AWS Security ChangesHomeSearch

AWS bedrock-agentcore documentation change

Service: bedrock-agentcore · 2026-04-10 · Documentation low

File: bedrock-agentcore/latest/devguide/policy-natural-language.md

Summary

Updated typographical formatting by changing straight quotes to curly quotes and standardizing ellipsis characters throughout the document

Security assessment

The changes are purely typographical and formatting updates (straight quotes to curly quotes, ellipsis character changes). No security-related content was added, removed, or modified. The security implications section about data remaining in the region of origin and encrypted transmission remains unchanged.

Diff

diff --git a/bedrock-agentcore/latest/devguide/policy-natural-language.md b/bedrock-agentcore/latest/devguide/policy-natural-language.md
index 9d11fb4ee..f1dc707b1 100644
--- a//bedrock-agentcore/latest/devguide/policy-natural-language.md
+++ b//bedrock-agentcore/latest/devguide/policy-natural-language.md
@@ -9 +9 @@ OverviewExamplePolicy effectsAuthorization semanticsPolicy elementsPolicy exampl
-Policy in AgentCore will automatically select the optimal region within your geography to process your inference requests made through Policy authoring service. This maximizes available compute resources, model availability, and delivers the best customer experience. Your data will remain stored only in the region where the request originated, however, input prompts and output results may be processed outside that region. All data will be transmitted encrypted across Amazon's secure network.
+Policy in AgentCore will automatically select the optimal region within your geography to process your inference requests made through Policy authoring service. This maximizes available compute resources, model availability, and delivers the best customer experience. Your data will remain stored only in the region where the request originated, however, input prompts and output results may be processed outside that region. All data will be transmitted encrypted across Amazon’s secure network.
@@ -132 +131 @@ Understanding how Cedar evaluates policies is crucial for writing effective auth
-  * **By default, everything is denied** \- If no policy explicitly permits an action, it's automatically blocked
+  * **By default, everything is denied** \- If no policy explicitly permits an action, it’s automatically blocked
@@ -211 +209 @@ Flexible expressions:
-  * "Allow the user refund-agent to..."
+  * "Allow the user refund-agent to…​"
@@ -213 +211 @@ Flexible expressions:
-  * "Permit users with username refund-agent to..."
+  * "Permit users with username refund-agent to…​"
@@ -215 +213 @@ Flexible expressions:
-  * "Users with role insurance-agent may..."
+  * "Users with role insurance-agent may…​"
@@ -217 +215 @@ Flexible expressions:
-  * "Anyone with the refund:write scope is authorized to..."
+  * "Anyone with the refund:write scope is authorized to…​"
@@ -219 +217 @@ Flexible expressions:
-  * "All users can..."
+  * "All users can…​"
@@ -259 +257 @@ Flexible conditional expressions:
-  * "...when the amount is less than $500"
+  * "…​when the amount is less than $500"
@@ -261 +259 @@ Flexible conditional expressions:
-  * "...if the region is US, CA, or UK"
+  * "…​if the region is US, CA, or UK"
@@ -263 +261 @@ Flexible conditional expressions:
-  * "...only when approval status is approved-by-manager"
+  * "…​only when approval status is approved-by-manager"
@@ -265 +263 @@ Flexible conditional expressions:
-  * "...provided that the risk score has been submitted"
+  * "…​provided that the risk score has been submitted"
@@ -355 +353 @@ Elements:
-Conditions are where policies often become ambiguous. Here's how to write clear, testable conditions.
+Conditions are where policies often become ambiguous. Here’s how to write clear, testable conditions.