AI product
Amazon Bedrock is a managed AWS service for building and running production generative AI workloads with hosted foundation models and APIs. It provides access to Amazon's and third-party models with managed infrastructure and tooling; customer data remains within the customer's VPC, prompts are not sent to model providers, and most inference traffic runs on AWS Trainium chips.
5 uses taken from transcripts — each links to the moment in the video.
Provides a cloud account route through which teams use Anthropic models and related inference infrastructure.
An external model and platform stack considered alongside other foundation-model options for enterprise solutions.
Default model provider running behind the Strands agent loop
AWS's managed AI model service. Garman says customer data never leaves the customer's VPC and prompts are never sent to model providers, which is why enterprises run production AI workloads on it; most Bedrock inference traffic runs on Trainium.
AWS inference/model service used to run Anthropic and OpenAI models for customers
5 in the library.