AWS wellarchitected medium security documentation change
Summary
Added new section on Generative AI and Machine Learning services including Amazon Bedrock, SageMaker AI, Bedrock Knowledge Bases, Bedrock Model Evaluation, OpenSearch Service vector, and Bedrock Prompt Engineering tools. Updated question from FSIPERF06 to FSIPERF09 focusing on AI system monitoring.
Security assessment
Explicitly mentions 'enterprise-grade security and privacy' for Amazon Bedrock and 'securely connect foundation models to company data' for Bedrock Knowledge Bases. These additions document security features for AI services handling sensitive financial data.
Diff
diff --git a/wellarchitected/latest/financial-services-industry-lens/perf-key-aws-services.md b/wellarchitected/latest/financial-services-industry-lens/perf-key-aws-services.md index 219f45f69..58da2f22f 100644 --- a//wellarchitected/latest/financial-services-industry-lens/perf-key-aws-services.md +++ b//wellarchitected/latest/financial-services-industry-lens/perf-key-aws-services.md @@ -65,0 +66,17 @@ +**Generative AI and Machine Learning** + + * [Amazon Bedrock](https://aws.amazon.com/bedrock/) is a fully managed service that offers foundation models from leading AI companies through a unified API, allowing for efficient development of generative AI applications with enterprise-grade security and privacy. + + * [Amazon SageMaker AI](https://aws.amazon.com/sagemaker/) is a comprehensive service that helps data scientists and developers prepare, build, train, and deploy high-quality machine learning models with infrastructure, tools, and workflows. + + * [Amazon Bedrock Knowledge Bases](https://aws.amazon.com/bedrock/knowledge-bases/) allows you to connect foundation models to your company data securely, ensuring responses are relevant, accurate, and specific to your business context. + + * [Amazon Bedrock Model Evaluation](https://aws.amazon.com/bedrock/evaluations/) helps you evaluate, compare, and select the most appropriate foundation models for your specific use cases by measuring performance on custom evaluation sets. + + * [Amazon OpenSearch Service vector](https://aws.amazon.com/opensearch-service/serverless-vector-database/) database capabilities enable efficient similarity search functionality for AI applications, with support for multiple algorithms and high-scale vector operations. + + * [Amazon Bedrock Prompt Engineering tools](https://docs.aws.amazon.com/bedrock/latest/userguide/prompt-engineering-guidelines.html) help optimize prompts for better AI responses, with features for tracking and managing prompt history and performance. + + + + @@ -72 +89 @@ To use the Amazon Web Services Documentation, Javascript must be enabled. Please -FSIPERF06: How do you make trade-offs in your architecture? +FSIPERF09: How do you monitor and tune AI system performance?