Skip to content

Testing Your Setup

Testing Studio

  1. Once you are set up, you should be able to login to the Studio via Auth0's login options (Gmail, Github etc.).
  2. For the open source installation, the URL for Studio is http://localhost:3000

  3. To use our hosted app, the URL for Studio is https://app.rowboatlabs.com

  4. Once in Studio, create a new blank project or browse through one of the example projects: Create Project

  5. Use the copilot to help you build agents: Use Copilot

  6. Ensure that the correct agent is set as the "start agent": Set Start Agent

  7. Test out a chat in the playground to verify the agents' behavior: Testing Chat

Testing the Chat API

  • For the open source installation, the <HOST> is http://localhost:3000
  • When using the hosted app, the <HOST> is https://app.rowboatlabs.com
  • <PROJECT_ID> is available in the URL of the project page
  • API Key can be generated from the project config page at <HOST>/projects/<PROJECT_ID>/config

Below is an example request and response. Modify the user message in the request, based on your example project.

Request:

curl --location 'http://<HOST>/api/v1/<PROJECT_ID>/chat' \
--header 'Content-Type: application/json' \
--header 'Authorization: Bearer <API_KEY>' \
--data '{
    "messages": [
        {
            "role": "user",
            "content": "What is my pending payment amount?"
        }
    ]
}'

Response: The last message in messages is either a user-facing response or a tool call by the assistant.

{
    "messages": [
        {
            "sender": "Credit Card Hub",
            "role": "assistant",
            "response_type": "internal",
            "content": null,
            "created_at": "2025-02-01T06:55:47.843909",
            "current_turn": true,
            "tool_calls": [
                {
                    "function": {
                    "arguments": "{\"args\":\"\",\"kwargs\":\"\"}",
                    // Internal tool calls are used to transfer between agents
                    "name": "transfer_to_outstanding_payment"
                    },
                    "id": "call_7jGpwpVvzhZFOyRgxHFkdOdU",
                    "type": "function"
                }
            ]
        },
        {
            "tool_name": "transfer_to_outstanding_payment",
            "role": "tool",
            "content": "{\"assistant\": \"Outstanding Payment\"}",
            "tool_call_id": "call_7jGpwpVvzhZFOyRgxHFkdOdU"
        },
        {
            "sender": "Outstanding Payment",
            "role": "assistant",
            // Response is not user-facing, to enable further post processing
            "response_type": "internal",
            "content": "Sure, could you provide the last four digits of your card or your registered mobile number so I can look up your pending payment amount?",
            "created_at": "2025-02-01T06:55:49.648008",
            "current_turn": true
        },
        {
            "sender": "Outstanding Payment >> Post process",
            "role": "assistant",
            // Response is user-facing
            "response_type": "external",
            "content": "Sure, please provide the last four digits of your card or your registered mobile number so I can check your pending payment amount.",
            "created_at": "2025-02-01T06:55:49.648008",
            "current_turn": true
        }
    ],
    "state": {
        // .. state data
    }
}

Testing the Python Chat SDK

  • For the open source installation, the <HOST> is http://localhost:3000
  • When using the hosted app, the <HOST> is https://app.rowboatlabs.com
  • <PROJECT_ID> is available in the URL of the project page
  • API Key can be generated from the project config page at <HOST>/projects/<PROJECT_ID>/config
pip install rowboat

Modify the user message in messages, based on your example project.

from rowboat import Client

client = Client(
    host="<HOST>",
    project_id="<PROJECT_ID>",
    api_key="<API_KEY>"  # Generate this from /projects/<PROJECT_ID>/config
)

# Simple chat interaction
messages = [{"role": "user", "content": "What is my pending payment amount?"}]
response_messages, state = client.chat(messages=messages)

The last message in response_messages is either a user-facing response or a tool call by the assistant.