Ashwin is a passionate Data Scientist and AI Solutions Engineer with expertise in Generative AI, Agentic Systems, and MLOps.
He specializes in building scalable, real-world AI solutions that push the boundaries of machine reasoning. From orchestrating autonomous multi-agent workflows using LangGraph and Gemini to deploying robust CI/CD pipelines on Google Cloud, Ashwin turns cutting-edge research into practical tools. As a Google Student Ambassador and SpaceTech enthusiast, he is always eager to explore the intersection of advanced AI and space exploration while contributing to the open-source community.
To learn more about Ashwin's work, explore the repositories below! 👇
Google's Agentic Leap: How Gemini Turned Workspace Into Your Autonomous Executive Assistant
In this blog, I explore Google's quiet shift into the agentic era by embedding Gemini across Workspace apps like Gmail, Drive, and Photos. I break down how cross-app workflows turn your cloud ecosystem into an autonomous executive assistant and share practical, action-oriented prompt strategies to automate your daily workflows. read more
Google Nano Banana: How Prompt Structure Changes AI Image Results
In this blog, I explore how structured prompting significantly improves AI-generated image results using Google’s Nano (Nano Banana 🍌) model. I break down a simple 5-step prompt framework—Subject, Action, Scene, Style, and Composition—and show how action-based prompts unlock better reasoning and storytelling in AI systems. read more