Enhance your HashiCorp Cloud Platform Terraform (Terraform Cloud) workflows with AI-powered analysis using Amazon Bedrock. This module integrates seamlessly as a Run Task to provide:
- Intelligent Terraform plan analysis with concise, human-friendly summaries
- Advanced function calling capabilities for extended analysis (e.g., AMI evaluation)
- Responsible AI implementation with customizable guardrails
-
AI-Powered Plan Summaries
-
Extensible Analysis with Function Calling
-
Responsible AI Integration
-
Secure Architecture
- Designed for deployment in a dedicated AWS account
- Optional AWS WAF integration for enhanced endpoint protection
- Adherence to AWS security best practices
-
Seamless Terraform Cloud Integration
- Operates as a native Run Task within your Terraform Cloud workflow
- Provides insights without disrupting existing processes
-
Flexible and Customizable
- Adapt the module to fit your specific organizational needs
- Easily configure and extend guardrails and analysis capabilities
This module leverages a hub-spoke model, designed for deployment in a dedicated AWS account with Amazon Bedrock access. It utilizes AWS Lambda, CloudFront, and other AWS services to provide a scalable and secure solution.
To implement this module, you'll need:
- An AWS account with appropriate credentials
- Access to Amazon Bedrock (default model: Claude 3 Sonnet)
- A HashiCorp Cloud Platform (HCP) Terraform account
For detailed setup instructions and best practices, please refer to the sections below:
Enhance your Terraform workflows with AI-powered insights while maintaining security and responsible AI practices.
-
Build and package the Lambda files
make all -
Enable Bedrock model access for
Claude 3 Sonnet. Refer to this guide for more info. -
Reference the
examples/basicfolder on how to use this modulecd examples/basic terraform init terraform plan terraform apply
-
Do not re-use the Run Tasks URL across different trust-boundary (organizations, accounts, team). We recommend you to deploy separate Run Task deployment per trust-boundary.
-
Do not use Run Tasks URL from untrusted party, remember that Run Tasks execution sent Terraform plan output to the Run Task endpoint. Only use trusted Run Tasks URL.
-
Enable the AWS WAF setup by setting variable
deploy_waftotrue(additional cost will apply). This will add WAF protection to the Run Tasks URL endpoint. -
We recommend you to setup additional CloudWatch alarm to monitor Lambda concurrency and WAF rules.
-
We recommend to add additional topic to the Bedrock Guardrail to fit your organization requirements.
This solution sends operational metrics to AWS (the “Data”) about the use of this solution. We use this Data to better understand how customers use this solution and related services and products. AWS’s collection of this Data is subject to the AWS Privacy Notice.
| Name | Version |
|---|---|
| terraform | >= 1.5.0 |
| archive | ~>2.2.0 |
| aws | >= 5.72.0 |
| random | >=3.4.0 |
| Name | Version |
|---|---|
| archive | ~>2.2.0 |
| aws | >= 5.72.0 |
| aws.cloudfront_waf | >= 5.72.0 |
| random | >=3.4.0 |
| terraform | n/a |
| time | n/a |
| Name | Source | Version |
|---|---|---|
| runtask_cloudfront | terraform-aws-modules/cloudfront/aws | 3.4.0 |
| Name | Description | Type | Default | Required |
|---|---|---|---|---|
| aws_region | The region from which this module will be executed. | string |
n/a | yes |
| hcp_tf_org | HCP Terraform Organization name | string |
n/a | yes |
| bedrock_llm_model | Bedrock LLM model to use (supports cross-region inference profiles) | string |
"global.anthropic.claude-sonnet-4-20250514-v1:0" |
no |
| cloudwatch_log_group_name | RunTask CloudWatch log group name | string |
"/hashicorp/terraform/runtask/" |
no |
| cloudwatch_log_group_retention | Lambda CloudWatch log group retention period | string |
"365" |
no |
| deploy_waf | Set to true to deploy CloudFront and WAF in front of the Lambda function URL | string |
false |
no |
| event_bus_name | EventBridge event bus name | string |
"default" |
no |
| event_source | EventBridge source name | string |
"app.terraform.io" |
no |
| lambda_architecture | Lambda architecture (arm64 or x86_64) | string |
"x86_64" |
no |
| lambda_default_timeout | Lambda default timeout in seconds | number |
300 |
no |
| lambda_python_runtime | Lambda Python runtime | string |
"python3.11" |
no |
| lambda_reserved_concurrency | Maximum Lambda reserved concurrency, make sure your AWS quota is sufficient | number |
10 |
no |
| name_prefix | Name to be used on all the resources as identifier. | string |
"runtask-tf-plan-analyzer" |
no |
| recovery_window | Number of days that AWS Secrets Manager waits before it can delete the secret | number |
0 |
no |
| run_task_iam_roles | List of IAM roles to be attached to the Lambda function | list(string) |
null |
no |
| runtask_stages | List of all supported run task stages | list(string) |
[ |
no |
| tags | Map of tags to apply to resources deployed by this solution. | map(any) |
null |
no |
| waf_managed_rule_set | List of AWS Managed rules to use inside the WAF ACL | list(map(string)) |
[ |
no |
| waf_rate_limit | Rate limit for request coming to WAF | number |
100 |
no |
| workspace_prefix | HCP Terraform workspace name prefix that allowed to run this run task | string |
"" |
no |
| Name | Description |
|---|---|
| runtask_hmac | HMAC key value, keep this sensitive data safe |
| runtask_url | The Run Tasks URL endpoint, you can use this to configure the run task setup in HCP Terraform |



