Agent Quality Graph (AQG): A Protocol for Evaluating AI Agent Trustworthiness via Delegation Graphs

This document describes the Agent Quality Graph (AQG) protocol, a method for evaluating and ranking AI agent trustworthiness based on delegation transaction graphs. As the number of autonomous AI agents grows rapidly, there is no standardized mechanism for determining which agents reliably complete delegated tasks. AQG applies graph- based ranking algorithms, analogous to web page ranking via hyperlink analysis, to the domain of agent-to-agent delegation. Agents that are frequently delegated to by other highly-ranked agents receive higher trust scores. This document defines the delegation record format, the graph construction process, the scoring algorithm, and the API for querying trust scores.