Today we are announcing the preview launch of Prompt Optimization in Amazon Bedrock. Prompt Optimization rewrites prompts for higher quality responses from foundational models.
Prompt engineering is the process of designing prompts to guide foundational models to generating relevant responses. These prompts need to be tailored for each specific foundational model, following best practices and guidelines for each model. Developers can now use Prompt Optimization in Amazon Bedrock to rewrite their prompts for improved performance on Claude Sonnet 3.5, Claude Sonnet, Claude Opus, Claude Haiku, Llama 3 70B, Llama 3.1 70B, Mistral Large 2 and Titan Text Premier models. Developers can easily compare the performance of optimized prompts against the original prompts without the need of any deployment. All optimized prompts are saved as part of Prompt Builder for developers to use for their generative AI applications.
Amazon Bedrock Prompt Optimization is now available in preview. Learn more here.
Source:: Amazon AWS