Hands-On Workshop Series-3: Build with Gemma 4

From Product Development to Deep Dive and Mastery

Join this hands-on workshop series designed for developers, AI enthusiasts, and builders who want to learn how to create real-world AI applications using Gemma 4. Across three progressive workshops, participants will gain practical experience building, testing, and refining AI-powered products while exploring the capabilities and advanced techniques of Gemma 4.

All hands-on development activities will be conducted using Antigravity, an agentic coding environment that helps developers accelerate AI application development.

What you will master across the series:

• Build with Gemma 4: Learn how to build applications and leverage agentic coding workflows to massively increase development productivity.

• Deep-Dive Technical Sessions: Explore the inner mechanics, boundaries, and hidden capabilities of the Gemma 4 architecture.

• Production-Ready AI Solutions: Master software engineering best practices for creating robust, secure, and scalable AI applications.

Through live coding demonstrations, guided exercises, and interactive discussions, attendees will gain practical experience using both Gemma 4 and Antigravity to transform ideas into working AI applications. Participants who virtually attend and successfully complete each workshop will receive a Workshop Completion Certificate recognizing their participation and achievement.

Session Title:

From Chatbot to Mentor: Building a Local Socratic Tutor with Gemma 4

Session abstract:

Most AI applications suffer from "answer-dumping"—they do the homework for the user instead of teaching them. In this practical, hands-on session, we will build a Socratic Study Buddy using Gemma 4. Unlike previous open models, Gemma 4’s high intelligence-per-parameter allows it to maintain complex pedagogical personas without "breaking character."

We will walk through the full developer lifecycle: from local setup in LM Studio to implementing multimodal vision inputs for analyzing textbook diagrams. We will also demonstrate how to bridge the gap between text and visuals by using Gemma 4 to generate real-time Mermaid.js logic flowcharts. Whether you are a student, educator, or developer, you will learn how to turn a raw model into a private, offline, and truly intelligent mentor.

About the speaker:

Lesly Zerna is an AI community leader, educator, and engineer from Bolivia. She serves as the Latin America Coordinator for City.AI and School of AI, helping grow AI communities across the region. She holds a master's degree in Computer Science from Belgium and is an Associate Professor in the Engineering School at a university in Bolivia.

She is the co-founder of Mentor Her, an initiative that encourages girls to explore careers in technology and data science. Lesly has delivered TEDx talks, created machine learning courses for Platzi, mentored learners at Udacity, and is a frequent international speaker on machine learning, TensorFlow, data science, and AI. She is passionate about education, community building, and empowering others through technology.