Corporate onboarding requires the effective transfer of complex organizational knowledge embedded in internal policies and procedural documents; however, existing artificial intelligence (AI)-driven course generation systems primarily target academic or public knowledge domains. This gap limits the scalability and consistency of enterprise training, particularly in regulated environments where factual accuracy is critical. In this study, we present a multi-agent pipeline that automatically generates Sharable Content Object Reference Model (SCORM) 1.2-compliant e-learning courses from heterogeneous enterprise documents using large language models and retrieval-augmented generation (RAG). The system integrates four stages: semantic document ingestion with structure-aware chunking and embedding, an autonomous ReAct-based architect agent for course design, a parallel content generation pipeline combining multi-query retrieval and neural reranking, and standards-compliant SCORM packaging for deployment in learning management systems. Evaluated using real-world occupational safety documents, the system produced a complete multi-module course with structured lessons and assessments within minutes, demonstrating end-to-end automation of instructional design grounded exclusively in source materials. By ensuring traceability of generated content to organizational knowledge, the approach reduces the risk of hallucinations.

Industrial energy consumption in shift-based manufacturing exhibits pronounced temporal asymmetry—here defined as direction-dependent conditional dynamics in which the transition from production to shutdown states follows a systematically different temporal trajectory than the reverse transition. At the facility studied, this asymmetry also manifests in the marginal distribution of hourly consumption values: pooling all 4724 observations yields a bimodal, right-skewed histogram (skewness ≈ −0.4) comprising two sub-populations corresponding to production hours (14–19 kWh/h) and shutdown hours (0–2 kWh/h). Although individual hourly observations are serially dependent and therefore not i.i.d., the marginal distributional shape is consequential because ARIMA-class models assume approximately Gaussian innovations, and residuals from models fit to this bimodal series inherit its non-Gaussianity. More fundamentally, the conditional distribution P(E_t|E_{t − 1}, …) is direction-dependent: the production-to-shutdown transition is abrupt (1–2 h, 18:00–20:00), while the shutdown-to-production ramp is slower and more variable (2–4 h, 05:00–07:00). Symmetric ARMA models, applying identical autoregressive coefficients regardless of transition direction, cannot represent this directional asymmetry, rendering their assumptions and associated error metrics structurally unreliable for this class of data. This paper addresses this asymmetry directly by presenting and evaluating two hybrid forecasting architectures—Prophet+LSTM and SARIMA+LSTM—for 24 h-ahead energy prediction at an industrial bread factory in Kazakhstan, instrumented with 15 IoT energy meters. The two-stage design exploits the complementary asymmetry-handling properties of each component: the statistical model (Prophet or SARIMA) captures deterministic seasonal structure, while the LSTM corrects asymmetric residuals that the statistical model systematically misrepresents. In a rigorous 14-day holdout evaluation, Prophet+LSTM achieves an MAE of 3.39 kWh—outperforming the Seasonal Naïve baseline by 12.3% and reducing Prophet-alone error by 32.7%—with statistical significance at the 10% level confirmed via Diebold–Mariano testing (DM = +1.747, p = 0.081). The LSTM residual correction reduces Prophet’s systematic negative bias by 69% (from −3.60 to −1.13 kWh), as confirmed by ablation testing. In eight weeks of production operation with incremental retraining, MAE improved 35% (7.02 → 4.58 kWh). These results demonstrate that explicitly modelling temporal asymmetry through hybrid statistical-neural architectures substantially improves industrial energy forecasting accuracy.