# Welcome to Crush

**Build systematic crypto strategies in plain English. No coding required.**

Crush is an AI-assisted quant trading platform. Describe what you want to test, backtest it against real market data, and deploy it live on Hyperliquid — all without writing a single line of code.

## How It Works

**1. Describe your strategy**\
Use Claude Code with MCP to describe trading ideas in plain English. Or use the visual strategy builder to combine signals from 116+ indicators.

**2. Backtest against real data**\
Run your strategy through our production-grade backtesting engine with realistic slippage and fee modeling. See Sharpe ratio, max drawdown, win rate, and more.

**3. Deploy live on Hyperliquid**\
One click from backtest to live execution on Hyperliquid, the leading onchain perpetuals exchange. No KYC. Global access.

## Who Is Crush For?

* **TradingView traders** who want a systematic edge but don't know Python
* **Retail crypto traders** who want to move beyond manual chart patterns
* **AI-native developers** who want institutional-grade crypto data and execution through Claude Code

## What Makes Crush Different

* **No coding required** — describe strategies in plain English via Claude Code, or use the visual builder
* **Crypto-native data** — 116+ indicators including proprietary crypto-specific signals (funding rates, open interest, liquidations, on-chain volume)
* **AI strategy building** — MCP integration lets Claude Code research, backtest, and deploy for you
* **Full loop** — backtest to live execution on Hyperliquid in one click
* **Production-grade engine** — high-performance time-series infrastructure with realistic slippage and fee modeling
* **MCP integration** — describe strategies to Claude Code, get results in seconds

## Get Started

Ready to build your first strategy? Head to [Create Your Account](/documentation/getting-started/create-account.md) to get started, or learn more about [why AI-assisted quant trading](/documentation/readme/why-ai-quant-trading.md) changes everything.


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://crushtrading.gitbook.io/documentation/readme.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.