MUMBAI, India, July 24 -- Intellectual Property India has published a patent application (202641067420 A) filed by Dr. K. R. Jansi; Narem Mounish Reddy; and Sal Anirudh Pataneni on May 29, 2026, for Dynamic Supply Chain Optimization Using Agentic Ai.
Inventors include Dr. K. R. Jansi; Narem Mounish Reddy; and Sal Anirudh Pataneni.
The application for the patent was published on July 17, 2026, under issue no. 29/2026.
Abstract: The project introduces an Autonomous Supply Chain Decision System which operates as a Python based multi agent artificial intelligence platform that enhances worldwide supply chain decision making through its intelligent automation and predictive analytics and simulation driven optimization capabilities. The system consists of a modular architecture: which operates 1 0 through a FastAPI backend and a Streamlit based interactive dashboard and a centralized orchestration layer that coordinates multiple specialized agents who handle specific business functions like market analysis and pricing strategy and logistics evaluation and risk assessment. The global orchestrator controls three main workflows which handle market intelligence and vendor simulation and price forecasting that enable users to assess worldwide demand and 1 5 execute pricing simulations with different restrictions while using machine learning to forecast future price movements. The agent based design follows a structured reasoning execution paradigm which enables 13 agents to process domain specific inputs and create intermediate insights and share structured outputs to create a complete decision pipeline. The vendor simulation workflow requires agents to follow a sequence which starts with market demand 20 analysis and supply surplus evaluation and transportation route assessment through Haversine formula and risk assessment of geopolitical and operational factors and then uses pricing elasticity to find optimal profit through heuristic grid search across various pricing levels. The system uses lightweight machine learning models for demand trend estimation and price forecasting which includes seasonal adjustments to enhance prediction accuracy. The system 25 uses a dynamic data layer which creates synthetic datasets for 15 global markets and 10 semiconductor related products and maintains the system's capacity to scale while preserving reproducibility through automated data generation. The API and dashboard communicate through RESTful endpoints which enable users to interact with AI driven insights in real time while visualizing the results. The system shows how multi-agent AI frameworks can change 30 conventional supply chain operations into adaptive data driven ecosystems that work to achieve maximum profitability while decreasing operational risks.
Disclaimer: Curated by HT Syndication.
