←Search results

Search “Agents”

By relevance · Total 6704 results Clear search

Saturday

Friday

  6. AWS Machine Learning

    Building Multi-Account AI Agents with AgentCore Gateway and MCP

    AWS explains how to build multi-account AI agents using Amazon Bedrock AgentCore Gateway and MCP: the platform account runs agents through AgentCore Runtime and performs LLM inference via Amazon Bedrock, while each line-of-business account packages its data and tools as MCP servers, with the Gateway serving as a single MCP endpoint for unified tool discovery and invocation. The solution also combines AgentCore Identity with Okta for OAuth 2.0 M2M authentication, and uses Policy in AgentCore (Cedar) to achieve fine-grained authorization.

    AWS explains how to build multi-account AI agents using Amazon Bedrock AgentCore Gateway and MCP: the platform account runs agents through AgentCore Runtime and performs LLM inference via Amazon Bedrock, while each line-of-business account packages its data and tools as MCP servers, with the Gateway serving as a single MCP endpoint for unified tool discovery and invocation. The solution also combines AgentCore Identity with Okta for OAuth 2.0 M2M authentication, and uses Policy in AgentCore (Ced

    Matched fieldsTitle、Summary、Body

    #lab#Tutorials / practice#Agents#English text is being prepared.

Thursday

  1. Cato AI Labs

    How to secure the actual behavior of Bedrock AgentCore agents

    Cato AI Labs points out that Amazon Bedrock AgentCore's native access controls cannot prevent prompt injection; content exchanged between agents and models must be inspected at four stages: prompts, tool calls, tool responses, and outputs. AgentCore Policy uses Cedar rules to intercept tool calls that go through the Gateway, but tools that developers write directly into code do not pass through the Gateway and are therefore not inspected. Cato's Amazon Bedrock integration discovers all agents on AgentCore in a read-only manner and covers agents on AWS, Microsoft Foundry, Amazon Quick, and developer-built endpoints.

    Cato AI Labs points out that Amazon Bedrock AgentCore's native access controls cannot prevent prompt injection; content exchanged between agents and models must be inspected at four stages: prompts, tool calls, tool responses, and outputs. AgentCore Policy uses Cedar rules to intercept tool calls that go through the Gateway, but tools that developers write directly into code do not pass through the Gateway and are therefore not inspected. Cato's Amazon Bedrock integration discovers all agents on

    Matched fieldsTitle、Summary、Body

    #research#Safety / alignment#Agents#English text is being prepared.

Wednesday

  7. AWS Machine Learning

    Evaluating Agents Equipped with Skills Using Strands Evals and Amazon Bedrock AgentCore

    The Strands Evals SDK and Amazon Bedrock AgentCore Evaluations add three new skill-oriented evaluators: Skill Selection Accuracy returns a binary result for each invoked skill, Skill Instruction Following gives a five-level rating for each prescribed step, and Strands Evals also provides a deterministic Skill Invoked check. These evaluators can run on trajectories recorded by Strands Evals or on OpenTelemetry traces, and are used to pinpoint two types of failures: selecting the wrong skill and incompletely executing instructions; all are operated through the AgentCore CLI.

    The Strands Evals SDK and Amazon Bedrock AgentCore Evaluations add three new skill-oriented evaluators: Skill Selection Accuracy returns a binary result for each invoked skill, Skill Instruction Following gives a five-level rating for each prescribed step, and Strands Evals also provides a deterministic Skill Invoked check. These evaluators can run on trajectories recorded by Strands Evals or on OpenTelemetry traces, and are used to pinpoint two types of failures: selecting the wrong skill and i

    Matched fieldsTitle、Summary、Body

    #lab#Tutorials / practice#Agents#Evaluations / benchmarks

Tuesday