We're currently in a calibration phase — a fresh start with clean stats is coming soon.

Live research experiment — Paper trading only. No real money involved. Simulated capital of $10,000 USDT (US Dollar equivalent).

Full transparency: losses displayed alongside wins. History is never erased.

Observations generated by AI (Claude + Gemini). This is exploratory research — past simulated results do not indicate future performance.

Live Research Experiment

We gave Claude and Gemini $10,000 in simulated capital. Here's what happened.

A live AI experiment: two models analyze crypto markets 6 times a day, then 10 hard-coded risk checks validate every decision. All trades, all reasoning, all losses — nothing hidden. Tracked against a simple BTC buy-and-hold benchmark.

LLMs have a unique advantage in narrative-driven markets — they synthesize technicals, sentiment, on-chain data, and news in under 20 seconds. But does real-time context improve AI reasoning? The data will tell.

354+
AI analysis cycles
10
Completed trades
59d
Experiment running

How it works

1

Collect

Price action, on-chain data, news feeds, and market sentiment — gathered every 4 hours.

2

Synthesize

Gemini (Google's AI) compresses thousands of data points into a structured market summary.

3

Decide

Claude (Anthropic's AI) analyzes the synthesis, weighs converging factors, and outputs an observation — or holds.

4

Validate

10 hard-coded risk checks — position sizing, invalidation zones, exposure limits. Zero AI, pure code.

5

Publish

Approved observations go to the Telegram premium channel and this dashboard in real time.

The hypothesis

20s

Speed of synthesis

Every 4 hours, the AI ingests technical indicators, on-chain metrics, market sentiment, and breaking news from multiple specialized sources. Whether 20 seconds of AI processing outperforms hours of human analysis is exactly what this experiment measures.

4 layers

Multi-source convergence

No analysis is based on a single indicator. A simulated buy requires convergence across technical analysis, market sentiment, on-chain data, and news flow. One factor alone means no action. Most cycles (~70%) result in a simulated hold — and that is by design.

10 checks

Deterministic risk control

The AI proposes, deterministic code enforces. Every decision passes through 10 hard-coded checks: position sizing, invalidation zone validation, exposure limits, drawdown protection rules. No override, no exceptions. This tests whether rules-based risk management improves AI outcomes.

Equity Curve

Tracks how the simulated $10,000 portfolio evolves over time, compared to simply holding Bitcoin. No real money is involved.

Full transparency into the experiment

Every AI decision comes with the full reasoning chain — the data it weighed, the counter-argument it considered, and the factors that drove its conclusion. Free users see the outcome. Premium observers see the process.

Free access48h delay
Sim. BUYBTC/USDTConf. 0.74

Simulated model parameters · 48h delayed

Key level: $51,200
Invalidation: $49,800
Target 1: $53,000
Target 2: $55,200

Full AI reasoning is Premium only

Premium accessReal-time
Sim. BUYBTC/USDTConf. 0.74

Simulated model parameters

Key level: $51,200
Invalidation: $49,800
Target 1: $53,000
Target 2: $55,200
Factual

Key technical indicators bouncing from oversold levels, moving average crossover confirmed, volume surging above recent average.

Sentiment

Market sentiment shifted from fear to greed in 7 days. Derivatives positioning neutral.

Counter-thesis

Momentum on higher timeframe still bearish, no confirmed trend reversal yet.

Free users see observations with a 48-hour delay. Premium observers follow every step of the experiment as it unfolds — including the AI's full reasoning chain.

€19.99/month

Real-time experiment stream + full AI reasoning + Telegram updates

Follow the Experiment

Cancel anytime. No commitment.