Abstract
The rapid transition from reactive large language model (LLM) interfaces to persistent, action-capable systems has revealed fundamental gaps in the architectural understanding of Agentic AI, particularly in disentangling inference, orchestration, and execution layers. Despite significant progress, there remains a lack of unified frameworks that systematically explain how autonomous agents can be designed, deployed, and evaluated as full-stack systems. This paper presents a comprehensive, layered analysis of Agentic AI architectures. We begin by establishing the foundations of Agentic AI and layered architectures, examining the evolution from reactive LLMs to persistent agentic systems and identifying core design principles such as modularity, memory hierarchy, and continuous execution. We then analyze OpenClaw and Ollama as a full-stack Agentic AI architecture, where Ollama functions as the LLM inference layer and OpenClaw operates as the agent runtime layer, enabling seamless integration from model inference to autonomous reasoning, planning, and action. To substantiate this architectural perspective, we introduce a prototype experimental validation of the OpenClaw–Ollama fullstack system. Through controlled configurations, benchmark task design, and system-level evaluation metrics, the results demonstrate a consistent monotonic improvement in performance as architectural complexity increases, confirming that autonomous capabilities such as tool use and persistent memory emerge from system integration rather than isolated models. Building on these findings, we further analyze operational challenges, safety, and evaluation, highlighting critical issues in security, privacy, governance, and benchmarking of persistent agentic systems. Finally, we explore future research directions, including scalable multi-agent systems, distributed architectures, and human-centered, responsible autonomous AI. Overall, this work establishes a unified architectural framework for Agentic AI, provides empirical validation of full-stack autonomous systems, and outlines a roadmap toward scalable, secure, and trustworthy autonomous agents. Prototype experimental validation, architecture, models, code, and experimental datasets are openly released to support reproducibility, transparency, and community benchmarking at GitHub.