The corpus covers most of these one at a time: the multimodal ones, code generation, and the cases where a managed AI service wins. This card is the whole list on one page, because a scenario usually names the use case and expects you to know the service without any further clue.
Flash card
The GenAI use cases the guide names by name (image, video, and audio generation; summarization; AI assistants; translation; code generation; customer service agents; search; recommendation engines), and where each one lands on AWS.
- Image, video, and audio generation run on Amazon Bedrock model families including Amazon Nova. Image generation is diffusion underneath, not a language model predicting the next token.
- Summarization is a generative task a foundation model does well out of the box. Translation is too, though Amazon Translate is cheaper and steadier when all you need is one language turned into another.
- AI assistants and customer service agents are Amazon Bedrock when you build the conversation yourself and Amazon Quick when you want a managed front end over your own data. Amazon Lex is still the fit for a bot answering a fixed set of defined intents.
- Code generation is Kiro for a developer working in an IDE. When the generating happens inside your own application, it is a code-capable model called directly on Bedrock.
- {“Search here means retrieval. Embeddings in a vector store find the passages and the model writes an answer over what came back. Recommendation engines are different again”=>”Amazon Personalize, trained on behavioural data, not a foundation model handed a browsing history.”}
Pick it when
Pick a generative model when the output is new content (prose, an image, audio, working code), or an open-ended conversation with no script to follow.
It's the wrong answer when
It is the wrong answer when a purpose-built service covers the task more cheaply and more consistently. Sentiment and entity extraction belong to Amazon Comprehend, transcription to Amazon Transcribe, straight translation to Amazon Translate, and ranked recommendations to Amazon Personalize.