Build with AI Conference 2026

Name: Build with AI Conference 2026
Start: 2026-03-27T16:00:00+01:00
End: 2026-03-27T20:00:00+01:00
Location: Palace of Science

Palace of Science, 11, 11000 Kralja Milana, Beograd, 11000

GDG Belgrade

Build the future with AI

Mar 27, 3:00 – 7:00 PM (UTC)

212 RSVP'd

Key Themes

AIAI - GeminiAI - GemmaBuild with AICareer DevelopmentConferenceWorkshop / hands-on session

About this event

👩‍💻 Build the future with AIBuild with AI 2026 is a community-led, hands-on event designed to help developers, students, and tech enthusiasts learn by building. Through practical sessions and real-world examples, participants will prototype, build, and deploy AI-powered applications using the latest Google AI technologies, including Gemini, AI Studio, and Antigravity.
🎯 Our GoalsMake AI tools practical and accessible for developers of all levels
Show how to build, test, and deploy AI-powered applications
Introduce Google’s AI ecosystem and best practices
Encourage hands-on experimentation with real use cases
🌟 What to ExpectGuided codelabs and live demos
Practical workshops using Google AI tools
Real-world AI use cases and implementation tips
Insights into AI development trends and future opportunities
👥 Who Should AttendDevelopers and engineers interested in building with AI
Students looking to gain practical AI experience
Data scientists and ML enthusiasts
Anyone curious about applied AI and modern cloud technologies
🔥 Why You’ll Love ItHands-on, beginner-friendly sessions
Learn directly from practical examples
Google Cloud credits to try GCP at no cost
Networking with developers, speakers, and the local tech community
🎟️ Free Registration – Spots Limited!

When

Friday, March 27, 2026
3:00 PM – 7:00 PM (UTC)

Where

Palace of Science
11, 11000 Kralja Milana
Beograd 11000

Agenda

Check-in
Event Opening
[Elaine Dias Batista] AI Agents Face-Off: Same App, Multiple frameworks	The mobile development landscape has long been divided by framework wars: Native vs React Native vs Flutter vs Progressive Web Apps. While traditional comparisons often rely on synthetic benchmarks or oversimplified examples, this talk presents a unique approach: leveraging multiple AI coding agents to build identical, real-world applications across different mobile frameworks, then evaluating the results through objective metrics. This session will demonstrate how various AI agents tackle the same mobile app requirements using Kotlin/Swift (Native), React Native, Flutter, and modern web frameworks. We'll dive deep into the challenges each agent encountered, the quality of code produced, and provide a multi-dimensional evaluation framework that goes beyond surface-level comparisons.
[Konstantinos Kechagias] Way Back Home Series - Mission I: Identify Yourself	Your escape pod crashes on an unknown world. Systems fail. The AI activates: “Survivor detected. Beacon locked. Identity required.” Before rescue can begin, yourself you must define. Using multi-turn image generation with Gemini’s image models (Nano Banana), you will forge a consistent space-explorer avatar across chat sessions. Through precise prompt engineering and the Gemini Image API via Python, you will generate a portrait, create a matching map icon, and register your identity on the galactic rescue map. You will learn: • Multi-turn image generation for character consistency • Prompt engineering for stylized visual outputs • Gemini Image API through Python • Chat-based iterative refinement By the end, you will: ✅ Have a generated explorer portrait ✅ Have a consistent map icon ✅ Be registered in the rescue network ✅ Appear on the live world map
[Darya Vinogradova] VLM System Design for an AI Assistant	As AI agents increasingly rely on vision-language models, the challenge shifts from raw capability to reliable perception. When is prompting enough, and when does an agent need a fine-tuned model to work in production? This talk explores how different adaptation strategies shape real-world agents through practical cases: a reactive home camera with text triggers, product matching on marketplaces, and a multimodal conversational assistant. We’ll look at how these systems behave under real constraints—and how to choose the right balance between flexibility and reliability when building AI agents.
Closing Ceremony