Gather the following information which will be required for the Terraform configuration:

• AWS Account Number (12-digit number)
• VPC ID (vpc-xxxxxxxxxxxxxxxxx)
• Two Subnet IDs:
  • subnet-xxxxxxxxxxxxxxxxx
  • subnet-xxxxxxxxxxxxxxxxx

Helpful AWS CLI commands:

# List your VPCs
aws ec2 describe-vpcs

# List subnets in a specific VPC
aws ec2 describe-subnets --filters "Name=vpc-id,Values=<your-vpc-id>"

Contact Cognition to receive:

1. An authentication token for pulling the hypervisor image
2. The Terraform configuration files customized for your environment

Once you share your environment information (from Step 1), we will provide these resources to you.

We can schedule a call to execute this step together. The process involves:

1. Extract the Terraform configuration files to a directory on your local machine:

   Copy

   Ask AI

   mkdir -p ~/devin-terraform && cd ~/devin-terraform
   # Extract files received from Cognition
   

2. Initialize the Terraform environment:

   Copy

   Ask AI

   terraform init
   

3. Review the planned infrastructure changes:

   Copy

   Ask AI

   terraform plan
   

4. Apply the configuration to provision the infrastructure:

   Copy

   Ask AI

   terraform apply
   

5. Confirm the changes when prompted.

After the Terraform script completes successfully, we will work together to:

1. Verify that the resources have been created in your AWS console
2. Run a first Devin session to ensure connectivity to the required services
3. Debug any issues that arise with the support of Cognition team

Devin requires a host instance to run isolated virtual machines for each session.

​

Instance Requirements

​

Security Group Rules

When Devin sessions are suspended, their state is compressed and stored.

​

2.1 Create an S3 Bucket

1. Navigate to S3 in the AWS Management Console

2. Select the appropriate region

3. Click Create bucket

4. Set the Bucket name as:

   Copy

   Ask AI

   devin-${YOUR_ORGANIZATION}-${BUCKET_REGION}
   

   (Replace ${YOUR_ORGANIZATION} and ${BUCKET_REGION} with actual values)

5. Click Create bucket

​

2.2 Apply S3 Bucket Policy & CORS

1. Open the S3 Bucket you created
2. Navigate to the Permissions tab
3. Scroll to Bucket Policy and click Edit
4. Add the following policy, replacing placeholders:

{
    "Version": "2012-10-17",
    "Statement": [
        {
            "Principal": {"AWS": "arn:aws:iam::272506498303:role/customer-bucket-access-role"},
            "Effect": "Allow",
            "Action": ["s3:GetObject", "s3:PutObject", "s3:DeleteObject"],
            "Resource": "arn:aws:s3:::devin-${YOUR_ORGANIZATION}-${BUCKET_REGION}/*"
        },
        {
            "Principal": {"AWS": "arn:aws:iam::272506498303:role/customer-bucket-access-role"},
            "Effect": "Allow",
            "Action": ["s3:ListBucket"],
            "Resource": "arn:aws:s3:::devin-${YOUR_ORGANIZATION}-${BUCKET_REGION}"
        }
    ]
}

5. Click Save
6. Scroll down to Cross-Origin Resource Sharing (CORS) and click Edit
7. Enter the following CORS policy:

[
    {
        "AllowedHeaders": ["*"],
        "AllowedMethods": ["GET"],
        "AllowedOrigins": ["*"],
        "ExposeHeaders": []
    }
]

8. Click Save

Run the following command:

curl -sSL https://api.devin.ai/hypervisor/setup?token=AUTH_TOKEN -o setup.sh && bash setup.sh

If user devices have a firewall, whitelist the following URLs:

• *.devin.ai
• *.devinenterprise.com
• *.devinapps.com
  

Sample AWS WAF Rule