I’d like to send a huge thanks to our friends at AWS for their support of the podcast and their sponsorship of today's episode. Amazon Bedrock is a fully managed platform for building and scaling generative AI applications and is used by tens of thousands of AWS customers today. To help developers build genAI responsibly, AWS offers Amazon Bedrock Guardrails, which allow users to set up configurable safeguards for their applications using policies like filters, contextual grounding checks, and now, automated reasoning checks. This new feature uses automated reasoning to detect hallucinations and for the first time, provide mathematically verifiable proof that your model response is accurate. Automated reasoning checks let users enhance the reliability of their applications for use cases where accuracy is critical such as HR, finance, compliance, and more. Stay tuned to dig into the underlying science, or visit twimlai.com/awsarc to learn more.
