climbed so fast it looks 'overbought,' so a pause or pullback wouldn't be surprising.

Stop-loss£3,313.35-7.5%
Today's price£3,582.00
Target£3,761.10+5.0%
If you invested £1,000
▲£1,050 if the target hits (+5.0%)
▼£925 if the stop-loss is hit (-7.5%)
The AI puts the chance of the win case at 62%. Not a guarantee — always set the stop-loss.

Why the AI likes it

What could go wrong

⚔ The Skeptic's View — Sage, the Devil's Advocate
  • RSI(14) is at 72.08, in overbought territory, and price is pinned against the upper Bollinger Band (3577.37 vs. price 3582.0), raising the odds of a near-term pullback rather than further upside.
  • OBV sits at 253.3M with no divergence flagged, and the stock is only 4.70% off its 52-week high, meaning most of the easy relative-strength gain versus the 8.14% benchmark spread may already be priced in.
Show the detailed analysis

Calibrated probability: 62% (raw model estimate: 64%) — adjusted using the accuracy of past resolved picks.

Trade math

0.7:1
60%
+0.5%
7%

Suggested allocation is half-Kelly sizing guidance capped at 10% — not personal investment advice. Allocations are scaled to 70% of half-Kelly for the current market regime.

What each AI analyst estimated

Aria
65%
High
Blaze
53%
Medium
Nova
—
—
Strong price momentum and near 52-week highs, but no company-specific news catalyst was found — only unrelated general market headlines — so there's no event to explain or sustain the move.
Orion
76%
Very High
Quinn
60%
Medium

Data Sources

Yahoo FinanceFinvizMarketWatchSeeking Alpha
#2 TSCO.LTesco PLC
3/5 Agents Agree  Risk 5/10  ⚠ Conflicting Signals  ⚠ Earnings in Window
Strong conviction · 62%

Tesco is the UK's largest supermarket chain, selling groceries and general merchandise both in stores and online. Its shares are up over the past month, have cleared both their 50-day and 200-day trend lines, and are outperforming the wider UK market even as many other domestic retailers struggle in the current sterling/gilt-driven sell-off, suggesting the company has its own positive momentum separate from sector-wide pressure. The main risk is that this is still a low-growth grocery stock in a shaky UK consumer environment, so any wobble in sentiment could quickly erase the recent gains.

Stop-loss£444.83-7.5%
Today's price£480.90
Target£504.94+5.0%
If you invested £1,000
▲£1,050 if the target hits (+5.0%)
▼£925 if the stop-loss is hit (-7.5%)
The AI puts the chance of the win case at 62%. Not a guarantee — always set the stop-loss.

Why the AI likes it

What could go wrong

⚔ The Skeptic's View — Sage, the Devil's Advocate
  • 5-day momentum has effectively stalled at just 0.01%, versus the 30-day return of 4.20%, suggesting the rally has lost near-term thrust even though RSI(59.9) isn't overbought.
  • OBV is deeply negative at -93.8M despite the price gain, an accumulation/distribution divergence indicating volume has skewed toward selling even as price rose — a caution flag not captured by the moving-average or RSI reads.
Show the detailed analysis

Calibrated probability: 62% (raw model estimate: 61%) — adjusted using the accuracy of past resolved picks.

Trade math

0.7:1
60%
+0.1%
7%

Suggested allocation is half-Kelly sizing guidance capped at 10% — not personal investment advice. Allocations are scaled to 70% of half-Kelly for the current market regime.

What each AI analyst estimated

Aria
72%
Very High
Blaze
51%
Low
Nova
—
—
Modest 30-day gain with no identifiable catalyst in the news; the move looks unremarkable and unexplained.
Orion
—
—
UK domestic grocery retailer earning mostly in sterling — falls in the domestic-cyclical category hit hardest by the current risk-off rout, not the global/dollar-earner rotation theme.
Quinn
60%
Medium

Data Sources

Yahoo FinanceFinvizMarketWatchSeeking Alpha

Retail Investor Execution Guide

This report identifies stocks with an AI-assessed probability of gaining +5% within 30 calendar days (target exit by October 14, 2026). Picks are ranked by how many independent AI agents agreed — more agreement means higher conviction. The guide below tells you exactly how to act on them.

