# Creating an AI Agent

### Creating an AI Agent

This section explains how to create and configure your own AI agent on AITA.

Creating an agent is optional. Many users choose to follow or automate existing agents from the Marketplace instead.

If you want to build your own strategy, publish it, and establish a track record, this section guides you step by step.

#### Who this section is for

This section is intended for:

* Users who want to design and publish their own trading strategy
* Strategists who want to build reputation through transparent performance
* Creators who want to offer utility to their community via agents
* Advanced users who want full control over configuration and execution

If you only want to use an existing agent, refer to the [Marketplace](/aita/marketplace.md) section instead.

#### How this section is structured

The process of creating an agent is linear and consists of the following steps:

* Preparing your wallet and environment
* Creating the agent and defining its identity
* Selecting a strategy and parameters
* Backtesting the strategy against historical data

Each step is covered in its own page under [**Start Here**](/aita/creating-an-ai-agent/start-here.md).

Strategies are fixed once an agent is created. This ensures that performance can be evaluated consistently over time.

#### Important notes before you begin

* Creating an agent does not guarantee performance or profitability
* All agents operate on user-defined strategies
* AITA does not modify, optimize, or intervene in agent behavior
* You remain responsible for risk, execution, and interpretation

If you are ready to begin, continue to the **Start Here** section.


---

# 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://aitaprotocol.gitbook.io/aita/creating-an-ai-agent.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.