Applied AI Summit

Free online conference | October 14-16, 2025

Agentic AI and the Future of Generative Supply Chain Solution

As generative AI continues to reshape enterprise workflows, the next frontier lies in intelligent, autonomous systems, Agentic AI—that go far beyond static chatbots. This session presents a transformative vision of how supply chain leaders can harness Agentic AI to drive real business outcomes.

We’ll explore how large language models (LLMs), when combined with retrieval-augmented generation (RAG) and task-oriented agents, enable assistants that not only answer user queries but also take initiative: proactively forecasting demand, generating replenishment recommendations, and issuing early warnings for potential stockouts or overages. These generative agents are embedded with supply chain context and connected to real-time data sources, enabling continuous reasoning and decision-making.

The talk will cover:

  1. Architecture of generative supply chain assistants using RAG + Agentic AI
  2. Real-world use cases such as inventory classification, phantom inventory detection, and demand prediction
  3. Integration with enterprise knowledge bases and ERP systems
  4. Design considerations for explainability, autonomy, and business alignment
Back to speakers

About the speaker

Shiva Kumar Ramavath

Lead AI Machine Learning Engineer at Albertsons

Shiva Kumar Ramavath, Ph.D. (Candidate) is a Data Scientist and Lead AI & Machine Learning Engineer with over a decade of experience transforming enterprise operations across retail, telecom, and manufacturing. At Albertsons, a Fortune 50 retailer, he leads initiatives in AI, digital twins, and machine learning, driving over $120 million in business impact through innovations in demand forecasting, inventory optimization, and supply chain efficiency. Through his work, he continues to drive innovation in data-driven decision-making and business transformation. Academically, Shiva is pursuing a Ph.D. in Artificial Intelligence at the University of the Cumberlands, where his research focuses on the development of Explainable AI for domain specific models and Small Language Models to address enterprises level problems. He holds a master’s degree in data science from the University of North Texas. His work blends advanced machine learning with real-world applications, helping enterprises unlock value from data while ensuring scalability, transparency, and resilience.