AWS prescriptive-guidance documentation change
Summary
Updated section title and modified SDK link to point to latest version
Security assessment
Changes are editorial improvements and link updates without security context. No vulnerabilities, security controls, or incidents are mentioned.
Diff
diff --git a/prescriptive-guidance/latest/strategy-operationalizing-agentic-ai/focus-areas-lifecycle.md b/prescriptive-guidance/latest/strategy-operationalizing-agentic-ai/focus-areas-lifecycle.md index 57f88dcf8..1126237eb 100644 --- a//prescriptive-guidance/latest/strategy-operationalizing-agentic-ai/focus-areas-lifecycle.md +++ b//prescriptive-guidance/latest/strategy-operationalizing-agentic-ai/focus-areas-lifecycle.md @@ -7 +7 @@ -StrategyBusiness value +StrategyBusiness value of lifecycle management @@ -21 +21 @@ Use feedback loops from observability data to initiate retraining, prompt tuning -Build a performance telemetry dashboard that shows decision accuracy, latency, cost, and reliability. To streamline and accelerate lifecycle management using AWS infrastructure, teams can use agent toolkits. One example is the [Strands Agents SDK](https://strandsagents.com/), which provides structured tooling for prompt versioning, tool registration, and CI/CD integration with AWS services, such as [AWS CodePipeline](https://docs.aws.amazon.com/codepipeline/latest/userguide/welcome.html), [AWS Cloud Development Kit (AWS CDK)](https://docs.aws.amazon.com/cdk/v2/guide/home.html), and [AWS Lambda](https://docs.aws.amazon.com/lambda/latest/dg/welcome.html). Additionally, use [Amazon S3](https://docs.aws.amazon.com/AmazonS3/latest/userguide/Welcome.html) and [Amazon Elastic File System (Amazon EFS)](https://docs.aws.amazon.com/efs/latest/ug/whatisefs.html) for storing agent artifacts and training data. Use [AWS Step Functions](https://docs.aws.amazon.com/step-functions/latest/dg/welcome.html) to automate complex retraining or validation workflows. You can use [Amazon SageMaker AI](https://docs.aws.amazon.com/sagemaker-unified-studio/latest/userguide/what-is-sagemaker-unified-studio.html) when agents require custom model tuning or fine-tuning workflows beyond LLM orchestration. Lifecycle discipline transforms agents from experiments into durable, evolving assets. +Build a performance telemetry dashboard that shows decision accuracy, latency, cost, and reliability. To streamline and accelerate lifecycle management using AWS infrastructure, teams can use agent toolkits. One example is the [Strands Agents SDK](https://strandsagents.com/latest/), which provides structured tooling for prompt versioning, tool registration, and CI/CD integration with AWS services, such as [AWS CodePipeline](https://docs.aws.amazon.com/codepipeline/latest/userguide/welcome.html), [AWS Cloud Development Kit (AWS CDK)](https://docs.aws.amazon.com/cdk/v2/guide/home.html), and [AWS Lambda](https://docs.aws.amazon.com/lambda/latest/dg/welcome.html). Additionally, use [Amazon S3](https://docs.aws.amazon.com/AmazonS3/latest/userguide/Welcome.html) and [Amazon Elastic File System (Amazon EFS)](https://docs.aws.amazon.com/efs/latest/ug/whatisefs.html) for storing agent artifacts and training data. Use [AWS Step Functions](https://docs.aws.amazon.com/step-functions/latest/dg/welcome.html) to automate complex retraining or validation workflows. You can use [Amazon SageMaker AI](https://docs.aws.amazon.com/sagemaker-unified-studio/latest/userguide/what-is-sagemaker-unified-studio.html) when agents require custom model tuning or fine-tuning workflows beyond LLM orchestration. Lifecycle discipline transforms agents from experiments into durable, evolving assets.