BTC/ETH 3-AI committee
Claude, GPT and Gemini vote on every candle; it only trades with a majority and confidence. It's cloned turned off in your practice account so you can review it before turning it on.
How it works
- 1The candle closesEvery 4h, price, volume, news and funding are collected for BTC and ETH.
- 2Three AIs voteClaude, GPT and Gemini analyze separately and return a vote, confidence and reason.
- 3The Trade Gate filtersIt only passes with at least 2 of 3 bullish votes and average confidence ≥ 70.
- 4It runs in practiceIt buys 2% of your virtual portfolio with TP +5% and an ATR stop, and messages you on Telegram.
About this strategy
Instead of trusting a single AI model, this bot asks three different models to analyse BTC and ETH price, volume, news and funding separately. Each one returns a vote (bullish, bearish or neutral), its confidence and its reasoning.
A Trade Gate then decides: it only trades if there is a minimum number of bullish votes and the average confidence beats your threshold. Without consensus, the bot logs it and does nothing. It’s a way to reduce arbitrary calls from any one model.
Every model call costs credits, so the cost depends on the assets and frequency you choose; the page works it out before you clone. AI doesn’t predict the market: it’s one more filter, which is why the bot keeps a stop, a maximum size and your risk limits.
The workflow
Click a node to see what it doesCustomize it before cloning
What you'll receive
Questions about this strategy
A single model can be confidently wrong. Requiring a majority cuts trades driven by noise; in our tests, at the cost of trading less.
Its vote counts as neutral. If two fail, the run is marked as an error and it doesn't trade.
Yes. In the Committee node you can pick others, like Grok, DeepSeek or Mistral, and see their cost per call.
It's cloned in practice. Try it for a few weeks and move it to real money only if you're convinced, with your risk limits.
Learn before you switch it on
- AI trading agents vs trading bots: what’s the difference?What an AI trading agent is, how it differs from a classic trading bot, what it can really do and what it can’t. With examples and the risks to watch for.
- How to backtest a trading strategy without fooling yourselfWhat backtesting is, how to test a trading strategy on historical data and the mistakes that inflate results: overfitting, look-ahead bias, fees and slippage.