​

Build Your First Assistant

This quick start guide will walk you through the process of creating and deploying a “Personal Assistant” using the Kosmoy Studio, leveraging a pre-integrated OpenAI connection and the powerful GPT-4o model.

Prerequisites:

• A Kosmoy account with a configured tenant.
• You should be either the Root User or an Admin User or a Studio User.

Steps:

​

1. Integrate with OpenAI

1. Navigate to Integrations: From the Kosmoy Studio home page, click on the “Integrations” icon in the left-hand navigation bar.

2. Add a New Integration: Click the ”+ ADD” button located in the upper right corner of the Integrations section.

3. Select OpenAI: In the “Add Integration” workflow, choose “OpenAI” from the provider dropdown menu.

4. Provide your OpenAI API Key: Enter your OpenAI API key in the designated field.

5. Click “Next”: Proceed to the next step.

6. Name and Describe the Integration: Give your integration a unique name (e.g., “My OpenAI Integration”) and an optional description.

7. Click “Review”: Review the integration details.

8. Click “Create”: Create the integration.

​

2. Register the GPT-4o Model

1. Navigate to Models: Click on the “Models” icon in the left-hand navigation bar.

2. Add a New Model: Click the ”+ ADD” button located in the upper right corner of the Models section.

3. Define Model Type: Select “LLM” as the model type.

4. Choose Provider and Integration: Select “OpenAI” as the provider and then choose the OpenAI integration you just created from the integration dropdown.

5. Select Model Version: Select “GPT-4o” from the model version dropdown.

6. Click “Next”: Proceed to the next step.

7. Name and Describe the Model: Give your model a unique name (e.g., “My GPT-4o Model”) and an optional description.

8. Click “Review”: Review the model details.

9. Click “Create”: Create the model registration.

​

3. Create a Personal Assistant

1. Navigate to Assistants: Click on the “Assistants” icon in the left-hand navigation bar.

2. Add a New Assistant: Click the ”+ ADD” button located in the upper right corner of the Assistants section.

3. Configure Basic Details:

   • Avatar: Select an avatar for your assistant.
   • Name: Give your assistant a name (e.g., “My First Assistant”).
   • Description: Provide a brief description of your assistant.

4. Select Template: Choose the “Personal Assistant” template.

5. Define Scope: Select “Private” as the assistant’s scope.

6. Configure Language: Keep the default value (“auto”) for the language setting.

7. Click “Next”.

8. Skip Data Channel and Memory: For this quick start, we’ll skip configuring a Data Channel and leave the Memory settings at their defaults (1 day and 10 past interactions).

9. Disable Guardrails: For this quick start, we will keep the Guardrails turned off.

10. Select Models:

    • Conversational Model: Select the “My GPT-4o Model” (or the name you gave it) you registered earlier.
    • Instructional Model: Select the “My GPT-4o Model” (or the name you gave it) you registered earlier.

11. Configure Assistant Prompt:

    • Role: Define the role of your assistant. Example: You are a helpful personal assistant.
    • Task: Describe the assistant’s task. Example: Your task is to assist the user with scheduling meetings, answering general knowledge questions, and providing recommendations based on their preferences.
    • Operating Principles: Establish the principles guiding the assistant’s behavior. Example: 1. Always be polite and respectful. 2. Prioritize user safety and privacy. 3. Provide accurate and up-to-date information. 4. Ask clarifying questions when needed.
    • Attitude: Define the attitude to be displayed by your assistant Example: Professional and friendly
    • Welcoming Message: Write a welcoming message for users. Example: Hello! I'm your personal assistant. How can I help you today?
    • Goodbye Message: Write a goodbye message for users. Example: Goodbye! Have a great day.

12. Click “Review”: Review the assistant’s configuration.

13. Click “Create”: Create the assistant. You will be redirected to the Assistants collection page.

​

4. Deploy the Assistant

1. Locate Your Assistant: On the Assistants collection page, find the card for the assistant you just created.

2. Initiate Deployment: Click the rocket icon (without a shadow) located on the lower left side of the assistant’s card.

3. Review Assistant Details: Review the assistant’s details on the deployment page.

4. Click “Next”.

5. Select Users: Select yourself from the list of users to grant access to this private assistant.

6. Click “Review”.

7. Click “Deploy”: Deploy the assistant.

​

5. Chat with Your Assistant

1. Access Kosmoy Chat: Navigate to your Kosmoy Chat instance at [tenant_name].client.kosmoy.com.
2. Start Chatting: You should now see your newly deployed “Personal Assistant” available in Kosmoy Chat. Start a conversation and test its capabilities!

Congratulations! You have successfully created and deployed your first AI assistant using Kosmoy Studio.

Next Steps:

• Explore the advanced features of Kosmoy Studio, including Data Channels, Routers, and Guardrails.
• Create more sophisticated assistants tailored to your specific needs.
• Refer to the detailed documentation sections for each Kosmoy Studio component to learn more.