Amazon Connect launches AI guardrails for Amazon Q in Connect

Amazon Q in Connect, a generative AI powered assistant for customer service, now enables customers to natively configure AI guardrails to implement safeguards based on their use cases and responsible AI policies. Contact center administrators can configure company-specific guardrails for Amazon Q in Connect to filter harmful and inappropriate responses, redact sensitive personal information, and limit incorrect information in the responses due to potential large language model (LLM) hallucination.

For end-customer self-service scenarios, guardrails can be used to ensure Amazon Q in Connect responses are constrained to only company-related topics and maintain professional communication standards. Additionally, when agents leverage Amazon Q in Connect to help solve customer issues, these guardrails can prevent accidental exposure of personally identifiable information (PII) to agents. Contact center administrators will have the flexibility to configure these guardrails and selectively apply them to different contact types.

For region availability, please see the availability of Amazon Connect features by Region. To learn more about Amazon Q in Connect, please visit the website or see the help documentation.