AWS prescriptive-guidance documentation change
Summary
Formatting changes including header styling updates, section heading improvements from italicized text to markdown headers, and a shortened link label for security documentation reference.
Security assessment
Changes are primarily structural/formatting improvements without introducing or modifying security-related information. The security reference change only shortens the link text without altering security guidance content.
Diff
diff --git a/prescriptive-guidance/latest/strategy-enterprise-ready-gen-ai-platform/model.md b/prescriptive-guidance/latest/strategy-enterprise-ready-gen-ai-platform/model.md index 422e3b0a2..70e0aa917 100644 --- a//prescriptive-guidance/latest/strategy-enterprise-ready-gen-ai-platform/model.md +++ b//prescriptive-guidance/latest/strategy-enterprise-ready-gen-ai-platform/model.md @@ -7 +7 @@ -Experimentation and customizationEvaluationImplementation recommendations +Model experimentation and customizationModel evaluationImplementation recommendations @@ -13 +13 @@ As organizations navigate the early stages of generative AI adoption, they quick -###### This section contains the following topics: +**This section contains the following topics:** @@ -28 +28 @@ As organizations navigate the early stages of generative AI adoption, they quick -Additionally, you can use Amazon Bedrock to [privately customize the foundation models](https://docs.aws.amazon.com/bedrock/latest/userguide/custom-models.html) with your own proprietary data and make them securely available to the users within your organization. For more information, see [Customize your model to improve its performance for your use case](https://docs.aws.amazon.com/bedrock/latest/userguide/custom-models.html) in the Amazon Bedrock documentation. For access management, AWS Identity and Access Management (IAM) integrates with Amazon Bedrock so that you can configure fine-grained access control. The controls determine which users can enable and access specific models. For more information, see [Layer 3: Security and governance for generative AI platforms on AWS](./security.html) in this guide. +Additionally, you can use Amazon Bedrock to [privately customize the foundation models](https://docs.aws.amazon.com/bedrock/latest/userguide/custom-models.html) with your own proprietary data and make them securely available to the users within your organization. For more information, see [Customize your model to improve its performance for your use case](https://docs.aws.amazon.com/bedrock/latest/userguide/custom-models.html) in the Amazon Bedrock documentation. For access management, AWS Identity and Access Management (IAM) integrates with Amazon Bedrock so that you can configure fine-grained access control. The controls determine which users can enable and access specific models. For more information, see [Layer 3: Security and governance](./security.html) in this guide. @@ -55 +55 @@ Use ground truth-based metrics if reference data exists. These metrics provide c -_Metrics based on ground truth data_ +#### Metrics based on ground truth data @@ -74 +74 @@ Amazon SageMaker Clarify and Amazon Bedrock include features to help you evaluat -_Metrics without ground truth data_ +#### Metrics without ground truth data