AWS bedrock-agentcore documentation change
Summary
Added description of Harness managed agent loop service with its features and integrations
Security assessment
Change describes a new service feature (Harness) without any security-specific content or vulnerability references. Pure feature documentation update.
Diff
diff --git a/bedrock-agentcore/latest/devguide/what-is-bedrock-agentcore.md b/bedrock-agentcore/latest/devguide/what-is-bedrock-agentcore.md index 49666aca8..12d14dbfa 100644 --- a//bedrock-agentcore/latest/devguide/what-is-bedrock-agentcore.md +++ b//bedrock-agentcore/latest/devguide/what-is-bedrock-agentcore.md @@ -23,0 +24 @@ Service | Description | Integrations +[Harness](./harness.html) | A managed agent loop that lets you define and invoke AI agents with a single API call. Specify a model, system prompt, and tools inline — Harness handles orchestration, tool execution, memory management, and response generation. Each session runs in an isolated microVM with filesystem and shell access, supporting use cases like code generation, data analysis, and deep research. Bring your own container image for custom environments with additional dependencies. | AgentCore Harness works with Amazon Bedrock, OpenAI, Google Gemini, and any OpenAI-compatible model provider. Integrates with AgentCore Memory, Gateway, Browser, Code Interpreter, and Observability. Supports remote MCP servers, inline functions, and custom container environments.