Industry 4.0 and 5.0 technologies have made industrial environments data-rich, yet a persistent cognitive gap remains: operators face substantial difficulty interpreting and acting on this data in unstructured, time-critical situations. This paper presents an architecture that integrates the Asset Administration Shell (AAS), OPC UA, and a Large Language Model (LLM)-based agentic AI within a mandatory Human-in-the-Loop (HITL) framework. The AAS acts as a semantic grounding layer through Retrieval-Augmented Generation (RAG), supplying the LLM agent with ECLASS-referenced technical parameters that reduce the risk of hallucination. OPC UA Methods form a deterministic execution layer that keeps agent actions within PLC-validated safety boundaries. The HITL mechanism enforces a cryptographic approval gate so that no physical machine action can occur without documented human authorization. This requirement was motivated by an industrial survey ($n=117$), in which 47% of employees stated that human oversight is irreplaceable, combined with enterprise safety and accountability requirements and broader governance considerations for AI-driven actuation in safety-critical cyber-physical systems. Two proof-of-concept case studies evaluate the architecture under controlled laboratory conditions. Proof-of-concept results indicate system processing latencies of 1.7 s (maintenance) and ∼15 s (scheduling), with end-to-end latencies (including mandatory human approval) of 14.9 s and 62 s, respectively, representing estimated improvements of approximately 97% and 96% over expert-estimated manual baselines (∼8 min and 25–40 min). All figures derive from single scripted runs under controlled laboratory conditions and should be read as indicating architectural feasibility at Technology Readiness Level 4, not as statistically validated performance benchmarks: variability bounds and confidence intervals are unavailable, the manual baselines are expert estimates rather than instrumented measurements, and operator deliberation times derive from a single response per scenario. A structured comparison with related work shows that, to the authors’ knowledge, no published approach in the surveyed literature combines AAS semantic grounding, OPC UA deterministic execution, and mandatory cryptographic HITL within a single empirically grounded framework.

LoRa mesh networks enable long-range, low-power connectivity but are constrained by very low bitrate, spreading-factor-specific SNR thresholds, and regional duty-cycle limits. This article presents a snapshot routing framework that separates feasibility from optimality. Feasibility is enforced as hard constraints-only radio options that satisfy SNR thresholds (with safety margin) and fit within remaining duty windows, which are admitted using an Okumura–Hata backbone with a model-agnostic specialization for link geometry. Optimality is achieved on a spreading-factor-expanded directed graph, where each feasible SF is represented as a distinct edge, and a composite, dimensionless hop metric balances airtime-driven energy expenditure, current and incremental duty usage, and optional quality penalties. The method yields per-hop SF selection via shortest-path computation and supports rapid re-planning without event-level simulation. Snapshot-based evaluation indicates improved control of airtime, duty exposure, and energy, providing a practical basis for multi-criteria routing in LoRa mesh networks with applicability to airborne and infrastructure-sparse deployments.