Step-by-Step Action Plan

  1. Act within one trading day. Prices are freshest now. The longer you wait, the more the entry price drifts away from what the agents analysed.
  2. Verify the entry price. Check the live price before buying. If a stock has already moved more than 3% above the Current Price shown in the report, skip it or wait for a pullback — the risk/reward has shifted.
  3. Use limit orders, not market orders. Set your buy limit at or below the Current Price shown. Chasing with a market order gives brokers and algorithms an advantage over you.
  4. Set your stop-loss immediately after buying. Use the Max Downside % on each pick card as your hard exit level. If the price falls to that level, sell without hesitation — the trade thesis is broken.
  5. Set a take-profit at the Target Price. Place a limit sell order at the Target Price shown. When it fills, the trade is done — resist the urge to hold for more.
  6. Exit all positions by October 14, 2026. This is your hard deadline. If a stock has not hit its target by then, exit anyway. Holding past the window turns a short-term trade into an unsupervised long-term position.
  7. Never add to a losing position. If your stop-loss is hit, exit completely. Averaging down turns a small, controlled loss into a potentially large one.

Position Sizing by Conviction Tier

Size each position according to the coloured border on its pick card. Cap your total exposure across all picks from this report at 25% of your overall trading budget.

Agents Agreeing What It Means Max Allocation Per Pick
5/5 Highest conviction — all five independent analytical checks passed Up to 10%
4/5 Very high conviction — four of five independent checks aligned Up to 8%
3/5 High conviction — three agents independently agreed Up to 6%
2/5 Moderate conviction — two agents independently agreed Up to 4%
1 Agent Speculative — solo pick, admitted only at Very High confidence Up to 2%

The Three Exit Rules

These picks are generated by AI agents for informational and educational purposes only. They do not constitute financial advice or a recommendation to buy or sell any security. Probability estimates reflect the agents' analytical models — they are not guarantees of any outcome. Past results are not indicative of future performance. Markets can and do move against even well-researched trades. Always conduct your own research, and consider seeking advice from a licensed financial adviser before placing any orders. Never invest money you cannot afford to lose.

Understanding the Numbers

A plain-English guide to every figure shown on each pick card — what it means, how it is calculated, and what a good or bad value looks like.

AI Conviction Meter
Estimated probability of hitting the target, shown as a 5-bar gauge
The filled bars and label translate the AI's probability estimate into plain language: 75%+ is Very strong, 60–74% Strong, 50–59% Moderate, below 50% Cautious. Where enough past picks have been resolved, the probability is calibrated against the AI's real track record.
e.g. "Moderate conviction · 58%" — the AI thinks this trade works slightly more often than a coin flip.
✓ More filled bars = more confidence — but even Very strong picks fail sometimes; always size positions accordingly.
If You Invested $1,000
$1,000 × (1 + Target Gain ÷ 100)  /  $1,000 × (1 + Max Downside ÷ 100)
The same Target Gain and Max Downside percentages expressed in concrete money terms for a $1,000 position — what you'd have if the target hits versus if your stop-loss is triggered.
e.g. +10% target and −12.3% stop → $1,100 on a win, $877 on a stopped-out loss.
✓ Scales linearly — a $500 position sees half these amounts, a $2,000 position double.
Current Price
Market price at time of analysis
The stock's price when this report was generated. All other figures on the card are calculated from this reference point.
e.g. $215.20 — check the live price before placing an order; if it has moved more than ~3%, re-evaluate the risk/reward.
✓ No positive/negative distinction — it is simply your cost basis.
Target Price
Current Price × (1 + Target Gain ÷ 100)
The price the agents project the stock could reach within the time window. This is your take-profit level — place a limit sell order here after buying.
e.g. $215.20 × 1.085 = $233.49 target on an 8.5% pick.
✓ Always above Current Price — this tool only selects upside candidates.
Target Gain
(Target Price − Current Price) ÷ Current Price × 100
The percentage return you would earn if the stock hits its Target Price from your entry. Set by the run parameters — every pick in this report targets the same percentage.
e.g. +8.5% means a $100 stock has a $108.50 target; a $500 stock has a $542.50 target.
✓ Always positive — picks are upside-only. A larger % means a bigger move is required.
Max Downside
Estimated stop-loss level, as % below entry
The worst-case loss the agents estimated if the thesis fails — based on key support levels and recent volatility. Use this as your hard stop-loss. If the price falls to this level, exit immediately; the trade thesis is broken.
e.g. −12.0% means: if you bought at $100, sell if it drops to $88.00.
⚠ Always negative. A smaller magnitude (e.g. −5%) = tighter risk. A larger magnitude (e.g. −20%) = more room to fall before you exit — riskier.
Reward : Risk
Target Gain ÷ |Max Downside|
How much you could gain for every dollar you are risking. A ratio of 2.0:1 means you stand to make $2 for every $1 at risk. Higher is better.
e.g. 8.5% gain ÷ 12% downside = 0.7:1 (unfavourable). 10% gain ÷ 5% downside = 2.0:1 (good).
✓ ≥ 2.0:1 is strong. ⚠ < 1.0:1 means you are risking more than you could gain — approach with caution.
Breakeven Win Rate
|Max Downside| ÷ (Target Gain + |Max Downside|) × 100
The minimum percentage of trades at this reward:risk that must succeed for you to break even over time — regardless of how good your stock picking is.
e.g. 12 ÷ (8.5 + 12) = 59% — you need roughly 6 in 10 trades to win just to avoid losing money.
✓ Lower is better — ≤ 35% means even a poor win rate is survivable. ⚠ ≥ 55% means you need most trades to work out.
Expected Value
(Probability% × Target Gain%) + ((1 − Probability%) × Max Downside%)
The average return per trade if the AI's probability estimate is accurate over many similar trades. A positive Expected Value means the trade has a mathematical edge; a negative value means the math works against you on average, even if you sometimes win.
e.g. 65% × +8.5% + 35% × −12% = +1.3% EV. Over 100 similar trades you would expect an average gain of 1.3% per trade.
✓ Positive = edge in your favour over many trades. ⚠ Negative = the math loses money on average — even if individual wins feel good. Note: EV is only as reliable as the probability estimate.
Suggested Allocation
half-Kelly: (Probability ÷ |Max Downside| − (1 − Probability) ÷ Target Gain) ÷ 2, capped at 10%
The Kelly criterion computes the portfolio fraction that maximises long-run growth for a bet with these odds; half-Kelly is the standard hedge against the probability estimate being too optimistic. Uses the calibrated probability where available. 0% means the math sees no edge worth sizing; — means it couldn't be computed.
e.g. 57% probability, +10% target, −13% downside → Kelly ≈ 8.5% of portfolio, half-Kelly ≈ 4.2%.
Generic sizing guidance only — not personal investment advice. Position sizing must reflect your own portfolio, risk tolerance and circumstances.
Every stock Scout considered — and why each was discarded

