QuorumTrading · v3.7

Trading bots,
but you can read
the receipts.

A council of three AI agents votes on every buy, sell, and hold. The reasoning is in the trail. Backtest it, paper-trade it, take it live — at your pace.

Council shape3 agents · 1 orchestrator
Trust ladderMock → paper → live
5-yr backtest · QQQ MA0.86 Sharpe
Backtester5yr / < 30s
Restart pointany council tick
Act 1The problem

Most bots are opaque.
Yours doesn't have to be.

Pick a typical trading bot. It bought QQQ at 14:00 ET on 07 May. Why? "Signal triggered." That's not a trade you can defend — to yourself, your spouse, or the IRS.

QuorumTrading writes a paragraph for every decision and stamps it with three independent votes. Open any council tick and you get the chart, the trail, the reasoning — the same panels you'd see if it were running your money.

Tech ETF — Moving Average Crossover

sim #025C205B · QQQ · alpaca paper · DCA on
Live
Portfolio value
$21,580.84
vs $20,000 start
Total return
+7.90%
today +$87.40
vs QQQ b&h
-1.62%
QQQ +9.52% same window
portfolioBUYHOLDSELL

Decision history

3 of last 38
Open full trail →
WhenActionVotes (T · F · S)Price
13:54 ETHOLDTechFundSent$451.80
10:00 ETBUYTechFundSent$942.10
07 MayBUYTechFundSent$445.30

Council · this tick

quorum unanimous · MAJORITY threshold 0.65
TechnicalBUY50d crossed 200d 3 sessions ago; RSI 62 — room to run.
FundamentalBUYQQQ P/E in band; sector earnings beats running 67%; ETF flows positive.
SentimentBUYNews +0.42 post earnings beat. Tech-sector sentiment rebounded from −0.18.
Act 2The council

Three specialists.
One quorum.

Technical reads price action and momentum. Fundamental reads filings and ratios. Sentiment reads news, filings, and social. Each runs on its own model with its own context window — no agent sees another's reasoning until after the orchestrator counts the vote.

The cards on the right show what we actually measure: how often each agent voted with the final consensus, and how often the orchestrator chose to override the majority. We don't track "accuracy" — there's no labeled ground truth for an agent's vote being right.

Agent council · last 12 sessions

Tech ETF · sim #025C205B
Technical12 sessions
With consensus
71%
Sessions
12
Voted yes · 12 sessions→ recent
voted with the final consensus 8 of 12 sessions
Fundamental12 sessions
With consensus
64%
Sessions
12
Voted yes · 12 sessions→ recent
voted with the final consensus 8 of 12 sessions
Sentiment12 sessions
With consensus
58%
Sessions
12
Voted yes · 12 sessions→ recent
voted with the final consensus 7 of 12 sessions
Orchestrator12 sessions
Override rate
8%
Sessions
12
Override · 12 sessions→ recent
overrode the majority on 1 of 12 sessions · earnings eve
Act 3Author the strategy

A markdown brief.
A short YAML config.

A QuorumTrading strategy is a markdown document with a short YAML frontmatter. The frontmatter holds the machine-readable rules — evaluation cadence, tickers, consensus method. The body is plain English: entry signals, exits, risk caps, what each agent should pay attention to.

Three agents read both before they vote. Fork from the public library or start with a blank page. Revisions are stamped, diff-able, and one click to roll back.

strategy.md

markdown + yaml · v3.2 · QQQ
---
version: v3.2
consensus_method: MAJORITY
consensus_threshold: 0.65
evaluation_interval_seconds: 3600
stock_tickers: [QQQ]
market_hours:
  timezone: "America/New_York"
  evaluation_times: ["10:00", "14:00"]
---

Tech ETF — Moving Average Crossover

A trend-following QQQ strategy. Enter on confirmed golden crosses, exit on death crosses or trailing-stop hits. The council weighs technical signals against earnings windows and macro sentiment.

Entry signals

  • 50-day SMA crosses above 200-day SMA (golden cross)
  • Confirmed by 2 consecutive daily closes
  • RSI not in overbought territory (< 70)

Exit signals

  • 50-day SMA crosses below 200-day SMA (death cross)
  • 8% stop loss from entry
  • Trailing stop at 20% below peak profit

Risk caps

  • Max 95% of portfolio in QQQ
  • 5% cash floor at all times
  • Drawdown halt at 25% from peak

Council

  • Technical · weight 1.0 · reads price action + indicators
  • Fundamental · weight 1.0 · reads sector earnings, ETF flows
  • Sentiment · weight 1.0 · reads news + social
  • Orchestrator can override on earnings eve or VIX spike
Act 4Backtest

Years of receipts
before a dollar of yours.

Replay 1–10 years of historical bar data. The council votes on each tick as if it were live. You get the equity curve, the decision trail, every hold and every override.

Every backtest renders against benchmarks. Below: Tech ETF — MA vs. QQQ buy & hold and the public Megacaps Rotor strategy on the same 5-year window. Click any tick in-app to restart the council from that point with a tweaked rule.

5-year backtest · Tech ETF — MA

2021-06 → 2026-02 · v3.2
+111.64%Tech ETF · MA (this strategy)+84.20%Megacaps · Rotor+72.00%QQQ buy & hold
Total return
+111.64%
Sharpe
0.86
Max DD
-19.21%
Act 5Go live

Mock. Paper. Real money.
You decide when.

Three states, one toggle each. The council doesn't know the difference; only the broker does. Cash floor, max position, max drawdown enforced in code at every state.

MMock

Fake fills · zero capital

Same data feeds, same agents. Orders never leave the platform. Debug a strategy quickly without spinning up a broker account.

mock
PPaper

Alpaca paper · fake money

Real fills against real market data with paper capital. Most users live here 4–12 weeks before promoting.

paper
LLive

Alpaca live · real money

One toggle, one confirmation. DCA top-ups optional. Pause from the dashboard any time — the trail keeps writing.

live

Open the council on your next trade.

Five minutes from sign-up to a council voting on your first backtest. No subscription, no contract — you only pay for the AI tokens you actually burn.

platform is freepay only for AI you consumemock, paper, and live Alpaca — no platform fee