Day 1

This session explores the challenges of designing and deploying custom ML solutions for unique business needs. We’ll cover tackling messy data, scalability, fairness, and integration issues, drawing from real-world project experience.
Learn strategies to align technical feasibility with stakeholder expectations and discover tools and best practices to streamline development. Whether you’re starting out or refining your approach, this talk offers actionable insights to build high-impact, scalable ML systems.

Advanced data transformations accelerators, such as data lineage powered by GenAI are becoming increasingly critical, as industries prioritize data modernization, transitioning from traditional legacy systems to advanced data technologies. This paper delves into the application of LLMs in tracing the data lineage. We will share our direct experiences in addressing the issues, obstacles encountered and the effective strategies we implemented to overcome them. The proposed approach offers several advantages, including improved efficiency, accuracy, reliability and enhanced data security by keeping data knowledge within the enterprises cloud environment. The approach involves custom chunking strategies, hybrid semantic and vector search capabilities, selection of embedding model. Overall, this paper presents an efficient and secure solution for accelerating data lineage task leveraging LLMs.

We are rapidly accelerating towards a future where humans and intelligent agents will be working side by side to perform business operations and deliver business and technology services. How will this work? What are some pitfalls and how do we manage the risks associated with them? Do we need to create new job functions? Is this a parallel alternate path to AGI?

Build a help chatbot using RAG & LLM models to interact with structured datasets and a defined context. Put your AI development skills to the test!

This session will guide you through the process of building AI agents using Google Cloud’s Vertex AI platform. Learn about the latest tools and technologies like Agent Builder, Agentspace, NotebookLM, and Vertex Reasoning Engine, and see how they can be used to create AI agents for a variety of use cases. The session will cover everything from prototyping to production, including data preparation, model development, and deployment. You’ll also learn about best practices for building and deploying AI agents, including security, scalability, and performance. Whether you’re a beginner or an experienced AI developer, this session will give you the knowledge and skills you need to build and deploy AI agents on Google Cloud.

In this session, Chirag plans to present an Agentic viewpoint to coordinate between essential strategic components as agents in achieving business growth through an AI-focused approach. The session centers around the cooperative roles of AI Practitioners, AI Users, Business stakeholders, Legal teams, Infrastructure Management Groups, Cyber Security Groups, Responsible AI and Governance Committees, Partners, etc. The presentation stresses the significance of a strong legal framework for compliance and risk reduction, as well as the crucial role of Infrastructure Management and Cyber Security in protecting AI-driven projects. The Responsible AI and Governance Committee ensures ethical AI development and execution, with Business KPIs directing AI strategies to align with overarching organizational objectives. The session delves into the interdependent relationship between AI Practitioners and AI Users, highlighting the importance of effective training and collaboration to fully leverage the technology’s capabilities. Furthermore, strategic partnerships are underscored as essential for expanding AI capacities, fostering innovation, and realizing sustainable business growth. By cultivating a cohesive Agentic mindset and design patterns, businesses can tap into the combined strength of these strategic components to unleash the full potential of AI-powered growth and innovation.

The session will explore the concept of agents, delving into what they are and their potential applications. It will provide insights into when agents should and should not be used, as well as guidance on utilizing agentic frameworks effectively. Participants will learn about agentic workflows and design patterns, complemented by real-world business case studies to demonstrate their practical impact and value.