Scout scanned 100 FTSE 100 constituents and short-listed 22 candidates for deep analysis by the five analysts. Here is what happened to each one.

  • VOD.LVodafone GroupAlready held
    Scout: Strong 5-day and 30-day momentum (+3.9%/+7.2%) and sitting just 0.6% off its 52-week high despite the broad market rout — clear relative strength.
    Already held: a position opened 2026-09-09 runs until 2026-10-09 (25 day(s) left). Re-picking it would concentrate the portfolio, not diversify it.
  • BP.LBP p.l.c.Already held
    Scout: Leading the index with +4.5% over 5 days and +9.2% over 30 days on the oil rally, a genuine sector tailwind rather than a one-day spike.
    Already held: a position opened 2026-08-20 runs until 2026-09-19 (5 day(s) left). Re-picking it would concentrate the portfolio, not diversify it.
  • SHEL.LShell plcPicked #1
    Scout: Similar energy-sector strength to BP, up nearly 8% over 30 days and only 4.7% off its 52-week high while most of the index sells off.
    Made the final report at #1.
  • TSCO.LTesco PLCPicked #2
    Scout: Defensive grocery name showing steady positive momentum (+1.4%/+4.2%) while discretionary retail peers are down sharply — a flight-to-staples beneficiary.
    Made the final report at #2.
  • STAN.LStandard Chartered PLCAlready held
    Scout: Asia-focused bank with limited UK domestic exposure, up over the last week and month and just 1.4% from its 52-week high, in sharp contrast to UK-domestic lenders selling off double digits.
    Already held: a position opened 2026-09-03 runs until 2026-10-03 (19 day(s) left). Re-picking it would concentrate the portfolio, not diversify it.
  • HSX.LHiscox LtdAlready held
    Scout: Insurer up nearly 5% over 30 days and only 1.2% from its 52-week high, showing it is largely insulated from the domestic-cyclical selloff.
    Already held: a position opened 2026-09-01 runs until 2026-10-01 (17 day(s) left). Re-picking it would concentrate the portfolio, not diversify it.
  • BEZ.LBeazley plcAlready held
    Scout: Essentially at its 52-week high (-0.08%) while the index is in a broad rout — a strong signal of relative strength worth watching for continuation.
    Already held: a position opened 2026-09-02 runs until 2026-10-02 (18 day(s) left). Re-picking it would concentrate the portfolio, not diversify it.
  • ITRK.LIntertek Group plcAlready held
    Scout: Flat and virtually at its 52-week high (-0.09%) during a day when most of the index is down double digits — textbook resilience.
    Already held: a position opened 2026-09-08 runs until 2026-10-08 (24 day(s) left). Re-picking it would concentrate the portfolio, not diversify it.
  • AZN.LAstraZeneca PLCDropped at merge
    Scout: Up over 6% on a 30-day basis; as a globally diversified, largely dollar-earning pharma major it is a natural beneficiary if sterling weakness is driving the domestic selloff.
    Average probability across the 2 agent(s) that selected it was 56% raw (48% after calibration), below the 58% minimum to qualify.
  • CCH.LCoca-Cola HBC AGDropped at merge
    Scout: Strong recent momentum (+3.7% over 5 days) in a defensive beverages name, bucking the broad decline.
    Only Quinn selected this stock — Quinn solo picks require High or Very High confidence and at least 60% probability (this pick: Medium, 60% raw (62% after calibration)).
  • BATS.LBritish American Tobacco p.l.c.Passed over
    Scout: Up 3.7% over the last week; a classic defensive, overseas-earnings name that tends to benefit from sterling weakness and risk-off rotation.
    Aria: 5-day momentum is negative and on-balance volume shows divergence from price, a warning sign
    Blaze: Price is below both its 50-day and 200-day averages, with falling trading volume despite the price holding near recent levels — a bearish signal.
    Nova: Weak, flat price action with a bearish volume divergence flag and no identifiable news catalyst.
    Orion: Only marginally positive over 30 days, trading below its moving averages, with trading-volume flow diverging bearishly from the price.
    Quinn: On-balance volume divergence (price rising without volume support) drags the score down to the 50% probability floor with weak conviction — a real institutional-distribution warning sign.
  • IMB.LImperial Brands PLCPassed over
    Scout: 5-day return has turned positive (+3.3%) even though the 30-day figure is still negative, suggesting a recent reversal in a defensive tobacco name.
    Aria: Share price is down over the past month and lagging the market, failing the trend requirement
    Blaze: 30-day price return is negative, failing the basic positive-trend requirement.
    Nova: Share price is down over the past month with no catalyst in sight — a genuine negative signal, not a data gap.
    Orion: Down over the past 30 days, failing the basic positive-trend requirement.
    Quinn: 30-day return and 5-day momentum are both negative and the price sits below its 50- and 200-day averages — a single positive MACD tick isn't enough to offset the broader downtrend.
  • ULVR.LUnilever PLCPassed over
