Quick Start¶

Get AG2Trust up and running in 5 minutes.

Step 1: Sign Up and Log In¶

1. Go to app.ag2trust.com
2. Sign up with your email or Google account
3. Complete the onboarding flow

Step 2: Add an LLM Provider¶

AG2Trust needs access to an LLM provider (OpenAI or Anthropic) to power your agents.

1. Navigate to Settings > Providers
2. Click Add Provider
3. Select your provider (OpenAI or Anthropic)
4. Enter your API key
5. Click Save

Step 3: Create Your First Agent¶

1. Navigate to Agents in the sidebar
2. Click Create Agent
3. Fill in the agent details:
4. Name: Give your agent a descriptive name (e.g., "Customer Support Bot")
5. System Prompt: Define your agent's personality and behavior
6. Provider: Select the provider you added
7. Model: Choose the model (e.g., gpt-4o, claude-sonnet-4-20250514)
8. Click Create

Example System Prompt¶

You are a helpful customer support agent for Acme Corp. You help users with:
- Account questions
- Billing inquiries
- Technical support

Be friendly, professional, and concise. If you don't know the answer,
say so and offer to escalate to a human agent.

Step 4: Start and Test Your Agent¶

1. Click the Start button on your agent card
2. Wait for the status to change to Running (usually 5-10 seconds)
3. Click on the agent to open the chat interface
4. Send a test message: "Hello, what can you help me with?"

Step 5: Get Your API Key (Optional)¶

To send messages programmatically:

1. Navigate to Settings > API Keys
2. Click Generate API Key
3. Copy and securely store your API key

Test with cURL¶

curl -X POST https://agents.ag2trust.com/api/v1/agents/{agent_id}/messages \
  -H "X-API-Key: cust_your_api_key_here" \
  -H "Content-Type: application/json" \
  -d '{"message": "Hello, what can you help me with?"}'

Response¶

{
  "message_id": "msg_abc123",
  "content": [
    {
      "type": "text",
      "text": "Hello! I'm here to help you with account questions, billing inquiries, and technical support. How can I assist you today?"
    }
  ],
  "metadata": {
    "tokens_used": 45,
    "model": "gpt-4o",
    "duration_ms": 1250
  }
}

What's Next?¶

Now that you have a working agent, explore these topics:

• Create Agent Pools for load balancing
• Set up Webhooks for async responses
• Organize Agents into Teams
• Configure User Permissions

Troubleshooting¶

Agent won't start¶

1. Check that your provider API key is valid
2. Ensure your provider has available credits/quota
3. Check the agent logs in the Dashboard

API returns 401 Unauthorized¶

1. Verify your API key is correct
2. Check the API key hasn't been revoked
3. Ensure you're using the X-API-Key header

Agent responds slowly¶

1. Check your provider's rate limits
2. Consider using a faster model (e.g., gpt-4o-mini)
3. Review your system prompt length

Need more help? Check our complete documentation or contact support.