A contract-bounded runtime architecture, a source-preserving data substrate, and a falsifiable measurement protocol are contributed, which proposes a cluster-period randomized crossover experiment with a four-state verdict: supported, falsified, conditional-engineering, or inconclusive.
Abstract
Enterprise AI deployment is a coordination problem across business units, application and AI teams, testing, platform engineering, infrastructure, security, operations, and data governance. Use-case benchmarks show whether one agent completes one task, but not how changing capabilities, models, runtime mechanisms, capacity, and enterprise data should be owned, changed, admitted, or evidenced together. We present four responsibility objects as shared organizational contracts: Skill (reusable, versioned capability and workflow asset), Harness (runtime compiler and governor), Scaffold (execution/control boundary and NFR owner), and a stack-external data substrate under independent CIO-governed semantics and telemetry. The runtime core is A =, with the data substrate outside that stack. The central contribution is one bounded, falsifiable hypothesis, P1 (cost-aware capability-capacity separability): within a declared operating region, changing activated capability preserves the capacity-response interaction within a preregistered equivalence margin, while changing compatible Scaffold capacity preserves capability semantics up to a non-inferiority margin, and the required controls stay within a declared enforcement budget. Six design conditions become measured obligations whose coverage, violations, uncertainty, cost, and exclusions determine whether P1 is decidable. We propose a cluster-period randomized crossover experiment (balanced order, reset/washout, repeated seeds and failure regimes, cluster-aware uncertainty) with a four-state verdict: supported, falsified, conditional-engineering, or inconclusive. This paper contributes a contract-bounded runtime architecture, a source-preserving data substrate, and a falsifiable measurement protocol. It reports no completed implementation, experiment, dataset, or measured result.
A unified systems foundation and reference architecture for the agentic skills ecosystem is established, formalize skills as externalized procedural knowledge bridging high-level cognitive planning with deterministic execution environments, and systematically delineate the architecture across a nine-stage lifecycle.
Sanket Badhe, D. Shah, Priyanka Tiwari et al.· 0 citations
This paper argues that the introduction of agentic AI requires a substantial expansion of traditional enterprise architecture principles to address new behavioral, security, and governance risks emerging from non-deterministic AI systems interacting with heterogeneous operational platforms-ERP, HCM, CLM, asset management, workflow engines, and domain-specific applications.
Elizabeth Koumpan, Vimal Dimpi· AHFE International· 0 citations
Agentic AI is becoming a systems workload. A delegated goal is not a single prompt-response request; it unfolds as an agentic trajectory through model calls, tool calls, context operations, waits, approvals, recovery actions, and external effects. The trajectory is the smallest unit over which budget, authority, recovery, evidence, and physical cost can be stated without hiding essential state in application convention. Existing managed units still matter. Instructions, processes, requests, and model calls each made a different layer of the stack schedulable, protectable, accountable, recoverable, and optimizable. Agentic trajectories strain these units because state, authority, cost, and side effects span many calls. The stack therefore needs a system-visible unit for such trajectories. This paper calls that unit a managed trajectory and focuses on the contract that gives lower layers a common handle on identity, goals, budgets, placement, memory, authority, effects, evidence, and recovery. From a computer architect's perspective, agentic work is an interface and resource-management problem. The paper develops a stack organization and open research agenda around context hierarchy, protected effects, and metrics for useful work per verified action rather than only tokens per second.
The Agent Operating System (AOS), a vendor-neutral reference operating architecture for distributed agentic systems, is proposed as the operating architecture through which heterogeneous components can be composed into governable, reliable, observable, and interoperable agentic systems.
Governance, serverless, and automation facilitate enterprise integration that is adaptive, cost-effective, low-code, and capable of creating dynamic, context-aware, and value-adding workloads. This creates a need for policy-based management that simplifies implementation in multicloud scenarios. Serverless automation, enabled by event-driven workloads and dynamic resource provisioning for short-lived tasks, can operate in multicloud environments without being controlled by any provider. Introducing artificial intelligence facilitates improvements in scheduling and resource optimization. However, these benefits are not well understood, nor are these ecosystems properly managed. What governance is required for such serverless automation in an AI-enable enterprise integration setting? What does governance in serverless environments achieve? These questions are addressed through a structured research-product approach. The concept of serverless automation is first established, then applied to governance and a serverless context.A critical perspective on governance emerges through examination of central concepts and their interplay within a formal control-compliance-risk framework. From a practical angle, governance focuses on preserving trust in business operation and service delivery. This leads to the consideration of a Cloud Automation Control Plane that governs the core events and processes of Cloud Automation on behalf of initiation parties. The enterprise integration layer can be made serverless to minimize code development, improve resilience, and enhance security with AI assistance. The AI inclusion can be exploited for intelligent workload and resource management without compromising the governing principles. These avenues in combination demonstrate that a clear governance model can enable sustainable Cloud AI Automation for the enterprises and the ecosystem.
Sridhar Mahadevan· International journal of com...· 0 citations
AI agents powered by large language models are evolving from isolated assistants into heterogeneous systems in which multiple agents, planners, tools, and execution backends operate over shared environments. In such settings, safety becomes a system-level action-governance problem: deciding whether a pending action should be committed given policy-relevant state accumulated across a session. Existing safeguards operate at fragmented boundaries, making it difficult to enforce shared policies over composed action flows across heterogeneous execution paths. We present OpenAgentFlow, a control-plane/action-plane architecture that establishes the action-commit boundary as a shared enforcement interface. GUI, API, tool, and LLM-generated actions are normalized into a common AgentEvent stream and mediated by a shared pre-execution Policy Enforcement Point, while provenance, session state, audit evidence, and updatable policies are maintained outside individual agents. This provides a common governance layer across incompatible executors and allows new policies to take effect without modifying agents, prompts, models, or execution paths. We evaluate OpenAgentFlow through complementary system evaluations spanning controlled action-flow tests, a public external benchmark, policy updates, and real Android execution. On a 300-case controlled suite, OpenAgentFlow achieves 94.00% accuracy and a 95.35% attack-block rate. On the complete 1,220-case AgentDojo-Traj split of TS-Bench, it achieves 97.62% accuracy, 96.59% unsafe-action recall, and a 1.96% safe false-intervention rate. New control-plane rules take effect without modifying protected agents, and the same enforcement path operates across live GUI, API/tool, and LLM-planned Android execution. These results show that a shared action-commit boundary provides a practical basis for system-wide governance across heterogeneous agent execution paths.
Dongsheng Chen, Xiangyu Zhao, Xin Yao et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
