Skip to main content

Create Your First Assistant

Use create_assistant() to create, deploy, and chat with your first assistant in a few lines of Python.

This is the fastest way to get started. For more control over the assistant lifecycle, see Custodian Class later.

Before You Begin​

Make sure you have:

Create a Python File​

Create a file named first_assistant.py:

from custodian_labs import create_assistant

app = create_assistant(
    model="gpt-4o",
    prompt="You are a helpful assistant for onboarding new users.",
    privacy_enabled=True,
)

print(app.chat_url)

reply = app.chat("What should a new admin do first?")
if reply is not None:
    print(reply.response)

Run the Assistant​

In your terminal, run:

python first_assistant.py

The SDK will:

  1. Create an assistant with your model and prompt.
  2. Deploy the assistant as an App.
  3. Send your message to the deployed app.
  4. Print the assistant's response.

Continue the Conversation​

The deployed App retains the active chat session automatically. Add a follow-up message:

response = app.chat("Can you explain that in one sentence?")
print(response.response)

The assistant receives the earlier conversation context without requiring you to manage the session ID manually.

Call .chat() without a message to continue chatting from your terminal:

app.chat()

Type exit or quit to end the interactive session.

Example​

Create your first assistant demo

Next Steps​