Building Production Grade Agentic Retrieval-Augmented Generation (RAG)
Large Language Models (LLMs) are powerful but suffer from two primary limitations: knowledge cutoff (they only know what they were trained on) and hallucinations (they confidently invent facts). Retrieval-Augmented Generation (RAG) solves this by grounding the model in external, verifiable data. Retrieval-Augmented Generation (RAG) is emerging as a core architectural pattern for building production-ready AI assistants because it overcomes the closed-world and staleness limitations of stand-alone large language models (LLMs) by grounding generation in external knowledge sources. Instead of relying solely on pre-training, a RAG system ingests heterogeneous documents, indexes them in a vector database, retrieves the most relevant snippets at query time, and injects them into the prompt to ensure responses are accurate, up-to-date, and aligned with private or domain-specific data. This talk presents a practical, end-to-end blueprint for RAG pipelines, emphasizing that most failures stem from the retrieval layer rather than from the LLM itself.
Date and Time
Location
Hosts
Registration
-
Add Event to Calendar
Loading virtual attendance info...
- 960 River Road
- TEANECK, New Jersey
- United States 07666
- Building: Becton Hall
- Room Number: 205
- Starts 10 March 2026 04:00 AM UTC
- Ends 10 April 2026 05:00 PM UTC
- No Admission Charge
Speakers
Dr. Deepak Garg of Advertising Research Foundation
Building Production Grade Agentic Retrieval-Augmented Generation (RAG)
Biography:
Dr. Deepak Garg is a seasoned practitioner in artificial intelligence with over 20 years of experience in AI, Deep Learning, Machine Learning, and Statistical Modeling. He currently serves as a Data Science Manager at the Advertising Research Foundation (ARF), where he drives end-to-end machine learning and analytics initiatives in advertising and audience research, leading the development and deployment of advanced AI systems. He has also architected RAG pipelines and works with emerging agentic AI technologies such as the Model Context Protocol (MCP) and A2A protocol. He holds a PhD in Mechanical Engineering from UCLA (2017), where he also completed a master’s degree in aerospace engineering (2015), thereby building deep expertise in modeling, simulation, and quantitative methods. He further expanded his engineering base with a master’s degree in engineering (2012) from Purdue University and a bachelor’s degree in Naval Architecture and Marine Engineering (2006) from Jadavpur University.
Email:
Address:New Jersey, United States