This standard defines a unified observability framework that helps organizations to instrument, monitor, measure, and validate the operational behavior of Artificial Intelligence (AI) systems with the rigor required for production-grade reliability and safety. The standard defines observability requirements, terminology, telemetry models, and measurement frameworks for AI systems throughout their operational lifecycle. It applies to AI-native systems and hybrid systems that integrate AI capabilities into traditional software, cloud-native, distributed, edge, and cyber-physical environments. To support the development of safe, dependable, and accountable AI systems in critical operational environments, the standard covers • model observability, including accuracy, drift, hallucination rates, safety evaluation metrics, and performance indicators; • inference and serving observability and dependencies, including latency distribution, throughput, token usage, request failures, and service level indicators; • agent and workflow observability, including tool-call tracing, agentic workflow and planning transparency, memory utilization, and multi-agent execution; • data and retrieval-augmented generation observability, including retrieval quality, embedding performance, vector database behavior, and context utilization; and • observability of supporting platforms and infrastructure, including compute accelerators, memory, storage, networking, and orchestration components that directly affect AI system behavior, performance, reliability, or safety. This standard applies to AI systems deployed across cloud, on-premises, edge, and hybrid environments. It does not replace general-purpose software or infrastructure observability standards but specifies the AI-specific telemetry and measurements required from those layers.
- Standard Committee
- C/AISC - Artificial Intelligence Standards Committee
- Status
- Active PAR
- PAR Approval
- 2026-09-25
Working Group Details
- Society
- IEEE Computer Society
- Standard Committee
- C/AISC - Artificial Intelligence Standards Committee
- Working Group
-
AISO-WG - Artificial Intelligence Systems Observability Working Group
- IEEE Program Manager
- Christy Bahn
Contact Christy Bahn - Working Group Chair
- PRAMOD BN
Other Activities From This Working Group
Current projects that have been authorized by the IEEE SA Standards Board to develop a standard.
No Active Projects
Standards approved by the IEEE SA Standards Board that are within the 10-year lifecycle.
No Active Standards
These standards have been replaced with a revised version of the standard, or by a compilation of the original active standard and all its existing amendments, corrigenda, and errata.
No Superseded Standards
These standards have been removed from active status through a ballot where the standard is made inactive as a consensus decision of a balloting group.
No Inactive-Withdrawn Standards
These standards are removed from active status through an administrative process for standards that have not undergone a revision process within 10 years.
No Inactive-Reserved Standards