    Scout: Positive across both windows with a resilient share price; a global staples multinational well-placed to benefit from any sterling weakness driving the domestic rout.
    Aria: 5-day momentum has turned sharply negative (-2.8%), failing the momentum screen despite a positive month
    Blaze: Price is essentially flat against its short-term average, with negative recent momentum and a bearish MACD reading.
    Nova: Price has been fading over the last 5 days and no specific catalyst was found in the news.
    Orion: Momentum turned down over the last week and shows a bearish MACD crossover, offsetting the modest monthly gain.
    Quinn: MACD histogram is negative with no Bollinger squeeze or golden cross — none of the quantitative setup triggers are met.
  • CPG.LCompass Group PLCPassed over
    Scout: 5-day return has swung positive (+2.1%) despite a negative 30-day figure, and its largely US-based catering revenue insulates it from UK-specific stress.
    Aria: Share price is down over the past month and underperforming the market, failing the trend requirement
    Nova: Share price down over the past month with no news catalyst to explain a reversal.
    Quinn: MACD histogram is razor-thin (+0.07, essentially noise) and the 30-day return is negative (-2.09%) — too weak a signal to act on.
  • EXPN.LExperian plcPassed over
    Scout: Recent reversal to positive 5-day momentum (+1.8%) in a globally diversified data/analytics business less exposed to UK domestic risk.
    Aria: Share price is down over the past month with negative 5-day momentum, failing both trend checks
    Blaze: 30-day return is negative and the stock remains well off its 52-week high with no confirmed catalyst for a rebound.
    Nova: Both the monthly return and recent momentum are negative, and no catalyst was found.
    Orion: Down over the past 30 days with weakening momentum, failing the positive-trend requirement.
    Quinn: MACD histogram is negative, no squeeze or golden cross is present, and both the 30-day return and 5-day momentum are negative.
  • PSON.LPearson plcPassed over
    Scout: 5-day return has turned positive (+2.6%) even as the broader market sells off, a notable divergence worth watching for follow-through.
    Aria: Share price is down over the past month with negative 5-day momentum, failing both trend checks
    Nova: Slightly negative monthly return and no identifiable catalyst in the news.
    Quinn: MACD histogram is negative and RSI is near neutral — none of the setup trigger conditions are satisfied.
  • BT-A.LBT Group plcAlready held
    Scout: Positive on both the 5-day and 30-day windows (+2.7%/+2.2%), showing steadier footing than most domestic-facing names today.
    Already held: a position opened 2026-08-21 runs until 2026-09-20 (6 day(s) left). Re-picking it would concentrate the portfolio, not diversify it.
  • GSK.LGSK plcPassed over
    Scout: Modest but consistent positive momentum across both windows in a globally diversified pharma name, a likely relative safe haven.
    Blaze: Recent 5-day momentum turned negative and the price sits below both key moving averages despite a modest 30-day gain.
    Nova: Price has been fading over the last 5 days and no company-specific catalyst was found.
    Orion: Trading below both its 50-day and 200-day averages with momentum fading over the last week, despite a modest monthly gain.
    Quinn: MACD histogram is negative, the 50-day average sits below the 200-day average, and 5-day momentum is negative.
  • SDR.LSchroders plcAlready held
    Scout: Only 2.3% off its 52-week high with mildly positive momentum, standing out against the sharp declines in UK financials broadly.
    Already held: a position opened 2026-09-09 runs until 2026-10-09 (25 day(s) left). Re-picking it would concentrate the portfolio, not diversify it.
  • REL.LRELX PLCPassed over
    Scout: Positive across both the 5-day and 30-day windows in a globally diversified data/analytics business, showing steadier momentum than the broader index.
    Blaze: Recent momentum has turned negative and the stock is sitting right at its 200-day average with no clear catalyst to push it higher.
    Nova: Price has been fading over the last 5 days and no company-specific catalyst was found.
    Orion: Monthly gain has been fading over the last week, trades near/below its 200-day average, and its sector wasn't confirmed as a rotation beneficiary.
    Quinn: MACD histogram is negative and there's no Bollinger squeeze — despite a positive 30-day return, no setup criteria are met.
  • AAF.LAirtel Africa PlcAlready held
    Scout: 30-day return of +4.6% reflects underlying strength despite a modest short-term pullback, in an emerging-markets telecom largely decoupled from UK domestic risk.
    Already held: a position opened 2026-09-03 runs until 2026-10-03 (19 day(s) left). Re-picking it would concentrate the portfolio, not diversify it.
  • BGEO.LLion Finance Group PLCLiquidity filter
    Scout: Trading just 2.5% off its 52-week high with only a marginal pullback, a Georgia-focused bank insulated from the UK-specific selloff hitting domestic lenders.
    20-day average daily volume 62,187 shares is below the 500,000-share liquidity floor.

