Skip to main content

Agent runtimes

Managed runtimes, copilots and agent protocols. WonderFence enforces inline where the runtime allows it and audits out of band where it does not. WonderBuild red-teams any agent that speaks A2A.

Amazon Bedrock AgentCore

A Lambda subscribed to the AgentCore runtime log group. With message content capture on, ADOT writes every GenAI message as its own log record; a subscription filter forwards them, the Lambda rebuilds one evaluation unit per model call and sends the user prompt, tool arguments, tool results and model output to Alice. Verdicts land in CloudWatch and, optionally, as spans inside the agent trace. Nothing in the agent changes and nothing is blocked.

Amazon Bedrock

Turn on Bedrock model invocation logging, point it at S3 or CloudWatch, and let a Lambda forward each logged prompt and response to Alice. Findings, case management and user-level workflows such as a three-strikes rule then run in the Alice platform, next to any Amazon Bedrock Guardrails verdicts you already have. No change to the application; evaluation happens after the fact.

Microsoft Copilot Studio

Alice connects to Microsoft Copilot Studio as an Environment Security Provider (ESP), Microsoft's external threat-detection interface. Enabled once per Power Platform environment, it covers every agent in it Copilot Studio does not send them to security providers.

Microsoft Dynamics 365

Dynamics 365 Contact Center agents run on the same framework as custom Copilot Studio agents, so they connect the same way the security provider interface does not send them.

A2A (Agent2Agent)

WonderBuild red-teams any agent that speaks the Agent2Agent (A2A) protocol over its JSON-RPC binding: an agent built with Strands, Google ADK, LangGraph or CrewAI, or an A2A runtime on Amazon Bedrock AgentCore (Preview). A version needs only the agent's URL and a credential. There is no request payload or response path to write, because A2A defines the message format and how a conversation continues.