Overview
Coursera Flash Sale
40% Off Coursera Plus for 3 Months!
Grab it
Explore hands-on AI development through live demonstrations of Google AI Studio's new build experience in this comprehensive technical webinar. Learn to transform simple prompts into fully functional AI applications within minutes using natural language commands and intuitive interfaces. Follow along as Logan Kilpatrick from Google DeepMind demonstrates three practical AI agent builds: a virtual food photographer that generates high-end imagery from text menus, a local tour guide utilizing Google Maps grounding capabilities for real-time location data, and a conversational pair programmer created entirely through voice commands. Discover the new grounding with Google Maps feature that connects Gemini to live place data without requiring API setup, and examine the Google AI Studio Gallery for inspiration and templates. Gain insights into the agent industry landscape and explore the future of AI models as integrated systems. Access practical resources including Google AI Studio, Veo 3.1, Gemini 2.5 models, and comprehensive documentation to begin building your own AI agents immediately after viewing.
Syllabus
0:00 - Intro
1:05 - [Demo] Create a virtual food photographer
9:55 - [Demo] Grounding with Google Maps
14:26 - [Demo] Exploring the Google AI Studio Gallery
19:05 - [Demo] "Yap to App": Building a Live Pair Programmer
26:31 - Agent Industry Pulse
31:35 - The power of grounding with Google Maps
32:33 - The future of agents: models as systems
36:08 - Outro
Taught by
Google Cloud Tech