AWS bedrock-agentcore documentation change
Summary
Restructured the document by adding a topics section, moving IAM permissions content, and changing heading styles from markdown headers to bold text for step numbers.
Security assessment
Changes are organizational and stylistic, improving document navigation and readability. No security-related content, vulnerabilities, or security features were added, removed, or modified.
Diff
diff --git a/bedrock-agentcore/latest/devguide/code-interpreter-resource-session-management.md b/bedrock-agentcore/latest/devguide/code-interpreter-resource-session-management.md index 0a37e2d43..22aa45413 100644 --- a//bedrock-agentcore/latest/devguide/code-interpreter-resource-session-management.md +++ b//bedrock-agentcore/latest/devguide/code-interpreter-resource-session-management.md @@ -11 +11 @@ The following topics show how the Amazon Bedrock AgentCore Code Interpreter work -## IAM permissions +###### Topics @@ -13 +13,5 @@ The following topics show how the Amazon Bedrock AgentCore Code Interpreter work -The following IAM policy provides the necessary permissions for using the AgentCore Code Interpreter: + * IAM permissions + + * How it works + + * Creating a Code Interpreter and starting a session @@ -15 +19 @@ The following IAM policy provides the necessary permissions for using the AgentC -JSON + * [Resource management](./code-interpreter-resource-management.html) @@ -16,0 +21 @@ JSON + * [Session management](./code-interpreter-session-characteristics.html) @@ -18 +22,0 @@ JSON -**** @@ -21,0 +26,5 @@ JSON +## IAM permissions + +The following IAM policy provides the necessary permissions for using the AgentCore Code Interpreter: + + @@ -47,6 +53,0 @@ You should also add the following trust policy to the execution role: -JSON - - -**** - - @@ -77 +77 @@ JSON - 1. ###### Create a Code Interpreter + 1. **Create a Code Interpreter** @@ -81 +81 @@ Build your own Code Interpreter or use the System Code Interpreter to enable cap - 2. ###### Integrate it within an agent to invoke + 2. **Integrate it within an agent to invoke** @@ -85 +85 @@ Copy the built-in tool resource ID into your runtime agent code to invoke it as - 3. ###### Assess performance using observability + 3. **Assess performance using observability** @@ -94 +94 @@ Monitor key metrics for each tool in CloudWatch to get real-time performance ins - 1. ###### Create a Code Interpreter + 1. **Create a Code Interpreter** @@ -98 +98 @@ When configuring a Code Interpreter, you can choose network settings (Sandbox or - 2. ###### Start a session + 2. **Start a session** @@ -102 +102 @@ The Code Interpreter uses a session-based model. After creating a Code Interpret - 3. ###### Execute code + 3. **Execute code** @@ -106 +106 @@ Within an active session, you can execute code in supported languages (Python, J - 4. ###### Stop session and clean up + 4. **Stop session and clean up** @@ -108 +108 @@ Within an active session, you can execute code in supported languages (Python, J -When you're finished using a session, you should stop it to release resources and avoid unnecessary charges. You can also delete the Code Interpreter if you no longer intend to use it. +When you’re finished using a session, you should stop it to release resources and avoid unnecessary charges. You can also delete the Code Interpreter if you no longer intend to use it.