Meet the Agents

Q Signals is powered by five AI agents, each with a distinct role, personality, and learning journey. They don't compete — they collaborate. Each agent has a soul document that defines who they are, what they stand for, and the rules they will never break. No hype. No fake confidence. Just honest, data-driven intelligence.

Q Signals Issued
Q Win Rate
DQN Training Steps
RL Stage
Q

Q — The Research Analyst

41 modules. Two gates. One honest signal.
Live DQN Learning
"I'm a research tool, not a crystal ball. I'll tell you what 24 independent analysis modules think about a stock — and I'll tell you when they disagree. My job is to surface data clearly, not to tell you what to do with it."

Q is the foundation of the platform. Every signal starts here. Q runs 41 analysis modules — from Fibonacci retracements and Elliott Wave patterns to congressional trading data, candlestick pattern recognition, and Fed minutes sentiment — and combines them into a single composite score. But a score alone isn't enough. Q uses a two-gate system: the composite must exceed a minimum threshold and at least 60% of modules must agree on direction before a signal is issued.

When the gates don't pass, Q says HOLD. No forcing. No rounding up. If only 55% of modules agree, Q waits. That discipline is what separates a signal engine from a random number generator.

Personality
Tone
Research-first. Concise. No hype.
Honesty
Reports confidence honestly. Flags weak signals.
Limits
Never says "buy this" or "sell this." Research output only.
Style
Data over adjectives. Numbers over narratives.

How Q Learns

  • DQN (Deep Q-Network) — 18,307 parameters. 10 offline modules feed into a 10→128→128→3 neural network that learns BUY/HOLD/SELL patterns from experience.
  • Experience Replay — Stores the last 10,000 experiences and trains on random batches of 32, breaking correlation between sequential observations.
  • Target Network — A slowly-updating copy of the main network (Polyak τ=0.01) provides stable Q-value targets during training.
  • Adaptive Module Weighting — Each module's historical hit rate adjusts its influence: effective_weight = base_weight × (0.5 + hit_rate). Modules that perform well get louder. Modules that don't get quieter.
  • Honest Stage Labels — Infant (<500 steps) → Learning (500-5K) → Developing (5K-25K) → Intermediate (25K-100K) → Experienced (100K+). No inflated "Expert" labels.
Last signal: loading…
What Q Monitors
Modules
24 — Fibonacci, Elliott Wave, Candle Patterns (Lao-Tzu), Swing, Volume, Sentiment, Insider, Congress, Fed Minutes, and more
Universe
150+ tickers across 15 sectors (Tech, Semis, Banking, Energy, Healthcare, etc.)
Horizons
Short-term (1d–3mo), Mid-term (3–6mo), Long-term (6mo+)
Output
BUY / HOLD / SELL with 3-tier price targets (conservative, moderate, aggressive), stop-loss, hold duration
Δ

Delta — The Options Architect

The last gate before capital is committed.
Live
"An options strategy cannot fix a bad signal. My job begins after Q has done its work — and my first question is always whether the opportunity deserves to have capital structured around it. When red flags dominate, I say so plainly."

Delta receives Q's confirmed signal and decides how to express it with options — or whether to express it at all. Delta thinks in spreads, not hopes. Every recommendation passes through an auto-critique engine that generates green flags (support), yellow flags (caution), and red flags (disqualifiers). If red flags dominate, Delta says "watch only."

Structure follows signal — Delta never works backward from a favorite strategy. Bullish + high IV → Bull Put Spread. Bearish + low IV → Bear Put Spread. Neutral + high IV → Iron Condor. The mapping is deterministic.

Personality
Tone
Institutional. Precise. Defined risk by default.
Honesty
Auto-critique on every recommendation. Green/yellow/red flags.
Limits
Below 25% confidence → no trade, watch only. Non-negotiable.
Philosophy
Capital efficiency over conviction. Even strong signals get risk-checked.

How Delta Works

  • Signal Validation — Only acts on signals that cleared Q's two-gate system. A single bullish module is noise, not a signal.
  • IV Regime Mapping — Crosses signal direction (bullish/bearish/neutral) with IV rank (high/low) to select the optimal structure.
  • Confidence Gates — <25%: no trade. 25-30%: minimum size only. 30-60%: standard. >60%: full size allowed.
  • DTE Window — 21-45 days. Target zone: 30-38 DTE. Anything shorter gets a warning.
Last recommendation: loading…
Strategy Map
Bullish + High IV
Wheel, Bull Put Spread (credit)
Bullish + Low IV
Bull Call Spread (debit)
Bearish + High IV
Bear Call Spread (credit)
Bearish + Low IV
Bear Put Spread, Long Puts
Neutral + High IV
Iron Condor, Covered Call
Neutral + Low IV
Calendar Spread, Long Straddle
M

Merlin — The Earnings Wizard

Predicting post-earnings moves is the closest thing to sorcery in the markets.
Live
"A wrong prediction with an honest confidence level is valuable. A right prediction with inflated confidence is dangerous. I always tell you how sure I am — and how sure I'm not."

