The Observability Gap in Multi-Agent AI Systems

As AI agents become more widely deployed, take on more tasks and help complete work projects, increased interactions between them will lead to failures that are particular to multi-agent systems, far beyond those of deployments of single agents in isolation. Real-time monitoring is necessary to prevent these failures because pre-deployment testing, while necessary, is insufficient, and post-hoc auditing does not prevent high-stakes incidents. However, agent frameworks have significant gaps in capturing key telemetry signals for effective real-time monitoring. This paper presents a documentation-based assessment of these gaps and provides preliminary recommendations for addressing them.