Quickstart Guide

1Create Your Account

Head over to app.erys.ai/sign-up to create your account. You can sign up with email or use OAuth providers like Google or GitHub.

After verifying your email, you'll land on the dashboard where you can manage your agents and view analytics.

2Generate an API Key

Navigate to Settings → API Keys in the dashboard. Click Create new key, give it a descriptive name (e.g. "Development"), and copy the generated key.

You'll need this key to send messages to your agent programmatically via the REST API.

3Create Your First Agent

From the dashboard, click New Agent. You'll be prompted to configure your agent:

• Name: Give your agent a descriptive name (e.g. "My First Agent")
• System prompt: This defines your agent's personality and capabilities
• Model: Choose a model (Claude Sonnet recommended for a good balance of speed and quality)

Example system prompt:

Click Create — your agent is now live and ready to receive messages.

4Send a Message

Now that your agent is running, you can send messages via the REST API. The endpoint pattern is:

Here's how to send your first message using TypeScript:

const response = await fetch(
  'https://app.erys.ai/api/agents/{agentId}/messages',
  {
    method: 'POST',
    headers: {
      'Authorization': 'Bearer YOUR_API_KEY',
      'Content-Type': 'application/json',
    },
    body: JSON.stringify({
      content: 'Hello! What can you do?',
    }),
  }
)

const data = await response.json()
console.log(data.content)

Or using cURL from the command line:

curl -X POST https://app.erys.ai/api/agents/{agentId}/messages \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"content": "Hello! What can you do?"}'

5See the Response

Your agent will process the message and return a JSON response:

{
  "id": "msg_abc123",
  "content": "Hello! I'm your AI assistant. I can help answer questions about your product, summarise information, and assist with various tasks. What would you like to know?",
  "role": "assistant",
  "createdAt": "2026-02-07T10:30:00Z"
}

Your agent is now running. Every message is part of a persistent session, so your agent remembers context within a conversation. This enables natural, multi-turn interactions without needing to resend conversation history.