article thumbnail

Enable Amazon Bedrock cross-Region inference in multi-account environments

AWS Machine Learning

The customers AWS accounts that are allowed to use Amazon Bedrock are under an Organizational Unit (OU) called Sandbox. We want to enable the accounts under the Sandbox OU to use Anthropics Claude 3.5 Use case For our sample use case, we use Regions us-east-1 and us-west-2. Sonnet v2 model using cross-Region inference.

article thumbnail

On Being an Accountable Customer Service Leader

Customer Service Life

Properly authenticating the account. Leaving complete account notes for the next person who interacts with the customer. This exercise reminded me of the time when we started this blog back in 2012. Starting a blog about customer service became instant accountability for me. Quality as accountability.

Insiders

Sign Up for our Newsletter

This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.

Trending Sources

article thumbnail

Security best practices to consider while fine-tuning models in Amazon Bedrock

AWS Machine Learning

The workflow steps are as follows: The user submits an Amazon Bedrock fine-tuning job within their AWS account, using IAM for resource access. The fine-tuning job initiates a training job in the model deployment accounts. Provide your account, bucket name, and VPC settings. The following code is a sample resource policy.

article thumbnail

Want More Sales? Give All Your Money Away!

Beyond Philosophy

Sales soared in 2012. In our customer experience consultancy, we help companies design a customer experience that that fosters customer loyalty and engagement by taking customers’ emotional behavior into account. This isn’t the first time Patagonia has scored big by proclaiming its environmental and social values.

Sales 353
article thumbnail

Amazon Bedrock Guardrails announces IAM Policy-based enforcement to deliver safe AI interactions

AWS Machine Learning

If a user assumes a role that has a specific guardrail configured using the bedrock:GuardrailIdentifier condition key, the user can strategically use input tags to help avoid having guardrail checks applied to certain parts of their prompt.

article thumbnail

Set up cross-account Amazon S3 access for Amazon SageMaker notebooks in VPC-only mode using Amazon S3 Access Points

AWS Machine Learning

With an increase in use cases and datasets using bucket policy statements, managing cross-account access per application is too complex and long for a bucket policy to accommodate. This post walks through the steps involved in configuring S3 Access Points to enable cross-account access from a SageMaker notebook instance.

article thumbnail

Build a cross-account MLOps workflow using the Amazon SageMaker model registry

AWS Machine Learning

When designing production CI/CD pipelines, AWS recommends leveraging multiple accounts to isolate resources, contain security threats and simplify billing-and data science pipelines are no different. Some things to note in the preceding architecture: Accounts follow a principle of least privilege to follow security best practices.