AWS bedrock-agentcore documentation change
Summary
Removed command execution comparison table and updated section titles to reflect new shell terminology
Security assessment
Content reorganization without security impact. Removed feature comparison doesn't relate to vulnerabilities or security features.
Diff
diff --git a/bedrock-agentcore/latest/devguide/runtime-execute-command.md b/bedrock-agentcore/latest/devguide/runtime-execute-command.md index acd52781f..8b0036b8b 100644 --- a//bedrock-agentcore/latest/devguide/runtime-execute-command.md +++ b//bedrock-agentcore/latest/devguide/runtime-execute-command.md @@ -7 +7 @@ -When to use InvokeAgentRuntimeCommandHow it worksPrerequisitesExecute a commandCoding agent workflow exampleCommon use casesKey design choicesSecurity considerationsError handlingBest practices +How it worksPrerequisitesExecute a commandCoding agent workflow exampleCommon use casesKey design choicesSecurity considerationsError handlingBest practices @@ -15,10 +14,0 @@ To call `InvokeAgentRuntimeCommand` , you need `bedrock-agentcore:InvokeAgentRun -## When to use InvokeAgentRuntimeCommand - -Use InvokeAgentRuntimeCommand | Use InvokeAgentRuntime ----|--- -The operation has a known command ( `npm test` , `git push` ) | The operation requires reasoning ("analyze this code and fix the bug") -You want deterministic execution - same command, same result | You want the LLM to decide what to do -You need streaming output from a long-running process | You need the agent to use tools in a loop -The operation is a validation gate in your workflow | The operation is the creative or analytical work -You’re bootstrapping the environment before the agent starts | You’re asking the agent to work on a task - @@ -444 +434 @@ To use the Amazon Web Services Documentation, Javascript must be enabled. Please -Invoke an agent +Shell execution @@ -446 +436 @@ Invoke an agent -Observe agents +Interactive Shells (Terminals)