On October 28, our highly interactive and practical training course will come back, and hopefully include all new speakers and content about how startups and developers can use the newest Google Cloud AI solutions.
Event Schedule
TBD
Session 1
The Future is Agentic AI: Your First Gemini App
The next generation of breakout applications will be intelligent, multi-modal agents. Learn why Gemini's native ability to understand text, images, and audio makes it the ultimate tool for building them. This session lays the cornerstone for that journey.
You will learn to:
Securely manage and use your AI Studio API key.
Build your first API call to Gemini 2.5 to generate structured JSON data.
Leverage Gemini Grounded with Google Search
Craft advanced prompts to get reliable, creative ideas from the AI.
Learn how Cloud Run will be used as the deployment platform throughout Startup School: Gen AI.
Products Covered:
Gemini 2.5 Flash
Agent Development Kit (ADK)
AI Studio API key generation + Get Code
Gemini Grounding
Cloud Run
TBD
Session 2
Nano Banana Basic & Veo 3
TBD
Session 3
AI-Powered Audio: From Expressive Speech to Quality Control
AI-Powered Audio: From Expressive Speech to Quality Control
Level: 300
Go beyond robotic voices to generate expressive, human-like speech. Then, learn how to build an AI-powered quality assurance system that listens to the generated audio, compares it to the source text, and provides an automated quality score, a crucial step for scaling any generative media application.
You will learn to:
Prompt Gemini TTS to output advanced vocals and emotions.
Process and handle audio data streams on your server.
Send both audio and text data to a multimodal Gemini model.
Craft a sophisticated prompt that turns the AI into a QA agent.
Create and display an automated quality score for your generated content.
Products covered:
Gemini 2.5 Pro multimodal input)
Gemini TTS
Gemini CLI