A resilient architecture is the foundation for building a successful business. However, keeping up with the latest advances and ensuring system resilience can be a daunting task. Missing critical information while monitoring, analyzing, and documenting architectural findings can leave your organization vulnerable to potential risks and inefficiencies. Even when an architecture assessment is performed, the report can be highly technical and difficult to understand for key stakeholders.
In this post, we explore how you can leverage the power of AWS Resilience Hub and Amazon Bedrock to bridge this gap and streamline the process of sharing architectural findings across your organization. Learn about a solution that uses Amazon Bedrock’s generative AI capabilities to translate technical reports into concise natural language summaries that are accessible to a broader audience.
Resilience Hub and Amazon Bedrock’s capabilities enable you to share your findings with executives, engineers, managers, and others within your enterprise to gain greater visibility into maintaining resilient architectures.
Solution overview
By combining Resilience Hub and Amazon Bedrock, you can generate architectural findings in natural language to save time and understand recovery time objectives (RTO) and recovery point objectives (RPO) requirements with clarity and clarity. You can distribute ratings through concise views. Resilience Hub is a central location on the AWS Management Console to manage, define, and evaluate your resilience goals using recommendations based on the AWS Well-Architected Framework. Amazon Bedrock is a complete platform for building generative AI applications through a single API using foundational models (FMs) from leading AI companies such as Anthropic, Mistral AI, Meta, Stability AI, Cohere, AI21 Labs, and Amazon. Managed service. Amazon Bedrock allows you to integrate generative AI solutions within your applications with the ability to test, fine-tune, and customize top FMs based on your use case.
The solution presented in this post is orchestrated through Amazon Cognito and logs into a sample UI that invokes an AWS Lambda function and an Amazon Bedrock prompt through a large-scale language model (LLM). Resilience Hub provides resiliency and operational recommendations such as alarms, standard operating procedures (SOPs), and fault injection experiments through AWS Fault Injection Service (FIS). When an assessment Amazon Resource Name (ARN) is entered from Resilience Hub, the results are summarized in natural language for sharing with others.
The following diagram shows the solution architecture.
The solution workflow includes the following steps:
- Users authenticate with a username and password through Amazon Cognito.
- Users access the main UI through Amazon CloudFront, which runs a single-page application hosted on Amazon Simple Storage Service (Amazon S3).
- Amazon API Gateway validates the access token with Amazon Cognito and uses the Lambda function as an integration target.
- Lambda collects the latest reputation ARN from applications published on Resilience Hub.
- The second Lambda function calls the Amazon Bedrock API.
- Amazon Bedrock processes the assessment and uses rapid engineering techniques to generate reports in natural language based on your target personas.
Prerequisites
This tutorial requires the following:
Deploying solution resources
You can deploy your solution using CloudFormation templates in our GitHub repository to automatically provision the necessary resources in your AWS account. Provision an Amazon S3 hosted UI using AWS CDK.
Run the solution
To run the solution, follow these steps:
- In your terminal or your preferred integrated development environment (IDE), run the following command:
- Using your favorite text editor (vim, nano, notepad),
EMAIL
inconstants.py
Create a file with the email. - Deploy using the following code:
Wait until the CloudFormation template starts successfully. Deploying this template takes approximately 10 minutes.
- AWS CloudFormation console, stack output In the tab, find the public URL of your web application (
CLOUDFRONTDISTRIBUTION
).
The user name is constants.py
Files and temporary passwords.
- Log in using the provided credentials and confirm the password change.
- In the UI, select report in the navigation pane.
- for personaselect the desired persona.
- for applicationselect the desired application from the list of existing published applications.
- choose Generate a report Review concise, summarized reports generated from the latest assessments. This report is ready for distribution.
Check the overview
This solution includes high-level examples from the executive sample stack. Due to the nature of the generation AI, your results may vary slightly, but should look similar to the following screenshot.
cleaning
To clean up your solution, follow these steps:
- In the AWS CloudFormation console, delete the CloudFormation stack you created earlier.
- If you downloaded a sample CloudFormation template to evaluate with Resilience Hub, delete that stack as well.
- Delete the newly created application in the Resilience Hub console. This will remove the rating.
conclusion
In this post, we discussed how Resilience Hub and Amazon Bedrock can significantly improve the maintenance and evaluation of resilient architectures within your organization. The solution automatically translates technical architectural findings into natural language summaries, making critical information accessible to a variety of stakeholders, including executives, auditors, and managers. Streamlined communication improves understanding, speeds decision-making, and ultimately benefits business operations. Integrating AWS services like Lambda and Amazon Cognito further automates and simplifies your workflows, providing a seamless experience from assessment to reporting.
Are you ready to strengthen your organization’s architectural resilience? Deploy the solution today and follow the steps outlined in this post to transform your technical reports into concise summaries. This gives stakeholders access to critical information and fosters informed decision-making and a resilient culture.
For more information and related content, see:
About the author
Ibrahim Ahmad I’m a Solutions Architect at AWS with a focus on resiliency and machine learning. He builds solutions for government technology customers to scale and modernize their cloud solutions. Outside of work, I love spending time with friends and family, working out, and racing cars.
Mike P.. I’m a Senior Solutions Architect at AWS based in South Florida. He specializes in helping customers use AWS services to strengthen their security posture and explore the potential of generative AI technologies. Mike works closely with organizations to design and implement robust security solutions while exploring innovative use cases for generative AI.
leland johnson I am a Senior Solutions Architect at AWS with a focus on Travel and Hospitality. As a Solutions Architect, you play a key role in guiding customers through their cloud journey by designing scalable and secure cloud solutions. Outside of work, I enjoy playing music and flying light aircraft.