Agent Analytical Approaches

Aria

Momentum & Technical

Checks 30-day price history for every candidate before making any selection. Requires positive period return and positive 5-day momentum as mandatory gates. Ranks picks by proximity to their period high and adjusts probability based on volume. Uses news only to rule out major negative catalysts.

Blaze

Fundamental & Earnings

Searches earnings results, analyst upgrades, and revenue trends before checking price data. Requires at least one verifiable fundamental catalyst — earnings beat, analyst upgrade, or revenue acceleration — within the last 60 days. Favours stocks with strong fundamentals trading below recent highs (value entry).

Nova

News Catalyst & Event-Driven

Hunts for specific events within the last 21 days: FDA approvals, major contract wins, product launches, earnings surprises, or significant analyst upgrades. Requires a positive price reaction confirming the market is recognising the catalyst. Also scans for upcoming events that could drive further gains.

Orion

Macro & Sector Rotation

Maps the macroeconomic regime (risk-on / risk-off / neutral) and identifies sectors benefiting from current conditions before looking at individual stocks. Only selects stocks from macro-aligned sectors with confirmed sector tailwinds. Adjusts for interest rate sensitivity and geopolitical factors.

Sage

Devil's Advocate

Reviews the final picks after all four analysts agree and actively challenges each bull thesis. Searches for bearish technical signals, negative news, insider selling, and elevated short interest that the agreeing agents may have underweighted. Produces evidence-based counter-arguments shown on each pick card.

Quinn

Quantitative / Statistical

Pure-quant analyst: no news, no narrative, only numbers. Identifies mean-reversion setups from RSI extremes (<35) with momentum turning, Bollinger squeeze breakouts, and multi-factor quant scores using RSI, MACD, OBV, short interest, and insider transaction data. Counterbalances narrative bias across the four analyst agents.