AWS bedrock-agentcore documentation change
Summary
Updated documentation to consistently use 'AgentCore' branding and clarify session isolation mechanisms. Added explicit references to security properties like microVM termination, memory sanitization, and prevention of credential sharing between sessions.
Security assessment
The changes emphasize existing security controls (microVM isolation, memory sanitization, credential separation) but do not indicate remediation of a specific vulnerability. The edits primarily improve clarity of pre-existing security features rather than addressing a newly discovered issue.
Diff
diff --git a/bedrock-agentcore/latest/devguide/runtime-sessions.md b/bedrock-agentcore/latest/devguide/runtime-sessions.md index f0b17ac76..97a8269c4 100644 --- a//bedrock-agentcore/latest/devguide/runtime-sessions.md +++ b//bedrock-agentcore/latest/devguide/runtime-sessions.md @@ -5,3 +5 @@ -Understanding ephemeral contextExtended conversations and multi-step workflowsRuntime session lifecycleHow to use sessions - -Amazon Bedrock AgentCore is in preview release and is subject to change. +Understanding ephemeral contextExtended conversations and multi-step workflowsAgentCore Runtime session lifecycleHow to use sessions @@ -11 +9 @@ Amazon Bedrock AgentCore is in preview release and is subject to change. -AgentCore Runtime lets you isolate each user session and safely reuse context across multiple invocations in a user session. Session isolation is critical for AI agent workloads due to their unique operational characteristics: +Amazon Bedrock AgentCore Runtime lets you isolate each user session and safely reuse context across multiple invocations in a user session. Session isolation is critical for AI agent workloads due to their unique operational characteristics: @@ -13 +11 @@ AgentCore Runtime lets you isolate each user session and safely reuse context ac - * **Complete execution environment separation** : Each user session in Runtime receives its own dedicated microVM with isolated Compute, memory, and filesystem resources. This prevents one user's agent from accessing another user's data. After session completion, the entire microVM is terminated and memory is sanitized to remove all session data, eliminating cross-session contamination risks. + * **Complete execution environment separation** : Each user session in AgentCore Runtime receives its own dedicated microVM with isolated Compute, memory, and filesystem resources. This prevents one user's agent from accessing another user's data. After session completion, the entire microVM is terminated and memory is sanitized to remove all session data, eliminating cross-session contamination risks. @@ -15 +13 @@ AgentCore Runtime lets you isolate each user session and safely reuse context ac - * **Stateful reasoning processes** : Unlike stateless functions, AI agents maintain complex contextual state throughout their execution cycle, beyond simple message history for multi-turn conversations. Runtime preserves this state securely within a session while ensuring complete isolation between different users, enabling personalized agent experiences without compromising data boundaries. + * **Stateful reasoning processes** : Unlike stateless functions, AI agents maintain complex contextual state throughout their execution cycle, beyond simple message history for multi-turn conversations. AgentCore Runtime preserves this state securely within a session while ensuring complete isolation between different users, enabling personalized agent experiences without compromising data boundaries. @@ -17 +15 @@ AgentCore Runtime lets you isolate each user session and safely reuse context ac - * **Privileged tool operations** : AI agents perform privileged operations on users' behalf through integrated tools accessing various resources. Runtime's isolation model ensures these tool operations maintain proper security contexts and prevents credential sharing or permission escalation between different user sessions. + * **Privileged tool operations** : AI agents perform privileged operations on users' behalf through integrated tools accessing various resources. AgentCore Runtime's isolation model ensures these tool operations maintain proper security contexts and prevents credential sharing or permission escalation between different user sessions. @@ -19 +17 @@ AgentCore Runtime lets you isolate each user session and safely reuse context ac - * **Deterministic security for non-deterministic processes** : AI agent behavior can be non-deterministic due to the probabilistic nature of foundation models. Runtime provides consistent, deterministic isolation boundaries regardless of agent execution patterns, delivering the predictable security properties required for enterprise deployments. + * **Deterministic security for non-deterministic processes** : AI agent behavior can be non-deterministic due to the probabilistic nature of foundation models. AgentCore Runtime provides consistent, deterministic isolation boundaries regardless of agent execution patterns, delivering the predictable security properties required for enterprise deployments. @@ -26 +24 @@ AgentCore Runtime lets you isolate each user session and safely reuse context ac -While Amazon Bedrock AgentCore provides strong session isolation, these sessions are ephemeral in nature. Any data stored in memory or written to disk persists only for the session duration. This includes conversation history, user preferences, intermediate calculation results, and any other state information your agent maintains. +While AgentCore provides strong session isolation, these sessions are ephemeral in nature. Any data stored in memory or written to disk persists only for the session duration. This includes conversation history, user preferences, intermediate calculation results, and any other state information your agent maintains. @@ -28 +26 @@ While Amazon Bedrock AgentCore provides strong session isolation, these sessions -For data that needs to be retained beyond the session lifetime (such as user conversation history, learned preferences, or important insights), you should use Amazon Bedrock AgentCore Memory. This service provides purpose-built persistent storage designed specifically for agent workloads, with both short-term and long-term memory capabilities. +For data that needs to be retained beyond the session lifetime (such as user conversation history, learned preferences, or important insights), you should use AgentCore Memory. This service provides purpose-built persistent storage designed specifically for agent workloads, with both short-term and long-term memory capabilities. @@ -32 +30 @@ For data that needs to be retained beyond the session lifetime (such as user con -Unlike traditional serverless functions that terminate after each request, Amazon Bedrock AgentCore supports ephemeral, isolated compute sessions lasting up to 8 hours. This simplifies building multi-step agentic workflows as you can make multiple calls to the same environment, with each invocation building upon the context established by previous interactions. +Unlike traditional serverless functions that terminate after each request, AgentCore supports ephemeral, isolated compute sessions lasting up to 8 hours. This simplifies building multi-step agentic workflows as you can make multiple calls to the same environment, with each invocation building upon the context established by previous interactions. @@ -34 +32 @@ Unlike traditional serverless functions that terminate after each request, Amazo -## Runtime session lifecycle +## AgentCore Runtime session lifecycle @@ -38 +36 @@ Unlike traditional serverless functions that terminate after each request, Amazo -A new session is created on the first invoke with a unique runtimeSessionId provided by your application. Amazon Bedrock AgentCore Runtime provisions a dedicated execution environment (microVM) for each session. Context is preserved between invocations to the same session. +A new session is created on the first invoke with a unique runtimeSessionId provided by your application. AgentCore Runtime provisions a dedicated execution environment (microVM) for each session. Context is preserved between invocations to the same session.