Personalize The Agent for your trading style—40+ screenable strategies, playbooks, and filters tied to a transparent six-step pipeline
The Agent is your personalized AI trading assistant. Unlike a one-size-fits-all approach, you control:
Choose which breadth indicators and market data feed into the market diagnosis.
Large pattern library (breakouts, pullbacks, mean reversion, sector momentum, VIX, and more) with named trader attribution where applicable.
One-click profiles that bundle trading intent, risk, strategy mix, and filters—activate from the header without rebuilding settings each time.
Real stocks found via Finviz API and database screening. Strategy-specific criteria. Zero hallucinated tickers.
Create your own strategies by describing them in plain English. The AI interprets and applies them.
All stocks, Twitter/X picks, your watchlists, or a union of both—with prioritize (boost your names) or strict (only your list) modes.
Open How it works or Page tour in the header on The Agent for a quick explanation or spotlight walkthrough (tour works best on a wide screen).
On The Agent, controls are in the header:
Signals are cached per user for today (US/Eastern trading date) with the same intent and compatible settings—reloads can be instant until something material changes. Use Re-run for a deliberate full pass.
When you New Signal or Re-run, the thinking panel streams these steps. Market Data and Stock Screening are grounded in live feeds and code; AI steps interpret, choose strategies, rank screened names, and build the plan—they do not invent tickers outside the screen results.
VIX, breadth (e.g. MCO/MCSI), trend strength, sector heat, and other context you’ve enabled feed the next step.
The model classifies regime (bull, range, compression, defensive, etc.) so later steps know which strategies are in play.
From your enabled library (playbook or saved preferences), the AI chooses one or more strategies that fit the regime. When nothing fits, you may get a deliberate no trade / cash outcome. Attribution (e.g. who inspired the pattern) appears when available.
Deterministic screeners (Finviz stages, yfinance verification, and/or database-backed patterns) produce real candidates per strategy—not LLM-guessed symbols.
The model ranks and selects from the screened set (with your watchlist/Twitter filter rules applied in the pipeline).
Concrete entry, stop, target, and conviction for the top idea(s). Optional Backtest Validation may appear afterward when historical KPIs exist for that strategy and symbol.
Each step shows reasoning in the thinking panel. For a shorter conceptual overview, use How it works on The Agent page.
In the Market Data step, the agent pulls context you’ve enabled (often adjusted via New Signal wizard or saved preferences). Typical inputs include:
Day traders: Enable % Above 5 SMA and Twitter sentiment for intraday edge. Swing traders: Focus on MCO/MCSI and % Above 50 SMA for multi-day moves.
The platform includes 40+ screenable patterns and strategies. In Strategy Selection, the AI chooses from the subset you’ve enabled (via playbook or preferences). The list below samples well-known named patterns with trader attribution; many additional screens (e.g. Jeff Sun momentum, VIX pivots, inside-day variants) live in the product without changing the core idea: code finds candidates, AI chooses and plans.
The following strategies have been backtested with historical data (SPY, 2-year lookback):
| Strategy | Win Rate | PF | Sharpe | Max DD |
|---|---|---|---|---|
| Absolute Momentum | 39.0% | 1.26 | 1.70 | -39.5% |
| Bearish | 38.8% | inf | -0.01 | -7.6% |
| Bottom Picker | 64.9% | 1.26 | 1.43 | -38.8% |
| Deep Trend Pullback | 80.2% | inf | 14.24 | -0.4% |
| Earnings Catalyst | 42.1% | 1.42 | 0.05 | -16.0% |
| Ema Cross Fast | 69.5% | 6.34 | 9.36 | -18.4% |
| Ema Crossover | 33.7% | 1.48 | 1.48 | -23.2% |
| Gap And Go | 42.4% | 3.34 | 0.31 | -16.4% |
| Golden Cross | 65.7% | 4.21 | 6.08 | -11.5% |
| Holy Grail | 44.3% | inf | 3.01 | -4.7% |
| Ichimoku Cloud | 71.5% | 4.80 | 9.77 | -12.5% |
| Inside Day | 57.5% | 1.58 | 2.56 | -23.1% |
| Jeff Sun Momentum | 51.2% | inf | 5.47 | -13.9% |
| Keltner Momentum | 39.5% | 1.32 | 1.18 | -27.7% |
| Macd Bb Combo | 70.5% | 5.10 | 8.03 | -24.8% |
| Macd Trend | 36.2% | 1.42 | 0.09 | -19.6% |
| Mean Reversion | 63.6% | 1.28 | 1.45 | -20.9% |
| Momentum Macd | 42.9% | 3.83 | 1.69 | -29.4% |
| Obv Trend | 68.7% | 4.75 | 10.75 | -9.6% |
| Parabolic Short | 22.6% | 0.72 | -2.55 | -27.1% |
| Power Earnings Gap | 42.4% | 2.30 | 1.46 | -14.0% |
| Prime Pullback | 36.7% | 1.25 | 1.63 | -33.8% |
| Qullamaggie Breakout | 37.8% | 1.29 | -0.15 | -18.3% |
| Reversal 2b | 52.2% | inf | 5.56 | -6.8% |
| Reversal Support | 52.2% | inf | 0.91 | -18.3% |
| San Ku | 60.8% | inf | 5.00 | -5.9% |
| Sma Trend | 30.5% | 1.22 | 1.02 | -32.8% |
| Strength List | 42.7% | 1.06 | 0.48 | -39.3% |
