> ## Documentation Index
> Fetch the complete documentation index at: https://mind-e.co/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# Quickstart

> Create your first AI agent and deploy it in minutes.

This guide walks you through creating an AI agent, uploading a document, testing it, and embedding it on your website.

## Prerequisites

* A Mind-e account — [sign up at app.mind-e.co](https://app.mind-e.co/auth/signup)

<Steps>
  <Step title="Create an agent">
    1. Go to your [dashboard](https://app.mind-e.co/dashboard) and click **Create Agent**
    2. Enter a **name** and **description** for your agent
    3. Select a **category** (Content, Support, Education, or Custom)
    4. Write a **system prompt** that tells the agent how to behave — for example:

    ```text theme={null}
    You are a friendly customer support assistant for Acme Corp.
    Answer questions based on the provided context. If you don't know
    the answer, say so and suggest contacting support@acme.com.
    ```

    5. Choose an AI **model** (GPT-4o is the default) and set the **temperature** (0.7 is balanced)
    6. Click **Create**
  </Step>

  <Step title="Upload a document">
    1. Open your agent and go to the **Sources** tab
    2. Click **Upload Document**
    3. Select a file — supported formats:

    | Format   | Extension | Max size               |
    | -------- | --------- | ---------------------- |
    | PDF      | `.pdf`    | 50 MB, up to 500 pages |
    | Word     | `.docx`   | 50 MB, up to 300 pages |
    | Text     | `.txt`    | 10 MB                  |
    | Markdown | `.md`     | 10 MB                  |

    4. Wait for processing — the document goes through conversion, chunking, and embedding
    5. Once the status shows **Embedded**, your agent can answer questions from this document

    <Tip>
      You can also add **web sources** by entering a URL, or create **text snippets** for custom content.
    </Tip>
  </Step>

  <Step title="Test in the playground">
    1. Go to the **Playground** tab
    2. Type a question related to your uploaded document
    3. The agent responds using relevant content from the document, with source attribution
    4. Try different questions to see how the agent retrieves information
  </Step>

  <Step title="Embed on your website">
    Go to the **Integration** tab to get your embed code. You have two options:

    **Option A: Chat widget (recommended)**

    Add this script before the closing `</body>` tag on your website:

    ```html theme={null}
    <script>
      window.mindeConfig = {
        agentId: 'your-agent-id'
      };
    </script>
    <script src="https://widget.mind-e.co/widget.js" defer></script>
    ```

    This adds a floating chat bubble to your site.

    **Option B: Iframe**

    Embed the chat directly into your page:

    ```html theme={null}
    <iframe
      src="https://mind-e.co/chat/your-agent-id"
      width="100%"
      height="600px"
      frameborder="0"
      style="border: none; border-radius: 12px;"
      title="Chat">
    </iframe>
    ```
  </Step>
</Steps>

## What's next?

<CardGroup cols={2}>
  <Card title="Core Concepts" icon="lightbulb" href="/core-concepts">
    Understand how agents, documents, RAG, and credits work together.
  </Card>

  <Card title="Customize your agent" icon="sliders" href="/guides/customizing-agent">
    Fine-tune your agent's behavior with system prompts, models, and temperature.
  </Card>

  <Card title="Knowledge base" icon="book" href="/guides/knowledge-base">
    Learn how to manage documents, web sources, and text snippets.
  </Card>

  <Card title="Chat appearance" icon="palette" href="/guides/chat-appearance">
    Customize the look and feel of your chat widget.
  </Card>
</CardGroup>