AWS connect high security documentation change
Summary
Updated AWS CLI examples for AI guardrail configuration, focusing on policy enforcement for blocked topics, content filtering, hallucination detection, and PII redaction
Security assessment
The changes demonstrate configuration of AI guardrails to block financial advice topics, filter insults, detect hallucinations, and redact credit card numbers. These are security controls preventing data leaks (PII redaction), inappropriate content, and unreliable AI outputs. The explicit 'BLOCK' action for credit card numbers and content filtering shows security intent.
Diff
diff --git a/connect/latest/adminguide/create-ai-guardrails.md b/connect/latest/adminguide/create-ai-guardrails.md index 847ebb9ec..f31cd82bf 100644 --- a//connect/latest/adminguide/create-ai-guardrails.md +++ b//connect/latest/adminguide/create-ai-guardrails.md @@ -115,0 +116,9 @@ Use the following sample AWS CLI command to block undesirable topics. + aws qconnect update-ai-guardrail + --cli-input-json { + "assistantId": "a0a81ecf-6df1-4f91-9513-3bdcb9497e32", + "aiGuardrailId": "9147c4ad-7870-46ba-b6c1-7671f6ca3d95", + "blockedInputMessaging": "Blocked input text by guardrail", + "blockedOutputsMessaging": "Blocked output text by guardrail", + "visibilityStatus": "PUBLISHED", + "topicPolicyConfig": { + "topicsConfig": [ @@ -117,17 +126,8 @@ Use the following sample AWS CLI command to block undesirable topics. - "assistantId": "a0a81ecf-6df1-4f91-9513-3bdcb9497e32", - "name": "test-ai-guardrail-2", - "description": "This is a test ai-guardrail", - "blockedInputMessaging": "Blocked input text by guardrail", - "blockedOutputsMessaging": "Blocked output text by guardrail", - "visibilityStatus": "PUBLISHED", - "topicPolicyConfig": { - "topicsConfig": [ - { - "name": "Financial Advice", - "definition": "Investment advice refers to financial inquiries, guidance, or recommendations with the goal of generating returns or achieving specific financial objectives.", - "examples": ["- Is investment in stocks better than index funds?", "Which stocks should I invest into?", "- Can you manage my personal finance?"], - "type": "DENY" - } - ] - } - } + "name": "Financial Advice", + "definition": "Investment advice refers to financial inquiries, guidance, or recommendations with the goal of generating returns or achieving specific financial objectives.", + "examples": ["- Is investment in stocks better than index funds?", "Which stocks should I invest into?", "- Can you manage my personal finance?"], + "type": "DENY" + } + ] + } + } @@ -139,0 +140,9 @@ Use the following sample AWS CLI command to filter harmful and inappropriate con + aws qconnect update-ai-guardrail + --cli-input-json { + "assistantId": "a0a81ecf-6df1-4f91-9513-3bdcb9497e32", + "aiGuardrailId": "9147c4ad-7870-46ba-b6c1-7671f6ca3d95", + "blockedInputMessaging": "Blocked input text by guardrail", + "blockedOutputsMessaging": "Blocked output text by guardrail", + "visibilityStatus": "PUBLISHED", + "contentPolicyConfig": { + "filtersConfig": [ @@ -141,16 +150,7 @@ Use the following sample AWS CLI command to filter harmful and inappropriate con - "assistantId": "a0a81ecf-6df1-4f91-9513-3bdcb9497e32", - "name": "test-ai-guardrail-2", - "description": "This is a test ai-guardrail", - "blockedInputMessaging": "Blocked input text by guardrail", - "blockedOutputsMessaging": "Blocked output text by