Skip to main content

Generative AI

Building and using generative AI on AWS, at three levels of abstraction.

ServiceLevelChoose whenKey distinction
Amazon QReady-to-use assistantChat/coding help with no buildFully managed AI assistant
Amazon BedrockFoundation-model APIBuild gen-AI apps on hosted FMsOne API to many models; fine-tune, RAG
Amazon SageMaker JumpStartModel hub in Amazon SageMaker AIDeploy/fine-tune models yourselfYou own the model and infrastructure
  • Abstraction ladder: use an assistant (Q) → call models via API (Bedrock) → run models yourself (JumpStart).

Linked from