AWS bedrock-agentcore documentation change
Summary
Updated documentation structure, corrected service names, added API reference links, and improved formatting consistency. Removed preview notice as the service is now generally available.
Security assessment
Changes focus on branding consistency (AgentCore Runtime), API documentation links, and formatting improvements. While security sections exist, the changes don't introduce new security content or address specific vulnerabilities. The credential management mention is a pre-existing security feature description with only naming standardization applied.
Diff
diff --git a/bedrock-agentcore/latest/devguide/runtime-how-it-works.md b/bedrock-agentcore/latest/devguide/runtime-how-it-works.md index 84c7da129..303a7cd55 100644 --- a//bedrock-agentcore/latest/devguide/runtime-how-it-works.md +++ b//bedrock-agentcore/latest/devguide/runtime-how-it-works.md @@ -7,2 +6,0 @@ Key componentsAuthentication and securityAdditional featuresImplementation overv -Amazon Bedrock AgentCore is in preview release and is subject to change. - @@ -12,0 +11,15 @@ The AgentCore Runtime handles scaling, session management, security isolation, a +###### Topics + + * Key components + + * Authentication and security + + * Additional features + + * Implementation overview + + * [Understanding the AgentCore Runtime service contract](./runtime-service-contract.html) + + + + @@ -15 +28 @@ The AgentCore Runtime handles scaling, session management, security isolation, a -### Agent runtime +### AgentCore Runtime @@ -19 +32 @@ An AgentCore Runtime is the foundational component that hosts your AI agent or t -You can build and deploy agents to AgentCore Runtime using the AgentCore Python SDK or directly through AWS SDKs. With the Python SDK, you can define your agent using popular frameworks like LangGraph, CrewAI, or Strands Agents. The SDK handles infrastructure complexities, allowing you to focus on the agent's logic and capabilities. +You can build and deploy agents to AgentCore Runtime using the AgentCore Python SDK or directly through AWS SDKs. With the AgentCore Python SDK, you can define your agent using popular frameworks like LangGraph, CrewAI, or Strands Agents. The SDK handles infrastructure complexities, allowing you to focus on the agent's logic and capabilities. @@ -21 +34 @@ You can build and deploy agents to AgentCore Runtime using the AgentCore Python -Each Agent Runtime: +Each AgentCore Runtime: @@ -34 +47 @@ Each AgentCore Runtime maintains immutable versions that capture a complete snap - * When you create an Agent Runtime, Version 1 (V1) is automatically created + * When you create an AgentCore Runtime, Version 1 (V1) is automatically created @@ -47 +60 @@ This versioning system provides reliable deployment history and rollback capabil -Endpoints provide addressable access points (i.e., aliases) to specific versions of your AgentCore Runtime. Each endpoint: +Endpoints provide addressable access points to specific versions of your AgentCore Runtime. Each endpoint: @@ -60 +73 @@ Key endpoint details: - * The "DEFAULT" endpoint is automatically created when you call `CreateAgentRuntime` and points to the latest version + * The "DEFAULT" endpoint is automatically created when you call [CreateAgentRuntime](https://docs.aws.amazon.com/bedrock-agentcore-control/latest/APIReference/API_CreateAgentRuntime.html) and points to the latest version @@ -62 +75 @@ Key endpoint details: - * When you update your Agent Runtime, a new version is created but the DEFAULT endpoint automatically updates to reference it + * When you update your AgentCore Runtime, a new version is created but the `DEFAULT` endpoint automatically updates to reference it @@ -64 +77 @@ Key endpoint details: - * Custom endpoints can be created via `CreateAgentRuntimeEndpoint` for different environments (dev, test, prod) + * You can create custom endpoints with the [CreateAgentRuntimeEndpoint](https://docs.aws.amazon.com/bedrock-agentcore-control/latest/APIReference/API_CreateAgentRuntimeEndpoint.html) operation for different environments (dev, test, prod) @@ -73 +86 @@ Endpoints have distinct lifecycle states: - * CREATING - Initial state during endpoint creation + * `CREATING` \- Initial state during endpoint creation @@ -75 +88 @@ Endpoints have distinct lifecycle states: - * CREATE_FAILED - Indicates creation failure due to permissions or other issues + * `CREATE_FAILED `\- Indicates creation failure due to permissions or other issues @@ -77 +90 @@ Endpoints have distinct lifecycle states: - * READY - Endpoint is operational and accepting requests + * `READY` \- Endpoint is operational and accepting requests @@ -79 +92 @@ Endpoints have distinct lifecycle states: - * UPDATING - Endpoint is being modified to reference a new version + * `UPDATING` \- Endpoint is being modified to reference a new version @@ -81 +94 @@ Endpoints have distinct lifecycle states: - * UPDATE_FAILED - Indicates update operation failure + * `UPDATE_FAILED` \- Indicates update operation failure @@ -122 +135 @@ Important session characteristics: - * Session state is ephemeral and should not be used for long-term durability (use Amazon Bedrock AgentCore Memory for context durability) + * Session state is ephemeral and should not be used for long-term durability (use AgentCore Memory for context durability) @@ -133 +146 @@ This complete isolation between sessions is crucial for enterprise security, par -Inbound Auth, powered by Amazon Bedrock AgentCore Identity, controls who can access and invoke your agents or tools in AgentCore Runtime: +Inbound Auth, powered by AgentCore Identity, controls who can access and invoke your agents or tools in AgentCore Runtime. @@ -196 +209 @@ Outbound Auth, powered by Amazon Bedrock AgentCore Identity, lets your agents ho - * Enterprise systems (Slack, Zoom, GitHub, etc.) + * Enterprise systems such as Slack, Zoom, and GitHub) @@ -205 +218 @@ Outbound Auth, powered by Amazon Bedrock AgentCore Identity, lets your agents ho -Amazon Bedrock AgentCore Identity manages these credentials securely, preventing credential exposure in your agent code or logs. +AgentCore Identity manages these credentials securely, preventing credential exposure in your agent code or logs. @@ -267 +280 @@ Here's how to get started with the AgentCore Runtime: - * Call the `InvokeAgentRuntime` operation with your agent's ARN and session ID + * Call the [InvokeAgentRuntime](https://docs.aws.amazon.com/bedrock-agentcore/latest/APIReference/API_InvokeAgentRuntime.html) operation with your agent's ARN and session ID