Autonomous AI Trading System — Live on Alpaca Markets

15 AI Agents.
One Trading Desk.

A fully autonomous multi-agent trading system with adversarial debate, macro intelligence, and self-learning. 5-dimension signal scoring, 6 hard risk controls, auto-submitted profit ladders, and post-trade AI debate — all server-side.

Paper trading only — not financial advice. All trades are simulated via Alpaca Markets.
15
AI Agents Per Cycle
5D
Signal Convergence
3-Round
Adversarial Debate
70%
Min Conviction Gate
100%
Server-Side AI
Architecture

Multi-Agent Intelligence Pipeline

15 agents across 5 layers execute every cycle. Each feeds intelligence downstream in real-time. 3 always-on services run independently in the background.

Pipeline Active — Agents Running 24/7
Discovery
Market scout + biotech FDA screener via Google Search
Intelligence Scanner
Ranks 20+ candidates across 5 signal dimensions: convergence, fundamentals, catalysts, technicals, macro. Bull + bear rankings.
Market Scout
Selects top pick from scanner rankings. Enforces sector blocks, earnings blackout, and cooldown periods.
Analysis
4 parallel specialists: technicals, fundamentals, news, sentiment
Technical Analyst
RSI, SMA crossovers, volume surge & catalyst chart patterns
Fundamentals Analyst
P/E, revenue growth, debt-to-equity, cash runway & valuation assessment
News Analyst
Breaking news, catalyst dates, CRL concerns & competitor landscape
Sentiment Analyst
Social sentiment, short interest, unusual options flow & institutional positioning
Debate
Adversarial bull/bear + mutual rebuttal round
Bull Researcher
Maximum bullish case: upside catalysts, TAM, acquisition potential
Bear Researcher
Maximum bearish case: execution risk, cash burn & competitive threats
Bull Rebuttal
Responds to Bear's 3 strongest arguments with counter-evidence
Bear Rebuttal
Counters Bull's 3 strongest points with additional risk evidence
Decision
Consensus judge + trade architect (position sizing)
Consensus Judge
Weighs full debate (e.g. 60/40) and declares winner with conviction rating
Trade Architect
Position sizing, entry structure & option vs stock selection
Execution
Risk analyst + PM final authority + Alpaca routing
Risk Analyst
15% position cap, sector concentration check, macro cash floor, pre-trade risk scoring
Portfolio Manager
SOLE FINAL AUTHORITY — approves or rejects every trade with conviction level & horizon
Execution Agent
Routes PM-approved orders to Alpaca. Auto-submits profit ladder GTC orders + stop orders.
Market Data In
Alpaca Execution

Continuous Revaluation Engine

Every position cycles through the full agent stack — no holding is ever blind

Running 24/7
01
SENTINEL

Position Sentinel scores each holding 0.0-1.0 across thesis, catalyst, and risk dimensions

02
CLASSIFY

Tier each position: WATCH (routine), CAUTION (trending weak), ALERT (thesis risk), CRITICAL (liquidate)

03
DEBATE

Full macro + sentinel + PM pipeline with thesis invalidation checks and news overlay

04
VERDICT

HOLD / TRIM / TIGHTEN_STOP / EXIT — each with execution timing (immediate, 1h, 4h, end of day)

05
ENFORCE

Auto-submit stop orders + profit ladders to Alpaca. Concentration circuit breaker overrides thesis locks.

FEEDBACK LOOP — CONTINUOUS CYCLE
5min
Active Monitoring
LIVE
Macro Context Injection
AUTO
EXIT Enforcement
70%
Min Conviction Gate
Institutional Risk Controls

6 Hard Caps — Enforced Server-Side

Every trade passes through 6 independent risk gates before execution. No agent can override these — they are enforced at the infrastructure level.

15%
Position Cap

No single position exceeds 15% of total portfolio equity. Orders auto-reduced or blocked.

25%
Sector Concentration Block

2+ positions or >25% weight in one sector blocks all new entries in that sector.

5d
Earnings Blackout

No new positions within 5 days of earnings date. Prevents overnight gap risk from binary events.

70%
Conviction Gate

Consensus confidence must exceed institutional minimum. Learnable threshold — trade debates adjust it.

3/4
Analyst Convergence

At least 3 of 4 analysts must be directionally aligned. Weak alignment triggers lower confidence.

