Cross Cloud AI Agent
Bluebrick Cross-Cloud AI Agent is in BETA.
Introducing Cross-Cloud AI Agent
Cross-Cloud AI Agent is a tuned LLM developed by Bluebricks that seamlessly migrates infrastructure between AWS, GCP, Azure, and other cloud providers.
The Cross-Cloud AI Agent enables organizations to:
Instantly replicate infrastructure using Bluebricks AI and Atomic Infrastructure™.
Manage infrastructure updates seamlessly after migration.
Predict costs for workloads on the new cloud before migration is applied
How Cross-Cloud AI Agent Works

The Terraform State file is provided to the Bluebricks Cross-Cloud AI Agent.
The agent processes the State file and searches for equivalent Blueprints on GCP.
Once a match is found, the agent maps the provided parameters to the new Blueprints and supplies them as input.
The Cross-Cloud AI Agent won't initiate a deployment during the BETA phase.
How to Use Cross-Cloud AI Agent
Ensure that bricks CLI is installed on your local machine by running:
If not installed, follow the official Bluebricks installation guide to set it up.
Open the terminal and connect to your Bluebricks account by running:
Generate API Token and set it as an environment variable (use Long Live Tokens article for more info)
Prepare your Terraform State file, then start the Cross-Cloud AI Agent by running the following command:
Replace <path_to_state_file> with the actual path to your Terraform State file.
Understand the Output
The Cross-Cloud AI Agent generates Terraform files that are compatible with the target cloud. The files consist of equivalent modules and values matching the provided state.
The agent organizes the output files under a root folder called outputs, with a specific path for each discovered module, relative to the working directory.
Each matching module will include a variables.tf that takes the equivalent values as defaults for its matching vars.
Runtime Output Example
See below the output of the Cross-Cloud AI Agent when migrating the S3 bucket from AWS to GCP:

Next Steps
Review the generated code and modify it as needed.
Create a blueprint out of the generated code. Follow the Creating IaC Packages guide.
Install the created Blueprint
Last updated
Was this helpful?