guardrail", - "visibilityStatus": "PUBLISHED", - "contentPolicyConfig": { - "filtersConfig": [ - { - "inputStrength": "HIGH", - "outputStrength": "HIGH", - "type": "INSULTS" - } - ] - } - } + "inputStrength": "HIGH", + "outputStrength": "HIGH", + "type": "INSULTS" + } + ] + } + } @@ -162,0 +163,9 @@ Use the following sample AWS CLI command to filter harmful and inappropriate wor + aws qconnect update-ai-guardrail + --cli-input-json { + "assistantId": "a0a81ecf-6df1-4f91-9513-3bdcb9497e32", + "aiGuardrailId": "9147c4ad-7870-46ba-b6c1-7671f6ca3d95", + "blockedInputMessaging": "Blocked input text by guardrail", + "blockedOutputsMessaging": "Blocked output text by guardrail", + "visibilityStatus": "PUBLISHED", + "wordPolicyConfig": { + "wordsConfig": [ @@ -164,14 +173,5 @@ Use the following sample AWS CLI command to filter harmful and inappropriate wor - "assistantId": "a0a81ecf-6df1-4f91-9513-3bdcb9497e32", - "name": "test-ai-guardrail-2", - "description": "This is a test ai-guardrail", - "blockedInputMessaging": "Blocked input text by guardrail", - "blockedOutputsMessaging": "Blocked output text by guardrail", - "visibilityStatus": "PUBLISHED", - "wordPolicyConfig": { - "wordsConfig": [ - { - "text": "Nvidia", - }, - ] - } - } + "text": "Nvidia", + }, + ] + } + } @@ -183,0 +184,9 @@ Use the following sample AWS CLI command to detect hallucinations in the model r + aws qconnect update-ai-guardrail + --cli-input-json { + "assistantId": "a0a81ecf-6df1-4f91-9513-3bdcb9497e32", + "aiGuardrailId": "9147c4ad-7870-46ba-b6c1-7671f6ca3d95", + "blockedInputMessaging": "Blocked input text by guardrail", + "blockedOutputsMessaging": "Blocked output text by guardrail", + "visibilityStatus": "PUBLISHED", + "contextualGroundPolicyConfig": { + "filtersConfig": [ @@ -185,15 +194,6 @@ Use the following sample AWS CLI command to detect hallucinations in the model r - "assistantId": "a0a81ecf-6df1-4f91-9513-3bdcb9497e32", - "name": "test-ai-guardrail-2", - "description": "This is a test ai-guardrail", - "blockedInputMessaging": "Blocked input text by guardrail", - "blockedOutputsMessaging": "Blocked output text by guardrail", - "visibilityStatus": "PUBLISHED", - "contextualGroundPolicyConfig": { - "filtersConfig": [ - { - "type": "RELEVANCE", - "threshold": 0.50 - }, - ] - } - } + "type": "RELEVANCE", + "threshold": 0.50 + }, + ] + } + } @@ -205,0 +206,9 @@ Use the following sample AWS CLI command to redact sensitive information such as + aws qconnect update-ai-guardrail + --cli-input-json { + "assistantId": "a0a81ecf-6df1-4f91-9513-3bdcb9497e32", + "aiGuardrailId": "9147c4ad-7870-46ba-b6c1-7671f6ca3d95", + "blockedInputMessaging": "Blocked input text by guardrail", + "blockedOutputsMessaging": "Blocked output text by guardrail", + "visibilityStatus": "PUBLISHED", + "sensitiveInformationPolicyConfig": { + "piiEntitiesConfig": [ @@ -207,15 +216,6 @@ Use the following sample AWS CLI command to redact sensitive information such as - "assistantId": "a0a81ecf-6df1-4f91-9513-3bdcb9497e32", - "name": "test-ai-guardrail-2", - "description": "This is a test ai-guardrail", - "blockedInputMessaging": "Blocked input text by guardrail", - "blockedOutputsMessaging": "Blocked output text by guardrail", - "visibilityStatus": "PUBLISHED", - "sensitiveInformationPolicyConfig": { - "piiEntitiesConfig": [ - { - "type": "CREDIT_DEBIT_CARD_NUMBER", - "action":"BLOCK", - }, - ] - } - } + "type": "CREDIT_DEBIT_CARD_NUMBER", + "action":"BLOCK", + }, + ] + } + }