Governance-Aware Agent Telemetry for Closed-Loop Enforcement in Multi-Agent AI Systems

TL;DR

This paper introduces GAAT, a framework that enhances multi-agent AI system observability with real-time policy enforcement capabilities, addressing the gap between telemetry collection and enforcement.

Contribution

GAAT provides a comprehensive architecture integrating telemetry, real-time policy enforcement, graduated interventions, and cryptographic provenance for multi-agent systems.

Findings

GAAT detects policy violations under 200 ms latency.

GAAT extends OpenTelemetry with governance attributes.

GAAT enables real-time enforcement with graduated interventions.

Abstract

Enterprise multi-agent AI systems produce thousands of inter-agent interactions per hour, yet existing observability tools capture these dependencies without enforcing anything. OpenTelemetry and Langfuse collect telemetry but treat governance as a downstream analytics concern, not a real-time enforcement target. The result is an "observe-but-do-not-act" gap where policy violations are detected only after damage is done. We present Governance-Aware Agent Telemetry (GAAT), a reference architecture that closes the loop between telemetry collection and automated policy enforcement for multi-agent systems. GAAT introduces (1) a Governance Telemetry Schema (GTS) extending OpenTelemetry with governance attributes; (2) a real-time policy violation detection engine using OPA-compatible declarative rules under sub-200 ms latency; (3) a Governance Enforcement Bus (GEB) with graduated interventions; and (4) a Trusted Telemetry Plane with cryptographic provenance.