Remove Prompt Engineering Remove Responsible AI Remove UX Design
article thumbnail

Reinvent personalization with generative AI on Amazon Bedrock using task decomposition for agentic workflows

AWS Machine Learning Blog

The personalized content is built using generative AI by following human guidance and provided sources of truth. The process employs techniques like RAG, prompt engineering with personas, and human-curated references to maintain output control. For this post, we use Anthropic’s Claude models on Amazon Bedrock.

article thumbnail

Accelerate video Q&A workflows using Amazon Bedrock Knowledge Bases, Amazon Transcribe, and thoughtful UX design

AWS Machine Learning Blog

By using a combination of transcript preprocessing, prompt engineering, and structured LLM output, we enable the user experience shown in the following screenshot, which demonstrates the conversion of LLM-generated timestamp citations into clickable buttons (shown underlined in red) that navigate to the correct portion of the source video.