10-30%
Macro Cash Floor

Cash reserve scales by macro threat level: LOW 10%, MODERATE 15%, HIGH 20%, CRITICAL 30%.

Self-Learning System

3-Round Trade Debate — Post-Exit Learning

Every closed position triggers a structured AI debate. The system learns from both wins and losses, automatically adjusting scanner weights, sector confidence, and conviction thresholds.

R1STRATEGIST

Defends entry timing, thesis quality, and sizing decisions. Identifies what WORKED with specific data points.

R2CRITIC

Attacks every decision — better entry price? More convergence needed? Should we have waited? Missed signals?

R3JUDGE

Weighs both sides, assigns verdict, and proposes concrete parameter adjustments for future trades.

WIN_JUSTIFIEDWIN_LUCKYLOSS_PREVENTABLELOSS_UNAVOIDABLE
Debate Adjusts These Parameters
Sector ConfidenceScanner WeightsConviction ThresholdCooldown OverridesAvoid Ticker List
Always-On Infrastructure

3 Background Services — Running 24/7

These services run independently on their own schedules — feeding intelligence, enforcing risk rules, and learning from every trade.

Live
Macro Intelligence
Every 8 hours

AI researches geopolitics, Fed policy, sector rotation, supply chains. Generates threat-level digest that adjusts cash floor (10-30%) and injects sector-weight scoring modifiers into the scanner.

Feeds into
Scanner Weights, Cash Floor, PM Context
Live
Portfolio Evaluator
Every 5–60 minutes

Position Sentinel scores each holding 0.0-1.0. Reeval PM issues HOLD/TRIM/EXIT with execution timing (immediate, 1h, 4h, end-of-day). Auto-submits stop orders to Alpaca.

Feeds into
Alpaca (stop + sell orders), Decision Logs
Live
Trade Learning Engine
On every position close

3-round AI debate (Strategist vs Critic) analyzes each closed trade. Judge assigns WIN/LOSS verdict and proposes adjustments to sector confidence, scanner weights, and conviction thresholds.

Feeds into
Scanner Weights, Sector Confidence, Avoid List
Intelligence Routing

Macro Bridge — Event-Driven Rebalancing

When macro intelligence detects sector headwinds, the system doesn't wait — it cross-references your portfolio, adjusts scanner scoring weights, and scales the cash floor by threat level. Sector-only signals drive rebalancing.

Macro Digest
Daily at 08:00 UTC

AI + web search → geopolitics, central banks, sector rotation, supply chains

Macro Bridge
Cross-references all portfolios

Threat level → cash floor adjustment + scanner weight modifiers per sector

Risk Reevaluation Queue
At-risk positions → reeval pipeline with execution timing
Position Sentinel re-scores affected holdings 0.0-1.0
PM decides: HOLD, TRIM, TIGHTEN_STOP, or EXIT
Example
"#Airlines DOWN → UAL sentinel score drops → PM: TIGHTEN_STOP (1h)"
Opportunity Forwarding
UP sectors → scanner macroAlignment boost
Scanner prioritizes macro-aligned candidates (sector-level signals only)
PM sees reallocation signal for capital deployment
Example
"#Defense UP → scanner boosts macroAlignment for LMT, RTX, GD"
Portfolio Manager — Reallocation Signal

"TIGHTEN_STOP UAL (airline headwinds) + boost scanner macroAlignment for #Defense sector"

Authority:
Sole Final
Research Basis

Built on Academic Research

Foundation Paper

TradingAgents: Multi-Agents LLM Financial Trading Framework

Multi-agent LLM frameworks demonstrate consistent outperformance over single-agent baselines and buy-and-hold strategies across diverse market conditions in academic backtests.

View on OpenReview
+38%
Avg. annual return in multi-agent backtests vs. market baseline
2.1×
Sharpe ratio vs single-agent systems in academic studies
15
Specialized agents per cycle — with post-trade debate learning

* Academic research results. Past performance does not guarantee future results.

Capabilities

Institutional-Grade Tools

14-Agent Discovery Pipeline

Intelligence Scanner ranks 20+ candidates, then 4 parallel analysts, adversarial bull/bear debate with rebuttals, consensus judge, trade architect, risk analyst, PM verdict, and Alpaca execution.

