AWS bedrock: Bedrock doc history entries for AdvPO and guardrails tiers
Summary
Adds two documentation-history entries: Advanced Prompt Optimization prompt shortening and application inference profile support, and contextual grounding checks now supporting the Standard safeguard tier.
Security assessment
These are release-notes/history entries describing feature availability (prompt shortening, application inference profiles, guardrails safeguard tiers). They mention guardrails but only as a feature announcement, with no vulnerability, CVE, or security fix described.
Evidence
+[Contextual grounding checks support safeguard tiers](https://docs.aws.amazon.com/bedrock/latest/userguide/guardrails-contextual-grounding-check.html)| Amazon Bedrock Guardrails contextual grounding checks now support Standard tier. Standard tier supports responses that include reasoning or conversational content, returns more consistent scores, and supports additional languages. For more information, see [Use contextual grounding check to filter hallucinations in responses](https://docs.aws.amazon.com/bedrock/latest/userguide/guardrails-contextual-grounding-check.html) and [Safeguard tiers for guardrails policies](https://docs.aws.amazon.com/bedrock/latest/userguide/guardrails-tiers.html).| October 19, 2026
Diff
diff --git a/bedrock/latest/userguide/bedrock-ug-doc-history.md b/bedrock/latest/userguide/bedrock-ug-doc-history.md index 5413de8..40f8433 100644 --- a//bedrock/latest/userguide/bedrock-ug-doc-history.md +++ b//bedrock/latest/userguide/bedrock-ug-doc-history.md @@ -12,0 +13 @@ Change| Description| Date +[Advanced Prompt Optimization supports prompt shortening and application inference profiles](https://docs.aws.amazon.com/bedrock/latest/userguide/advanced-prompt-optimization-shorten.html)| You can enable prompt shortening per prompt template to reduce prompt length while maintaining or improving evaluation scores. Application inference profiles are accepted as target models and judge models. Results include median time to first token and average and median latency. For more information, see [Shorten prompts](https://docs.aws.amazon.com/bedrock/latest/userguide/advanced-prompt-optimization-shorten.html).| October 20, 2026 @@ -13,0 +15 @@ Change| Description| Date +[Contextual grounding checks support safeguard tiers](https://docs.aws.amazon.com/bedrock/latest/userguide/guardrails-contextual-grounding-check.html)| Amazon Bedrock Guardrails contextual grounding checks now support Standard tier. Standard tier supports responses that include reasoning or conversational content, returns more consistent scores, and supports additional languages. For more information, see [Use contextual grounding check to filter hallucinations in responses](https://docs.aws.amazon.com/bedrock/latest/userguide/guardrails-contextual-grounding-check.html) and [Safeguard tiers for guardrails policies](https://docs.aws.amazon.com/bedrock/latest/userguide/guardrails-tiers.html).| October 19, 2026