> For the complete documentation index, see [llms.txt](https://docs.iotex.io/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.iotex.io/quicksilver/getting-started/create-your-first-agent.md).

# Create your First Agent

In QuickSilver, agents are **AI assistants** that creators can configure, **power with APIs**, and optionally **monetize**. Once created, these agents can be published to QuickSilver, where other users can interact with them through chat—either globally or directly.

This guide walks you through creating your first agent, defining its behavior, connecting it to APIs, and preparing it for publication on the QuickSilver network.

{% hint style="success" %}

### Developer Tip

You can also access your agent programmatically via the [QuickSilver API](/quicksilver/developers/quicksilver-api.md), making it easy to integrate your agent into your own apps, bots, or backend systems.
{% endhint %}

## Step 1 — Sign in

Before you begin, log in to your Quicksilver account:

* &#x20;Go to: <https://qs.iotex.ai/sign-in> and click the **"Sign in"** button

<figure><img src="/files/S4dN4XyDkkzKZPL92TdT" alt=""><figcaption></figcaption></figure>

## Step 2 – Create a New Agent

1. From the left panel, navigate to your **projects** dashboard: <https://qs.iotex.ai/projects>
2. Click the ”**+ New Project**” button

<figure><img src="/files/t67NWYk2sS8AcN0T5u3y" alt=""><figcaption></figcaption></figure>

2. Fill in your Agent’s basic information:

* **Name** – Chose a clear and descriptive name for your agent
* **Description** – Describe what the Agent can do
* **System Prompt** – Define your Agent’s functional boundaries and expected behavior: define this prompt carefully as it will define how your Agent responds to user queries.
* **Example Questions**: include some example questions that a user would want to ask to this agent
* **Tags**: include tags to help users find this Agent when they search for specific features
* **README**: include any additional documentation in the Readme.md file &#x20;

<figure><img src="/files/MCoEEmm1lvI9CiYRzxHo" alt=""><figcaption><p>Example Agent Creation Details</p></figcaption></figure>

## Step 2 – Add an API Schema

1. After creating the Agent, you can also access it from your [Projects Dashboard](https://qs.iotex.ai/projects).
2. Open the Agent details page:
3. Scroll down the details page and click on “**Add Schema**” to start defining the APIs your Agent will use:
4. Start from providing the API schema basic details:

* **Schema Name**: A clear name for this API, will help identifying this API in your dashboard
* **Description**: A description of the API
* **API endpoint:** the API server endpoint

<figure><img src="/files/YIhg83yraAWXBjXYKMKR" alt=""><figcaption></figcaption></figure>

<figure><img src="/files/pVWKJT8RPmSukcMt6QF0" alt=""><figcaption></figcaption></figure>

4. Next, define the API schema by providing the OpenAPI or curl specification:

* Ensure you include descriptions for each endpoint and its input/outputs for better results when the Agent decides which endpoint to use when replying to user queries:

<figure><img src="/files/du7GCseiRZCyPU5WPKYB" alt=""><figcaption></figcaption></figure>

## Step 3 — Publish your Agent

Once your Agent is ready, you can use the Publish button in the top right of the Agent's page to publish/unpublish the Agent to Quicksilver:

{% hint style="warning" %}
**Tip:** Preview and test your agent before publishing to ensure quality.

* Set guardrails in the Agent's System Prompt to restrict or allow certain topics or actions.
* Testing: Use the Agent's chat to preview how the agent handles real queries.
  {% endhint %}

<figure><img src="/files/Z4jPFZmJaqkljWC2af7A" alt=""><figcaption></figcaption></figure>

**Your Agent is Now Live!**

* It will appear on the [Quicksilver portal](https://qs.iotex.ai/marketplace?tab=agents).
* Users can engage with it via:
  * The Global Entry (shared chat box on the home page)
  * Direct Selection (agent-specific chat window)


---

# 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.iotex.io/quicksilver/getting-started/create-your-first-agent.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.