Intelligent automation of economic processes based on retrieval-augmented generation and large language models

<jats:p>The article is devoted to the theoretical and methodological substantiation of the concept of intelligent automation of economic processes based on the integration of Retrieval-Augmented Generation (RAG), Large Language Models (LLM), Prompt Engineering, and Automatic Engineering technologies. The modern digital economy is moving from technical automation to cognitive automation, in which self-learning systems are emerging that can adapt to environmental changes, analyze the results of their own activities, and generate new economic solutions. RAG acts as a cognitive intermediary between generation and data retrieval, ensuring the factual reliability of analytical results. LLMs provide semantic interpretation of information and create conditions for natural-language scenario modeling. Prompt Engineering determines the quality of interaction between humans and the system by transforming users’ analytical intentions into a formalized query structure. Particular attention is paid to Automatic Engineering as a meta-level of cognitive management that ensures automated prompt improvement, reconfiguration of generation parameters, development of decision metamodels, and formation of digital twins of management processes. A multilevel cognitive-engineering model of economic management is proposed, which includes strategic, cognitive-technical, self-learning, and reflexive levels. This architecture forms a closed cognitive cycle of “generation – evaluation – optimization – updating,” which ensures the system’s capacity for reflexive self-learning and evolutionary development. The practical significance of the research lies in creating a methodological basis for implementing agentic AI solutions in strategic planning, risk forecasting, and enhancing the intellectual resilience of economic systems in the digital economy. Keywords: intelligent automation, Retrieval-Augmented Generation (RAG), Large Language Models (LLM), Prompt Engineering, Automatic Engineering, cognitive architecture, digital economy, strategic management, self-learning economy, artificial intelligence.</jats:p>