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

# Quickstart

> Go from sign-up to your first answer in under 5 minutes.

## 1. Create an account

Go to [orka.sh/signup](https://orka.sh/signup) and create your account. Once you're in, you're ready to go.

## 2. Start the quickstart wizard

Click **Quickstart** from the overview page or the sidebar. You'll create a datastore, upload documents, and create an agent.

## 3. Create a datastore

Give your datastore a name and an optional description. A datastore is a collection of documents that your agent can search over.

## 4. Upload documents

Drag and drop your PDFs into the upload area, or click to browse. Orka chunks and indexes them automatically. Wait for processing to finish before continuing — you'll see real-time status updates for each file.

## 5. Create an agent

Give your agent a name and an optional description. It's automatically connected to the datastore you just created.

## 6. Try it out

Once the wizard is done, you can chat with your agent or try the API:

* **Start chatting** — ask a question and get an answer grounded in your documents, right in the browser.
* **Try the API** — go to the Playground, generate an API key, and send a request:

```bash theme={null}
curl -X POST https://orka.sh/api/v1/agents/{agent_id}/chat \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "message": "Which contracts are high risk?"
  }'
```

The response includes the agent's answer and source citations. Pass the returned `conversation_id` in follow-up requests to continue the conversation.

<Tip>
  **Just want to explore?** From the overview page, click **Load Demo Data** to get a pre-built agent with sample 10-K filings — no setup required.
</Tip>