AWS bedrock-agentcore documentation change
Summary
Removed reference to built-in web search tool from the list of available tools
Security assessment
The change simply removes a feature reference ('web search') without mentioning security vulnerabilities, patching, or threats. No security context or implications are indicated in the change.
Diff
diff --git a/bedrock-agentcore/latest/devguide/harness.md b/bedrock-agentcore/latest/devguide/harness.md index 2267e07b1..a24558f6b 100644 --- a//bedrock-agentcore/latest/devguide/harness.md +++ b//bedrock-agentcore/latest/devguide/harness.md @@ -17 +17 @@ The managed agent harness in AgentCore turns that work into configuration. You d -Every harness session is stateful by default and runs in a secure, **isolated microVM per session** (backed by AgentCore runtime). The agent has its own **filesystem and shell** , so it can write code, execute it, and can persist **short-term and long-term memories** and files across sessions, even when the underlying microVM session has expired and is replaced by a new one. Agents can use **any model** provided by Amazon Bedrock, OpenAI, Google Gemini, or any LiteLLM-compatible provider, and can **switch providers mid-session** without losing context, so you can plan with one model and execute with another, or swap providers for a price-performance test without rebuilding the conversation. Agents can connect to tools through **[AgentCore gateway](https://docs.aws.amazon.com/bedrock-agentcore/latest/devguide/gateway.html), [MCP servers](https://modelcontextprotocol.io/), or use the built-in [browser](https://docs.aws.amazon.com/bedrock-agentcore/latest/devguide/browser-tool.html), [code interpreter](https://docs.aws.amazon.com/bedrock-agentcore/latest/devguide/code-interpreter-tool.html), or web search**. You can attach **AWS skills from Git, S3, or the curated AWS skills** catalog with a single toggle, so the agent picks up domain expertise on demand instead of improvising. When you need a custom environment with your own dependencies, you can **bring your own container.** You can also **mount S3 Files or EFS** to share data across sessions and harnesses with full S3 durability and history. **Every action is traced automatically** through AgentCore observability, with a unified view that surfaces what the agent did across every capability in one place, so you stop hopping between log groups to piece together what happened. +Every harness session is stateful by default and runs in a secure, **isolated microVM per session** (backed by AgentCore runtime). The agent has its own **filesystem and shell** , so it can write code, execute it, and can persist **short-term and long-term memories** and files across sessions, even when the underlying microVM session has expired and is replaced by a new one. Agents can use **any model** provided by Amazon Bedrock, OpenAI, Google Gemini, or any LiteLLM-compatible provider, and can **switch providers mid-session** without losing context, so you can plan with one model and execute with another, or swap providers for a price-performance test without rebuilding the conversation. Agents can connect to tools through **[AgentCore gateway](https://docs.aws.amazon.com/bedrock-agentcore/latest/devguide/gateway.html), [MCP servers](https://modelcontextprotocol.io/), or use the built-in [browser](https://docs.aws.amazon.com/bedrock-agentcore/latest/devguide/browser-tool.html) or [code interpreter](https://docs.aws.amazon.com/bedrock-agentcore/latest/devguide/code-interpreter-tool.html) **. You can attach **AWS skills from Git, S3, or the curated AWS skills** catalog with a single toggle, so the agent picks up domain expertise on demand instead of improvising. When you need a custom environment with your own dependencies, you can **bring your own container.** You can also **mount S3 Files or EFS** to share data across sessions and harnesses with full S3 durability and history. **Every action is traced automatically** through AgentCore observability, with a unified view that surfaces what the agent did across every capability in one place, so you stop hopping between log groups to piece together what happened.