Souvik Ta Won Google GenAI Capstone Award
We are super excited to share Souvik Ta has been recognized as a top-20 winner in the highly competitive Google GenAI Intensive Course Capstone. This prestigious global competition attracted over 6,000 teams—many of which included multiple members—making Souvik’s solo achievement especially remarkable. Souvik's innovative approach stood out for its novelty and practical potential, and we are excited to further develop it toward industry-scale deployment in collaboration with industrial partners. We the SustainAI group is proud to support cutting-edge work at the intersection of generative AI and real-world engineering challenges.
Links:
Official Announcement by Google
Project Intro: ChemSimGuide: AI-Powered Chemical Simulation Assistant
Google GenAI Capstone Project – Honorable Mention
This project addresses the inherent complexity and usability challenges faced by chemical engineers and researchers when setting up simulations with advanced computational tools like Cantera. ChemSimGuide is an AI-driven conversational assistant designed to simplify chemical simulation setup through intuitive, natural language interactions.
Leveraging Google's Gemini-2.5-Pro language model, ChemSimGuide translates user-described simulation goals into executable Python scripts, automatically integrating detailed knowledge from Cantera’s extensive documentation using Retrieval-Augmented Generation (RAG). The conversational interface, powered by LangGraph, systematically guides users through clarifying simulation parameters, making model selections, and troubleshooting common simulation errors.
