From the course: Responsible AI on AWS: Bedrock Guardrails, Amazon Q Security, and SageMaker Clarify
Course introduction
From the course: Responsible AI on AWS: Bedrock Guardrails, Amazon Q Security, and SageMaker Clarify
Course introduction
- Hi, my name is Noah Gift, and I'm the founder of Pragmatic AI Labs, and this training is focused on three key technologies on AI on the Amazon platform. First up, we have Bedrock. Bedrock is a very fascinating platform, because it serves a foundational model interface where you can toggle out different foundational models like Anthropic Claude, or maybe you have internal Amazon models, or upcoming models like Mistral, and all these come together through this single interface, which allows us to do security and monitoring and governance. And that's really what this course is about is how do we dive into creating an enterprise-level, comprehensive way to think about Bedrock. We also get into the security components of Amazon Queue as well, and we go into a comprehensive enterprise-level overview, and then finally, we wrap up with Clarify from SageMaker, which allows you to look at some of the things that are more problematic with models, like what are the features that are driving this model? Is there an unbalanced dataset? How can I actually monitor the performance of a model in production? So, really fine-grained details that are available through the Clarify interface. So, that's the sum of the course, and we have a lot to cover, so let's go ahead and get started.
Contents
-
-
Course introduction1m 29s
-
(Locked)
AI security architecture4m 19s
-
(Locked)
AI auth patterns4m 1s
-
(Locked)
Complete AI security3m 49s
-
(Locked)
AI monitoring and logging3m 51s
-
(Locked)
AWS Rust compilation3m 49s
-
(Locked)
Monitoring Bedrock calls3m 46s
-
(Locked)
Visualizing Bedrock API calls2m 51s
-
-
-
-
-