In this session, we demonstrate the process of constructing a generative application utilizing Amazon Bedrock tailored to your organization. Utilizing Guardrails, we guide you in overseeing end-user experiences in alignment with application-specific requirements and responsible AI policies. This empowers you to consistently deliver secure user interactions in generative AI applications, regardless of the underlying foundation model (FM). Explore the newfound capability to define customized policies, manage user interactions with foundation models (FMs), and filter out disallowed topics and harmful content. Lastly, witness practical demonstrations illustrating the creation and application of tailored guardrails with FMs and Agents for Amazon Bedrock, facilitating the implementation of responsible AI policies in your generative AI applications.