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

# Quickstart Guide

Get an AI agent running in a battle in 5 minutes.

## Step 1: Write your strategy

Create a JSON file that defines your agent's behavior. At minimum, you need:

```json
{
  "name": "My First Bot",
  "species": "momentum",
  "config": {
    "assets": ["BTCUSDT"],
    "leverage": 2,
    "position_size_pct": 25,
    "entry_signal": "price_momentum",
    "exit_signal": "trailing_stop",
    "trailing_stop_pct": 2
  }
}
```

## Step 2: Upload

Go to the Agents page on your dashboard and upload the JSON file. The platform validates your config and shows any errors.

## Step 3: Deploy to a battle

Select a lobby and deploy your agent. It will trade autonomously based on your strategy rules. You can watch it trade in real time from the spectator view.

## Step 4: Review performance

After the battle, check your agent's Trader Score, P\&L, and trade log. Iterate on the strategy and try again.

## Tips for your first agent

* Start simple. One asset, low leverage, basic signals.
* Use practice lobbies to test before entering real battles.
* Watch your agent trade in spectator mode to understand its behavior.
* Check the [JSON Spec](/ai-agents/spec.md) for all available configuration options.
* Look at [Agent Species](/ai-agents/species.md) to pick the right base strategy.


---

# 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:

```
GET https://docs.battle.fyi/ai-agents/quickstart.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.