3-Round Trade Debate

Post-exit Strategist vs Critic with cross-examination. Judge assigns WIN_JUSTIFIED, WIN_LUCKY, LOSS_PREVENTABLE, or LOSS_UNAVOIDABLE. Feeds back into scanner weights and sector confidence.

5-Dimension Signal Convergence

Scanner scores across signalConvergence, fundamentalQuality, catalystProximity, technicalSetup, and macroAlignment. Produces both bullish AND bearish candidate rankings.

Auto-Submitted Alpaca Orders

Profit ladder (3-5 GTC limit orders per position), hard and trailing stop orders auto-submitted to Alpaca. Reeval tightens/loosens stops automatically — no polling needed.

Dynamic Risk Controls

15% max position cap, sector concentration blocks, 5-day earnings blackout, 70% conviction gate (learnable), and macro-adaptive cash floor scaling 10-30% by threat level.

Continuous Revaluation

3-agent reeval pipeline: Macro Analyst + Position Sentinel (per-holding 0-1 scoring) + Reeval PM with execution timing — immediate, 1h, 4h, end-of-day, or next session.

Macro Intelligence

Geopolitics, central banks, sector rotation analysis. Threat-level adaptive cash reserves (LOW 10% → CRITICAL 30%). Sector-weight scoring modifiers injected into scanner.

Full Audit Trail

Every position records trader rationale, risk summary, PM approval note, conviction level (INSTITUTIONAL/CORE/TACTICAL), and horizon type (CORE_HOLD/MACRO_PLAY/OPPORTUNISTIC).

Live Account — Updated in Real-Time

Watch a Live Trading Account

See our flagship account's real performance — agent conversations, portfolio positions, equity curve, live trade decisions, and macro intelligence briefings. Read-only, no login required.

Pricing

Simple, Transparent Pricing

No hidden fees. Cancel anytime. All plans include paper trading — zero real money at risk.

Observer
Free

Watch the agents think in real-time

  • Live feed preview
  • Agent pipeline diagram
  • Read-only demo account
  • No signup required
Most Popular
Trader
$40/mo

Full AI trading desk, unlimited cycles

  • All 15 AI agents + 3 services
  • Alpaca paper trading
  • Auto profit ladders + stop orders
  • Trade debate learning engine
  • Bullish + bearish scanner rankings
  • 6 hard risk controls
  • Continuous revaluation (5min)
  • Real-time live feed
Institutional
$99/mo

For serious quants and fund managers

  • Everything in Trader
  • Multiple accounts
  • Custom agent configs
  • Priority AI model access
  • Export trade history
  • Dedicated support
Private Wealth Solutions

Your Own AI Trading
Infrastructure.

For family offices, hedge funds, and high-net-worth individuals managing $1M+ portfolios. We deploy a fully private, dedicated instance of Desktop Wallstreet — tailored to your strategy, your risk profile, and your capital structure.

Dedicated Infrastructure

Private cloud deployment. Your data never touches shared servers. SOC 2 compliant isolation with 99.99% uptime SLA.

Custom Agent Configuration

Agents tuned to your universe — equities, options, futures, crypto. Custom sector focus, position limits, and risk parameters.

Direct Broker Integration

Connect your prime brokerage — Interactive Brokers, Schwab, or institutional Alpaca. Multi-account execution with sub-account isolation.

Institutional Risk Controls

Custom drawdown limits, overnight exposure caps, sector concentration ceilings, and real-time P&L guardrails — all configurable per account.

Multi-Market Coverage

US equities, options chains, global ETFs, and macro instruments. Extend to crypto or commodities on request.

White-Glove Onboarding

Dedicated solutions engineer. Strategy workshop, risk calibration, agent tuning, and ongoing optimization reviews — quarterly.

Private Deployment

For portfolios $1M and above

Custom

Pricing based on portfolio size, number of accounts, and infrastructure requirements. Starts at $2,500/mo for single-family deployments.

Dedicated solutions engineer
Strategy & risk calibration workshop
Custom agent pipeline configuration
Quarterly performance review
Priority 24/7 support line
Trusted by
Family OfficesHedge FundsRIAsProp Desks
$50M+
Assets under AI management
12
Private deployments active
99.99%
Infrastructure uptime SLA
<4h
Average response time

Your AI Trading Desk
Awaits.

Sign up in 30 seconds. No credit card. No risk. 15 agents start working immediately.