AWS connect medium security documentation change
Summary
Removed a line about routing criteria update limits and updated the link text for AI guardrails documentation. The AI guardrails section describes safeguards against harmful content, PII redaction, and LLM hallucination mitigation.
Security assessment
The AI guardrails update explicitly addresses security measures like filtering harmful responses, redacting sensitive information, and mitigating LLM hallucinations, which are security-related safeguards.
Diff
diff --git a/connect/latest/adminguide/doc-history.md b/connect/latest/adminguide/doc-history.md index cc6a7d8fd..11160af04 100644 --- a/connect/latest/adminguide/doc-history.md +++ b/connect/latest/adminguide/doc-history.md @@ -13 +12,0 @@ Change| Description| Date -Increased limit on number of routing criteria updates per queued contact| Previously, routing criteria could be updated only up to three times while a contact was in queue. You can now update the routing criteria on a queued contact an unlimited number of times. However, if you update the routing criteria more than 3 times on a queued contact, only the latest 3 updates will be stored on the contact record and used to calculate metrics such as Step Expired % and Step Contacts Queued. To learn more, see [RoutingCriteria](https://docs.aws.amazon.com/connect/latest/adminguide/ctr-data-model.html#ctr-RoutingCriteria) in the contact record documentation.| March 17, 2025 @@ -61 +60 @@ Amazon Connect Contact Lens automates agent performance evaluations using genera -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 more information, see [Create AI guardrails for Amazon Q in Connect](https://docs.aws.amazon.com/connect/latest/adminguide/create-ai-guardrails.html).| December 1, 2024 +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 more information, see [AI Guardrails for Amazon Q in Connect](https://docs.aws.amazon.com/connect/latest/adminguide/ai-guardrails-for-amazon-q-in-connect.html).| December 1, 2024