AWS announces the launch of natural language test Q&A generation for Automated Reasoning checks in Amazon Bedrock Guardrails. Automated Reasoning checks uses formal verification techniques to validate the accuracy and policy compliance of outputs from generative AI models. Automated Reasoning checks deliver up to 99% accuracy at detecting correct responses from LLMs, giving you provable assurance in detecting AI hallucinations while also assisting with ambiguity detection in model responses.
To get started with Automated Reasoning checks, customers create and test Automated Reasoning policies using natural language documents and sample Q&As. Automated Reasoning checks generates up to N test Q&As for each policy using content from the input document, reducing the work required to go from initial policy generation to production-ready, refined policy.
Test generation for Automated Reasoning checks is now available in the US (N. Virginia), US (Ohio), US (Oregon), Europe (Frankfurt), Europe (Ireland), and Europe (Paris) Regions. Customers can access the service through the Amazon Bedrock console, as well as the Amazon Bedrock Python SDK.
To learn more about Automated Reasoning checks and how you can integrate it into your generative AI workflows, please read the Amazon Bedrock documentation, review the tutorials on the AWS AI blog, and visit the Bedrock Guardrails webpage.
Categories: general:products/amazon-bedrock,marketing:marchitecture/internet-of-things
Source: Amazon Web Services
