Build with AI roadshow is a premier event series powered by Google Developer Groups that aims to empower developers, tech enthusiasts, and innovators to create scalable, real-world solutions using Google's latest artificial intelligence models and Cloud technologies.

The roadshow delivers an immersive, hands-on experience where attendees can dive directly into code, deployment, and modern AI architectures. Participants engage in interactive workshops, technical deep-dives, and live product demos that cover a wide range of topics, from mastering advanced generative models like Gemini to building robust cloud infrastructure and multi-agent systems.

Agenda

Reducing Human Cognitive Load Through Generative AI Platforms by Saleem

As Generative AI platforms become increasingly integrated into everyday workflows, designing experiences that simplify rather than overwhelm users has become critical. This session explores the concept of human cognitive load and how Generative AI can be designed to reduce mental effort, improve decision-making, and enhance productivity. The talk covers key cognitive load theory concepts, practical UX and product design strategies for AI systems, real-world examples, and the challenges of building human-centered AI experiences. Attendees will gain insights into how thoughtful AI design can transform GenAI platforms into effective cognitive partners rather than additional sources of complexity.

Build Multi AI Agents using Agent Development Kit (ADK)

We will have a hands-on workshop about the Google ADK (Agent Development Kit).

Participants will learn the concepts and practical steps to develop their own AI Agents and deploy either to Cloud Run or the Agent Engine.

We will cover:

- Multi-agent Architecture

- Model Context Protocol (MCP)

- Agent2Agent Protocol (A2A)

- ADK Dev UI

- Deploying Agents to Cloud Run and Agent Engine

LLMOps in practice: Operating AI beyond the Demo by Majd

LLM applications are moving fast from demos to real production systems, but many teams are still operating them like experiments. Traditional DevOps pipelines are great at deploying code, and traditional MLOps pipelines are great at managing data and models, but LLM-powered applications introduce new production assets: prompts, embeddings, vector indexes, retrieval pipelines, model gateways, evaluation datasets, guardrails, and agent workflows.

In this session, we will explore the new MLOps/DevOps stack for LLMs: how to version prompts, automate evaluation in CI/CD, deploy RAG pipelines, manage model endpoints, observe token usage and latency, control cost, secure access to enterprise knowledge, and use GitOps principles to promote AI changes safely across environments.

The goal is to show how DevOps and MLOps practices can transform LLMs from impressive demos into reliable, governed, and scalable production platforms.

Gemma 4 Redefined: Training Smarter, Faster, and Lighter by Eya

In this session, we’ll move beyond using AI as a general tool and learn how to turn Gemma 4 into a specialized expert for your specific needs. Using a powerful tool called Unsloth, we will walk through the process of teaching the model new skills using your own data, all while saving time and reducing the computing power required.

What we will cover:

• The "Specialist" Shift: How to move from a general AI to a model that understands your specific database and industry language.

• Faster & Smarter Tuning: A look at how Unsloth makes training 2x faster and much lighter on your hardware.

• Step-by-Step Implementation: From prepping your data to running the actual training loop and testing the final results.

• Real-World Results: Seeing how a fine-tuned model compares to a "standard" one when handling specialized tasks.

Unlocking Enterprise AI: A Deep Dive into the Gemini Enterprise Agent Platform by Ahmad

In this deep-dive session, we will explore the capabilities of the Gemini Enterprise Agent Platform and how it is redefining the way organizations build, deploy, and scale autonomous AI agents. Designed specifically for developers, technical architects, and technology leaders, this presentation moves beyond foundational generative AI concepts to uncover the robust architecture required for multi-step, production-ready enterprise workflows.

Venue

Venue: Zain Innovation Campus KHBP, Amman, Jordan.

Location: https://maps.app.goo.gl/P5Qoac7WaoxLXVBX7

Parking information: KHBP outdoor parking space are available and free.

Venue Access: Use the Gate 2 for entrance to KHBP and arrive at Zain Innovation Campus.

Accessibility: Our event is well-prepared to host people with physical disabilities, contact us for assistance.

Registration Policy

Join the Waitlist: Please complete the registration form to join the waitlist. We will be releasing spots as they become available, and you will be notified immediately via email. We appreciate your understanding and hope to see you there!

RSVP Required: Registration via the official event platform is mandatory. Attendance is free.

Check-in & Capacity: Check-in is available all time. Entry is first-come, first-served for registered attendees, subject to venue capacity limit.

Code of Conduct: Adherence to the GDG Code of Conduct is required by all attendees.

Photography/Media: Event photography/videography may occur. Attendance implies consent for potential inclusion in official GDG Amman and partnering media.

Cancellation: If unable to attend, please cancel your registration promptly via the platform, as spaces are limited.

Age Requirement: Attendees under 18 must be accompanied by a responsible adult guardian.

Right of Refusal: GDG Amman Organizers and hosting venue personnel reserve the right to decline entry or remove individuals for policy/Code of Conduct violations or safety concerns.