> For the complete documentation index, see [llms.txt](https://docs.rezlabs.org/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.rezlabs.org/readme.md).

# Introduction

Rez is an agentic execution & intelligence layer for perpetual derivatives. We are building a non‑custodial platform & infra where on‑chain agents autonomously manage perps with 0 manual commands.

## What is Rez?

Unlike traditional algorithmic bots that rely on static, hard-coded rules, Rez leverages **Neuro-Symbolic AI**. It uses "symbolic" technical indicators (EMA, RSI, MACD) as tools, which its "neural" brain (LLM) interprets to form a market thesis.

### Key Philosophy: Radical Abstraction

Rez is designed to abstract away the complexities of DeFi trading. Instead of managing individual orders and API rate limits manually, users interact with Rez via high-level **Risk Profiles**. Rez handles the underlying execution, risk management, and market analysis autonomously.

## Core Pillars

1. **Autonomous Intelligence**: Uses a ReAct (Reasoning and Acting) loop to dynamically fetch data and validate entry/exit points.
2. **Hyperliquid Integration**: Optimized specifically for the Hyperliquid L1, taking advantage of its high throughput and native perpetuals.
3. **Local Alpha**: Calculates technical indicators locally to ensure maximum precision and minimize dependence on external processing services.
4. **Transparent Reasoning**: Every trade decision is backed by a verbose reasoning chain, viewable in real-time via the companion dashboard.

## Next Steps

Explore the [Core Concepts](/core-concepts/ai-trading.md) to understand how Rez thinks, or dive into the [Architecture](/unit-architecture/architecture.md) to see how it's built.


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## 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, and the optional `goal` query parameter:

```
GET https://docs.rezlabs.org/readme.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

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.