Example deployment using AI Copilot

This section will walk you through a deployment of an AWS VPC and Subnet infrastructure.

The following are the main steps to deploy infrastructure using the AI Copilot:

1. Pre-requisites

It is assumed that you are able to login to QMCLOUD and have created the pre-requisites including stack profile and a stack.

1. Select the stack and click on canvas button to open the canvas

2. Select the AI Copilot assistant button on the bottom right of the canvas as shown below (marked with a red arrow):

Canvas - AI Copilot chat icon

1. The AI Copilot assistant window opens as shown below. Refer to the user interaction prompt window at the bottom of the assistant (marked with red):

AI Copilot assistant

1. Enter a description of the desired infrastructure to be deployed. For example, in this case the user enters the following description as shown below and click the small arrow button to submit the description:

create the following components including aws vpc named vpcaws1 with cidr 172.35.0.0/19, one public subnet with /20, an igw, a "route table association", a "route table" for this vpc and a "route" with default route of 0.0.0.0/0 with target gateway as the igw in the route.

1. The AI Copilot will automatically generate an appropriate configuration based on the user description and prompts the user to click ok as shown below:

AI Copilot assistant output

1. Once the user selects "Ok" the assistant generates the visualization and renders the proposed infrastructure on the canvas as shown below:

AI Copilot assistant canvas render

1. The user can now review the proposed configuration and make changes if any.

2. As with any generative AI based technology, the more information and context that is provided to the assistant, the more accurate responses will be.

For example, in a case where a user may not have added the context, the assistant may miss a dependency between various components. In this example deployment, the "Subnet" component may not be connected to the "Vpc" component. The user can manually connect the Subnet and the Vpc components together using a connector. (Select the red dot for the Subnet component representing the vpcid property and connect to the green dot of the Vpc component)

1. The user can now initiate the deployment using the Save, Validate, Plan and Deploy action buttons on the canvas as shown below marked in red:

AI Copilot canvas action buttons

1. Once the deployment is completed, the user can check the logs by clicking on the "Status" area at the bottom of the canvas. A status log is shown as shown below:

Status Log

1. This completes the deployment using the AI Copilot assistant.

In summary, the AI Copilot assistant was used to enter a description of the desired AWS infrastructure and the assistant generates the required configuration and renders the visualization on the canvas. The user can make changes if any and initiate the deployment.