Amazon Bedrock

Amazon Bedrock offers a way to build and scale generative AI applications with foundation models, providing a developer experience to work with a broad range of FMs from AI companies like AI21 Labs, Anthropic, Cohere, Meta, Stability AI, and Amazon.

A single API is used for inference regardless of the models chosen, offering the flexibility to use FMs from different providers and keep up to date with the latest model versions with minimal code changes. And users can privately customize FMs with an organization's own data through a visual interface without writing any code by simply selecting the training and validation data sets stored in Amazon Simple Storage Service (Amazon S3) and, if required, adjusting the hyperparameters to achieve the best possible model performance.

AI agents built on the platform can execute a variety of complex business tasks—from booking travel and processing insurance claims to creating ad campaigns, preparing tax filings, and managing inventory—by dynamically calling company systems and APIs. Fully managed agents for Amazon Bedrock extend the reasoning capabilities of FMs to break down tasks, create an orchestration plan, and execute it.

Since Amazon Bedrock is serverless, there is no infrastructure to manage, and it can be securely integrated with enterprise systems to deploy generative AI capabilities into applications using familiar AWS services.