Technical Analyst
Price action, market structure, support / resistance, indicator interpretation. Sees the same OHLC window as the others but reports on form.
How AlphaFlowSeven works
Six AI agents. Three reasoning tiers. One synthesised call per cycle. AF7's council architecture is built so no single model — and no single bias — produces a signal alone.
The pipeline at a glance
- Tier 1 — Specialists (parallel): Technical Analyst, Momentum Analyst, Risk Analyst.
- Tier 2 — Advocates (parallel): Bull Advocate, Bear Advocate.
- Tier 3 — Synthesis: Lead Trader weighs everything plus its own last four calls.
Tier 1 — three specialists read the market
Momentum Analyst
RSI, ADX, +DI / -DI velocity, trend persistence. Quantifies whether what's moving is likely to keep moving.
Risk Analyst
ATR volatility, recent drawdown, exposure. Anchors the council to "what happens if we're wrong" rather than just "what's the opportunity."
Tier 2 — adversarial advocacy
Tier 2 sees all three Tier-1 outputs and is asked to build the strongest possible case for one side. Bull and Bear advocates run in parallel, each producing a directional thesis with explicit counter-arguments.
This step exists to stress-test Tier 1 before any signal is issued — a call that survives both advocates' criticisms is worth more than one that only convinces a consensus.
Tier 3 — the Lead Trader
The Lead Trader receives Tier 1's three analyses, Tier 2's bull and bear cases, and — crucially — its own four most recent prior calls for the same council. That continuity prevents whiplash: the Lead Trader knows whether it just opened a simulated position, whether the council has been hesitating, whether it called HOLD three times in a row.
Final output: BUY, SELL, HOLD, or
CLOSE, with a conviction score from 0.0 to 1.0 and a
plain-language summary.
From signal to simulation
AF7 never touches a real exchange account. Every signal can be routed into a built-in portfolio simulation that opens, manages, and closes simulated positions. Take-profit and trailing-stop levels can be fixed per-strategy or council-determined per-call.
Monitoring runs every 60 seconds. Live OHLC arrives via WebSocket from Binance International, with automatic Kraken fallback after three connection failures or a region block.
Models and configuration
Each agent can use a different model. AF7 supports Anthropic Claude (Sonnet, Opus, Haiku), OpenAI (GPT-4o and the GPT-5 family), Google Gemini (2.5 Flash and 2.5 Pro), xAI (Grok 4), DeepSeek (V3.2), and Moonshot AI (Kimi K2.6). Temperatures are per-agent.
Try it free
New accounts get three free AI councils on a curated set of tickers. No credit card required.