AWS bedrock-agentcore documentation change
Summary
Updated formatting and added clarifications to the on-demand evaluation guide, including a note about running from an AgentCore project directory and renumbering steps in the interactive section.
Security assessment
The changes are purely documentation formatting and clarifications about command usage and workflow steps. There is no mention of security vulnerabilities, patches, or security features. The note about the `--agent-arn` flag is a usage clarification, not a security feature.
Diff
diff --git a/bedrock-agentcore/latest/devguide/getting-started-on-demand.md b/bedrock-agentcore/latest/devguide/getting-started-on-demand.md index fded2a36f..0ca075703 100644 --- a//bedrock-agentcore/latest/devguide/getting-started-on-demand.md +++ b//bedrock-agentcore/latest/devguide/getting-started-on-demand.md @@ -142 +142 @@ The following code samples demonstrate how to run on-demand evaluations using di -AgentCore CLI +###### Example @@ -143,0 +144 @@ AgentCore CLI +AgentCore CLI @@ -146 +147 @@ AgentCore CLI - # Runs evaluation for the specified runtime and session. + 1. # Runs evaluation for the specified runtime and session. @@ -162,0 +164,9 @@ AgentCore CLI +Results are saved locally and can be reviewed later with `agentcore evals history` . In interactive mode, the CLI automatically discovers recent sessions from CloudWatch — you don’t need to know session IDs in advance. + +###### Note + +Run this from inside an AgentCore project directory (created with `agentcore create` ). The `--agent-arn` flag can be used outside a project directory. + + + + @@ -166 +176 @@ Interactive -Run `agentcore` to open the TUI, then select **run** and choose **On-demand Evaluation** : + 1. Run `agentcore` to open the TUI, then select **run** and choose **On-demand Evaluation** : @@ -168 +178 @@ Run `agentcore` to open the TUI, then select **run** and choose **On-demand Eval - 1. Select evaluators to run against agent traces: + 2. Select evaluators to run against agent traces: @@ -172 +182 @@ Run `agentcore` to open the TUI, then select **run** and choose **On-demand Eval - 2. Review the configuration and press Enter to confirm: + 3. Review the configuration and press Enter to confirm: @@ -182,2 +192 @@ AgentCore SDK - - from bedrock_agentcore_starter_toolkit import Evaluation + 1. from bedrock_agentcore_starter_toolkit import Evaluation @@ -348,2 +359,0 @@ To evaluate a specific trace or tool within a session, you can specify the targe -The `evaluationTarget` parameter you specify depends on the evaluator level: -