Issue link: https://iconnect007.uberflip.com/i/1544155
14 SMT007 MAGAZINE I APRIL 2026 retrieval. The retriever component searches a large corpus of information to respond to the input query, and the generator component generates the final output by integrating the input query with retrieved passages. By fetching "facts" from external sources, RAG enables the link between the private data and the LLM to perform data analysis, summarization, and other tasks. This technique overcomes the limi- tation of AI models to what they have learned from their initial training on public data (up to a certain point in time). Overall, it enhances the accuracy, relevancy, and reliability of AI models. RAG also facilitates synthetic data generation by combining the real data and RAG documents to generate answers (outputs), which can be stored as synthetic training data for smaller models. Using RAG to fetch authoritative passages, then prompting the LLM to create synthetic corpora (summaries, expla- nations, reasoning chains) aligned with domain knowledge, is a plausible pathway. Agentic RAG Agentic RAG further extends RAG with agent-like behavior; it can plan what information it needs before retrieving, and choose which tools or sources to query. It iterates by retrieving, evaluating the results, deciding whether more retrieval is needed, and then retrieving again. It can also decompose complex questions into sub-questions and retrieve for each. As an intelligent layer that reasons, retrieves, and verifies, an added agent decides what to retrieve and when to continue ongoing conversations. The agentic nature provides step-by-step reasoning chains to lead to richer synthetic data than LLM outputs by adding context and rationale. My next column on AI data module 3 will focus on the development of synthetic data and IoT data management. SMT007 References 1. "Artificial Intelligence, Part 6: Data Module 1," by Jennie S. Hwang, SMT007 Magazine, October 2025. 2. "Artificial Intelligence, Part 4: Prompt Engineering," by Jennie S. Hwang, SMT007 Magazine, January 2025. Appearances Dr. Jennie Hwang will present "The AI Bubble Myth: Intelligence Incorporated and the Global Race," at The Wilson Science and Technology Forum on April 10, 2026. Dr. Jennie S. Hwang, an international business- woman, speaker, and business and technology advisor, is a pioneer and long-standing leader in SMT manufacturing since its inception, and in developing and implementing lead-free electronics technology and manufacturing. She has served as chair of Artificial Intelligence- Justified Confidence for DoD Command and Control study, chair of AI Committee of the National Acad- emies, and Review Panels of NSF National AI Insti- tutes and Committee of Strategic Thinking for Engi- neering Research. An International Hall of Famer (Women in Technology), she has been inducted into the National Academy of Engineering, named an R&D-Stars-to-Watch, and received the YWCA Achievement Award. She has held senior executive positions with Lockheed Martin Corp., and was CEO of International Electronic Materials Corp. She is currently CEO of H-Technologies Group, providing business, technology, and manufacturing solutions. She has served as chair of the Laboratory Assess- ment Board, the DoD Army Research Laboratory Assessment Board, and the Assessment Board of Army Engineering Centers. She is on the board of Fortune-500 NYSE companies and civic and univer- sity boards, Commerce Department's Export Council, National Materials and Manufacturing Board, NIST Assessment Board, various national panels/commit- tees, and international leadership positions. She is the author of 10 books (four as co-author) and 750+ technical/editorial publications. She is a speaker and author on trade, business, and educa- tion issues. Her formal education includes four academic degrees (Ph.D., M.S., M.A., B.S.), as well as Harvard Business School Execu- tive Program and Columbia University Corporate Gover- nance Program. To read previous columns, click here. S M T P E RS P ECT I V ES & P RO S P ECTS