Merlin is the newest member of the council — an earnings prediction agent that combines historical earnings patterns, options-implied move calculations, pre-earnings sentiment momentum, and analyst revision tracking into a single directional call: will the post-earnings move exceed, match, or fall short of what the options market is pricing?

Merlin speaks in probabilities, never certainties. A 65% confidence prediction means Merlin is telling you it's wrong 35% of the time. Most predictions land in the 35-65% confidence range — because earnings are inherently uncertain, and any agent that claims otherwise is lying.

Personality
Tone
Measured. Precise. Like a professor who says "probably."
Honesty
Declines to predict when data is insufficient rather than guessing.
Humor
"Implied says ±4%. Historical says ±8%. Someone's wrong. Historically, it's not the stock."
Philosophy
Predict the move, not the report. Direction and magnitude, not EPS.

How Merlin Predicts

  • Module 1: Historical Patterns (35%) — 8-12 quarters of earnings results. Beat rates, average moves, direction correctness. This is the most reliable signal.
  • Module 2: Implied Move (25%) — ATM straddle price vs historical average move. When history exceeds implied, the market may be underpricing the move.
  • Module 3: Sentiment Momentum (20%) — 7-day pre-earnings news and social sentiment trend. Accelerating bullish sentiment can mean the bar is set too high.
  • Module 4: Analyst Revisions (20%) — Upgrades, downgrades, target price gaps over the past 30 days. Revision velocity signals institutional consensus.
  • Outcome Tracking — Every prediction is logged in Supabase with actual results tracked post-earnings. Performance is measured, not assumed.
Last prediction: loading…
Prediction Output
Predictions
UPSIDE EXCEED / DOWNSIDE EXCEED / NO EXCEED
Confidence
0-100% — honest scale. 80% is rare. Most calls: 35-65%.
Delta Integration
Upside → Bull Call Spread. Downside → Bear Put. No Exceed → Iron Condor.
Warning
0-3 DTE options carry extreme gamma risk. Always flagged.

Lao-Tzu — The Candle Pattern Observer

Observation precedes wisdom. The candles speak — if you know what to look for.
Live
"Most candles are just candles. The ones that matter announce themselves — a hammer at a 52-week low means something different than a hammer in the middle of a range. I don't predict; I observe. And I always tell you what I see."

Lao-Tzu is the visual observer of the council. Named after the philosopher who taught that observation precedes wisdom, Lao-Tzu scans every daily candlestick chart for all 61 TA-Lib recognized patterns — from single-candle formations like Doji and Hammer to complex multi-candle structures like Morning Star, Three White Soldiers, and Abandoned Baby.

Every detection comes with a plain-English explanation of what actually happened in the candles ("Sellers pushed hard all day, then buyers stepped in at the close and erased the damage — that's a hammer"), a confidence score weighted across four factors, and context about where the pattern appeared relative to trend, support/resistance, and 52-week levels. A single candle pattern is a clue, not a verdict — and Lao-Tzu says so.

Personality
Tone
Observational. Calm. Visual-first. Paints a picture with words.
Honesty
"No clear pattern today — the candles are unremarkable." Says so when there's nothing to see.
Style
Plain English. No jargon without explanation. Teaches while analyzing.
Philosophy
One module among many. A clue, not a verdict. Context always matters.

How Lao-Tzu Analyzes

  • 61 TA-Lib Patterns — Full coverage: Doji, Hammer, Engulfing, Morning/Evening Star, Three White Soldiers, Three Black Crows, Harami, Piercing, Dark Cloud, Kicking, Abandoned Baby, Mat Hold, Hikkake, and 48 more.
  • Confidence Scoring — Four-factor weighted formula: pattern strength (35%), volume buildup vs 20d average (25%), breakout potential (20%), 52-week context (20%).
  • Chart Generation — 90-day daily candlestick chart (PNG) with detected pattern candles highlighted, directional arrow, and pattern label.
  • DQN Integration — Candle pattern score feeds directly into Q's DQN state vector as an offline-computable feature. Weight: 7% base (adaptive via hit rate).
  • Graceful Degradation — If TA-Lib is unavailable, returns neutral score (0.0). Never crashes the pipeline.
Integrated into signal pipeline
Pattern Categories
Reversal
Hammer, Engulfing, Morning/Evening Star, Doji Star, Abandoned Baby, Kicking, Three Soldiers/Crows
Continuation
Rising/Falling Three Methods, Mat Hold, Separating Lines, Tasuki Gap
Indecision
Doji variants (standard, long-legged, dragonfly, gravestone), Spinning Top, High Wave
Complex
Three Inside Up/Down, Three Outside, Concealing Baby Swallow, Stick Sandwich, Unique Three River
.laotzu-agent .soul-quote { border-left-color: #A855F7 } .ew-agent .soul-quote { border-left-color: #58a6ff }