OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
AI Developer Tools & SDKs

AWS Well-Architected Review GenAI Sample

A Python sample application that uses generative AI to analyze AWS architecture documents and prepare Well-Architected Framework reviews, with an option to create a workload in the AWS Well-Architected Tool.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

AWS Well-Architected Review GenAI Sample — OpenViST project profile in AI Developer Tools & SDKs.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use it when building an AWS-hosted workflow to speed up an initial architecture assessment or to carry assessment results into a Well-Architected Tool workload.

Who it is for

  • AWS teams reviewing solution designs or architecture documents.
  • Developers and architects implementing a generative-AI-assisted Well-Architected review workflow.

Documented uses

  • Upload PDF technical documents for architecture analysis.
  • Generate a solution summary, assessment, best practices, recommendations and risks.
  • Ask questions about the uploaded document and generated review.
  • Create an AWS Well-Architected Tool workload with initial question selections and assessment notes.
Before you choose

Requirements & limits

The repository is public and licensed under MIT-0. The application instructions describe deployment to AWS and login through a user created in Amazon Cognito.

  • Quick analysis is described as faster and does not create a Well-Architected Tool workload; the deep option creates one.
  • The implementation requires access to specified Amazon Bedrock models and a CDK deployment environment.
  • The sample includes Amazon Bedrock Guardrails enabled by default and allows optional features to be changed in app.py.
  • OpenSearch Serverless redundancy can be disabled to reduce stack cost during development and testing.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Deploy the sample and open its Streamlit interface

Prepare and deploy the sample with AWS CDK, then access its web interface.

Before you start

  • Access to Amazon Bedrock models Titan Text Embeddings V2 and Claude 3.5 Sonnet.
  • Python 3.9 or later, AWS CDK v2, Docker CE, and the AWS CDK prerequisites.
  • An AWS account and a configured deployment region.

Steps

  1. Clone or download the repository and install its Python dependencies in a virtual environment.

  2. Set the CloudFront managed prefix list for the deployment region and configure the AWS account and region in the CDK app.

  3. Bootstrap the account with CDK if this is its first CDK deployment, then synthesize and deploy the stack.

  4. Create a user in the Cognito user pool named in the deployment output, then launch the Streamlit application and open the CloudFront URL.

Expected outcome

A deployed web interface for creating a Well-Architected review, accessed through the CloudFront URL.

Guide limitations

  • The README estimates deployment at about 20–25 minutes.
  • The sample requires AWS resources and configured Bedrock model access; it is not a hosted service.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
17 October 2026
Original website title
aws-samples/sample-well-architected-acceleration-with-generative-ai · Official homepage title · retained in its source language
How we review sourcesSuggest a correction