Generative AI
Generative AI solutions cover multiple use cases that affect your security scope. To
better understand the scope and corresponding key security disciplines, see the AWS blog post
Securing generative AI: An introduction to the Generative AI Security Scoping
Matrix. Depending on your use case, you might use a managed service where the
service provider takes more responsibility for the management of the service and model, or you
might build your own service and model. AWS offers a wide range of services to help you
build, run, and integrate artificial intelligence and machine learning (AI/ML) solutions of
any size, complexity, or use case. These services operate at all three layers of the generative AI stack: infrastructure layer for foundation model
(FM) training and inference, tooling layer to build with large language models (LLMs) and
other FMs, and application layer that uses LLMs and other FMs. This guidance focuses on the
tooling layer, which provides access to all the models and tools you need to build and scale
generative AI applications by using Amazon Bedrock.
For an introduction to generative AI, see What is Generative AI? on the AWS website.
The scope of this current guidance is exclusively around the generative AI capabilities
of Amazon Bedrock. Future updates will iteratively expand the scope and add guidance to
include the full array of AWS services for generative AI.