| Supertrend | 40.9% | 1.61 | 2.73 | -21.6% |
| Supertrend Pullback | 82.8% | 92.25 | 10.56 | -5.8% |
| Triple Ema Crossover | 37.1% | 1.53 | 1.49 | -22.6% |
| Ttm Squeeze | 49.3% | inf | 3.01 | -22.4% |
| Turtle Breakout | 36.9% | 1.19 | 0.80 | -34.8% |
| Vcp Patterns | 40.5% | inf | 0.47 | -7.1% |
| Vix Pivot Daily | 49.6% | 1.11 | 0.68 | -37.6% |
| Vix Pivot Weekly | 48.1% | 1.56 | 2.57 | -32.7% |
| Vix Reversal | 58.9% | 1.61 | 2.60 | -22.7% |
| Waterfall Decline | 34.0% | 1.41 | 2.03 | -34.8% |
| Weinstein Stage2 | 43.4% | inf | 3.46 | -23.6% |
When the agent selects a strategy, you'll see who created it — for example, "VCP by Mark Minervini (SEPA)". This appears in both the thinking display and the final strategy card.
After Strategy Selection, Stock Screening runs as code: Finviz-style pre-filters, per-strategy rules, yfinance checks, and/or precomputed database patterns—so every candidate symbol is grounded in data before Ticker Selection.
Each strategy category uses different screening criteria:
Every stock ticker the agent recommends was found by real market screening (Finviz API or our database). The AI never invents stock names — it only selects from stocks that actually match the strategy criteria today.
If the screening finds zero candidates for the chosen strategy, the agent tells you clearly: "No stocks matched screening criteria for [strategy] today." Sometimes the best trade is no trade, and the agent won't force a pick when there are no real setups.
You can create your own strategies by describing them in plain English. The AI will interpret your description and apply the logic during synthesis.
"Buy stocks gapping up 3% or more at the open with above-average volume. Look for continuation in the first 30 minutes. Target 1:2 risk-reward. Best in trending markets when sector rotation is strong."
Be specific in your descriptions. Include: entry criteria, volume requirements, market conditions, and risk management guidelines. The more detail you provide, the better the AI can apply your strategy.
Configure the stock filter in Advanced (Stock Filter section). Watchlists themselves are managed from the header Watchlists button; then set Use as Filter on a list or wire the filter mode to watchlist/Twitter/union as needed.
Full market universe (default).
Stocks surfaced from handles you enable (lookback and confidence thresholds in Advanced).
Focus on symbols from your active watchlist.
Combine watchlist and Twitter picks.
Prioritize (common default): screening still runs broadly, but names on your watchlist get a score boost so they rise to the top. Strict: only symbols in your filter set are eligible; you may still see reference context if nothing on your list triggers.
The Agent streams six core steps while it runs (labels match the UI). A seventh row—Backtest Validation—appears when historical KPIs are available for the chosen strategy and symbol.
After a signal, Pro+ can use the floating Ask The Agent chat for follow-ups (platform AI key or your own BYOK). The assistant can call curated tools for live data, screening, and pipeline context. Pro and below do not include this chat.
On Pro+, the floating chat is an agentic assistant: it can call tools to fetch live market data, inspect your latest signal, run strategy screens, and more. It is not included on Free, Starter, or Pro.
When the agent calls a tool, you'll see real-time progress indicators showing what data it's fetching.
Power users can type slash commands for quick access to specific tools:
| /refresh | Compare morning signal vs current market |
| /vix | Current VIX levels and interpretation |
| /breadth | Market breadth indicators |
| /sectors | Hot sectors ranked by performance |
| /screen <strategy> | Screen stocks (e.g., /screen inside_day) |
| /price <symbol> | Stock price (e.g., /price NVDA) |
| /steps | Signal pipeline steps |
| /playbook | Active playbook details |
| Social sentiment picks | |
| /help | Show all available commands |
"Has anything changed since my signal was generated?"
"Screen stocks for inside day patterns"
"Why was this strategy chosen over others?"
"Switch to my aggressive playbook"
Pro+ can use the platform default model or bring your own provider keys where configured. Suggestion chips appear when the chat is empty to help you get started.
Six7 Alpha provides information for educational purposes only and does not constitute financial advice.
Trading involves substantial risk of loss. Past performance does not guarantee future results.
AI-generated content may contain errors. Always do your own research and consult a licensed financial advisor before making investment decisions.
Strategy names reference publicly known methodologies for educational purposes only. Six7 Alpha is not affiliated with or endorsed by any referenced traders or their organizations.
Terms of Service ·
Risk Disclaimer