Building AI That Works: ESnet's Pragmatic Approach to AI-Driven Operational Excellence

• URL: http://arxiv.org/abs/2607.22948v1
• Date: Fri, 24 Jul 2026 23:20:59 GMT
• Title: Building AI That Works: ESnet's Pragmatic Approach to AI-Driven Operational Excellence
• Abstract summary: ORBIT is an agentic AI system integrated into ServiceNow, ESnet's primary incident management platform.<n>The design uses a modular, layered architecture comprising a centralized reasoning hub, access via MCPs for ESnet data sources, a semantic search layer, and an operator-facing chat interface.<n>Key results show that ORBIT successfully delivered all six initial tasks, and the architecture enabled rapid development of two additional tasks proposed by NOC engineers.
• Score: 0.909937273720124
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: The ORBIT (Operations Responses and Business Intelligence Toolkit) project was initiated to assess agentic AI for the upcoming ESnet 7 initiative and to address persistent operational pain points in the Network Operations Center (NOC) workflow. ESnet operators experience slow retrieval from siloed data sources, incidents described in lengthy and difficult-to-parse tickets, and context loss across shift handoffs. These challenges increase cognitive load and prolong incident resolution times. ORBIT therefore targets routine automation, cross-source synthesis, and actionable insights delivered directly within operators' existing tooling. ORBIT is an agentic AI system integrated into ServiceNow, ESnet's primary incident management platform. The design uses a modular, layered architecture comprising a centralized reasoning hub, tool access via MCPs for ESnet data sources, a semantic search layer, and an operator-facing chat interface. To manage the complexity and stochasticity of the AI toolchain, ORBIT follows industry best practices by structuring task logic as versioned, tested "skills" that guide the system in performing bounded responsibilities. This improves reliability and predictability compared to fully unconstrained agent behavior. Key results show that ORBIT successfully delivered all six initial tasks, and the architecture enabled rapid development of two additional tasks proposed by NOC engineers. We observed strong organic adoption of general-purpose infrastructure components, especially the chat interface and LiteLLM model gateway, including high request volumes from outside the project. Experiments with skills indicate that this approach can reduce task completion steps while eliminating observed error modes.

Related papers

• Autonomous Incident Resolution at Hyperscale: An Agentic AI Architecture for Network Operations [0.33842793760651557]
  This paper presents an agentic AI architecture for autonomous incident resolution in large-scale network operations.<n>Our system employs a multi-agent orchestration framework where specialized AI agents collaborate to detect, diagnose, and remediate network incidents without human intervention.
  arXiv  Detail & Related papers  (2026-06-08T07:15:53Z)
• Building Effective AI Coding Agents for the Terminal: Scaffolding, Harness, Context Engineering, and Lessons Learned [9.127884945730019]
  We present OPENDEV, an open-source, command-line coding agent engineered specifically for this new paradigm.<n>It overcomes these challenges through a compound AI system architecture with workload-specialized model routing.<n>It employs an automated memory system to accumulate project-specific knowledge across sessions and counteract instruction fade-out.
  arXiv  Detail & Related papers  (2026-03-05T16:21:08Z)
• Agentic Assistant for 6G: Turn-based Conversations for AI-RAN Hierarchical Co-Management [11.369638196554929]
  Co-management of RAN and edge AI is the gap, which creates hierarchical and dynamic problems that require turn-based human interactions.<n>Here, we create an agentic network manager and turn-based conversation assistant that can understand human intent-based queries.<n>These initial results indicate the universal challenges of hallucination but also fast response performance success.
  arXiv  Detail & Related papers  (2026-02-14T19:58:20Z)
• Towards 6G Native-AI Edge Networks: A Semantic-Aware and Agentic Intelligence Paradigm [85.7583231789615]
  6G positions intelligence as a native network capability, transforming the design of radio access networks (RANs)<n>Within this vision, Semantic-native communication and agentic intelligence are expected to play central roles.<n>Agentic intelligence endows distributed RAN entities with goal-driven autonomy, reasoning, planning, and multi-agent collaboration.
  arXiv  Detail & Related papers  (2025-12-04T03:09:33Z)
• AI-Enhanced Operator Assistance for UNICOS Applications [41.99844472131922]
  This project explores the development of an AI-enhanced operator assistant for UNICOS, CERN's UNified Industrial Control System.<n>Preliminary evaluations suggest that the system is capable of decoding widgets, performing root cause analysis, and tracing DPEs across a complex.
  arXiv  Detail & Related papers  (2025-09-16T03:43:54Z)
• A Survey on Cloud-Edge-Terminal Collaborative Intelligence in AIoT Networks [49.90474228895655]
  Cloud-edge-terminal collaborative intelligence (CETCI) is a fundamental paradigm within the artificial intelligence of things (AIoT) community.<n>CETCI has made significant progress with emerging AIoT applications, moving beyond isolated layer optimization to deployable collaborative intelligence systems.<n>This survey describes foundational architectures, enabling technologies, and scenarios of CETCI paradigms, offering a tutorial-style review for CISAIOT beginners.
  arXiv  Detail & Related papers  (2025-08-26T08:38:01Z)
• Agentic Web: Weaving the Next Web with AI Agents [109.13815627467514]
  The emergence of AI agents powered by large language models (LLMs) marks a pivotal shift toward the Agentic Web.<n>In this paradigm, agents interact directly with one another to plan, coordinate, and execute complex tasks on behalf of users.<n>We present a structured framework for understanding and building the Agentic Web.
  arXiv  Detail & Related papers  (2025-07-28T17:58:12Z)
• Towards a Playground to Democratize Experimentation and Benchmarking of AI Agents for Network Troubleshooting [48.131257144711576]
  We focus on the application of AI agents to network troubleshooting.<n>We elaborate on the need for a standardized, reproducible, and open benchmarking platform.
  arXiv  Detail & Related papers  (2025-07-01T08:46:37Z)
• AIOpsLab: A Holistic Framework to Evaluate AI Agents for Enabling Autonomous Clouds [12.464941027105306]
  AI for IT Operations (AIOps) aims to automate complex operational tasks, such as fault localization and root cause analysis, to reduce human workload and minimize customer impact.<n>Recent advances in Large Language Models (LLMs) and AI agents are revolutionizing AIOps by enabling end-to-end and multitask automation.<n>We present AIOPSLAB, a framework that deploys microservice cloud environments, injects faults, generates workloads, and exports telemetry data but also orchestrates these components and provides interfaces for interacting with and evaluating agents.
  arXiv  Detail & Related papers  (2025-01-12T04:17:39Z)
• SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering [79.07755560048388]
  SWE-agent is a system that facilitates LM agents to autonomously use computers to solve software engineering tasks. SWE-agent's custom agent-computer interface (ACI) significantly enhances an agent's ability to create and edit code files, navigate entire repositories, and execute tests and other programs. We evaluate SWE-agent on SWE-bench and HumanEvalFix, achieving state-of-the-art performance on both with a pass@1 rate of 12.5% and 87.7%, respectively.
  arXiv  Detail & Related papers  (2024-05-06T17:41:33Z)
• The Foundations of Computational Management: A Systematic Approach to Task Automation for the Integration of Artificial Intelligence into Existing Workflows [55.2480439325792]
  This article introduces Computational Management, a systematic approach to task automation. The article offers three easy step-by-step procedures to begin the process of implementing AI within a workflow.
  arXiv  Detail & Related papers  (2024-02-07T01:45:14Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.