Uploaded August 2026 | Updated September 2026, 2 weeks ago
Launch your web-based video game with AI lab → https://g.dev/ai/builders-lab-3
Launch a web-based video game with Google AI Studio.
🎮 Welcome back to the third installment of the AI Builder series. In this video, Luke takes things a step further by launching a live, web-based, turn-based video game using Google AI Studio and Google Cloud.
1. Building on the previous tutorials where we launched a portfolio site and a to-do application, this lab introduces more advanced concepts to help you create your own sharable multiplayer games.
2.*What you'll learn in this video:*
* *Event sourcing explained:* Learn how event sourcing works by saving a complete history of game actions rather than overwriting database states. This allows for advanced features like replaying and undoing moves.
3. *Building a tic-tac-toe game:
Luke walks through setting up a turn-based game using simple algorithms like Minmax for single-player mode.
4. *Handling database permissions:* See a real-time example of troubleshooting Firestore "missing or insufficient permissions" errors using the Google AI Studio "fix" feature.
5. *Deploying to Cloud Run:* Publish the game to a live .ai.studio domain and test its functionality across devices.
7. *Real-time multiplayer:* Experience how Firestore automatically handles synchronization so two players can compete in real time from anywhere in the world.
8. *Debugging production bugs:* Learn how to catch, copy, and feed production bugs directly back into Google AI Studio for quick debugging and republication.
9. *Inspecting the Firebase console:* Look under the hood at how game events are structured and stored chronologically in your database collections.
10. *Prerequisites:* Before getting started, make sure a Google Cloud project with billing is attached. (Note: This app relies on local logic and does not make calls to LLMs).
11. Ready to build your own custom game? Customize the code to create chess, your own original turn-based game, or stick to classic tic-tac-toe!
12. Don't forget to visit the link at the end of the lab to claim your completed builder's badge.
13. If you enjoyed this tutorial, please like, subscribe, and happy building! 🚀
Watch more AI Builders → https://g.dev/cloud/builders-lab
🔔 Subscribe to Google Cloud Tech → https://goo.gle/GoogleCloudTech
Speaker: Luke Schlangen
Products Mentioned: Google AI Studio, Firebase, Firestore, Cloud Run
Launch your web-based video game with AI lab → https://g.dev/ai/builders-lab-3
Launch a web-based video game with Google AI Studio.
🎮 Welcome back to the third installment of the AI Builder series. In this video, Luke takes things a step further by launching a live, web-based, turn-based video game using Google AI Studio and Google Cloud.
1. Building on the previous tutorials where we launched a portfolio site and a to-do application, this lab introduces more advanced concepts to help you create your own sharable multiplayer games.
2.*What you'll learn in this video:*
* *Event sourcing explained:* Learn how event sourcing works by saving a complete history of game actions rather than overwriting database states. This allows for advanced features like replaying and undoing moves.
3. *Building a tic-tac-toe game:
Luke walks through setting up a turn-based game using simple algorithms like Minmax for single-player mode.
4. *Handling database permissions:* See a real-time example of troubleshooting Firestore "missing or insufficient permissions" errors using the Google AI Studio "fix" feature.
5. *Deploying to Cloud Run:* Publish the game to a live .ai.studio domain and test its functionality across devices.
7. *Real-time multiplayer:* Experience how Firestore automatically handles synchronization so two players can compete in real time from anywhere in the world.
8. *Debugging production bugs:* Learn how to catch, copy, and feed production bugs directly back into Google AI Studio for quick debugging and republication.
9. *Inspecting the Firebase console:* Look under the hood at how game events are structured and stored chronologically in your database collections.
10. *Prerequisites:* Before getting started, make sure a Google Cloud project with billing is attached. (Note: This app relies on local logic and does not make calls to LLMs).
11. Ready to build your own custom game? Customize the code to create chess, your own original turn-based game, or stick to classic tic-tac-toe!
12. Don't forget to visit the link at the end of the lab to claim your completed builder's badge.
13. If you enjoyed this tutorial, please like, subscribe, and happy building! 🚀
Watch more AI Builders → https://g.dev/cloud/builders-lab
🔔 Subscribe to Google Cloud Tech → https://goo.gle/GoogleCloudTech
Speaker: Luke Schlangen
Products Mentioned: Google AI Studio, Firebase, Firestore, Cloud Run








![Dynamic Firebase skills: Architecting agent ready codebases
Firebase agent skills → https://goo.gle/4u3McWt
[GitHub] Agent skills → https://goo.gle/42JsuEa
[Codelab] How to use AI Agent Skills → https://goo.gle/4umgrbO
Watch along and hear Rody Davis break down how to architect existing, real world codebases for agentic development. Discover how to implement client side Firebase skills using Firestore to create sandbox contexts, maximize LLM efficiency with agent optimized context.md directory readmes, and manage complex monorepos through interconnected AI agent structures. Whether you are using Antigravity for backend workflows or tools like Stitch and Google AI Studio to accelerate your MVP design phase, discover how optimizing code health and architectural patterns can massively supercharge your AI assisted engineering velocity.
Chapters:
0:00 - Intro
0:37 - Shipping skills with Firebase
2:25 - Preparing codebases for agentic AI
3:51 - Tips and tricks for using Antigravity
5:33 - How to get started with agentic AI and vibecoding
7:13 - Wrap up
Watch more Google Cloud Next 2026 → https://goo.gle/next-talks-2026
🔔 Subscribe to Google Cloud Tech → https://goo.gle/GoogleCloudTech
#GoogleCloudNext
Speakers: Aja Hammerly, Rody Davis
Products Mentioned: Gemini, Google AI Studio, Antigravity, Stitch, Firebase Dynamic Firebase skills: Architecting agent ready codebases](https://i.ytimg.com/vi/urBML_2BbD8/mqdefault.jpg)

![Building GPU-accelerated multi-agent apps with Google ADK and Gemma 4
Join the Google Cloud & NVIDIA community → https://goo.gle/google-nvidia-programs
On this week’s livestream, join Chelsie Czop and @NVIDIAs Jay Rodge and learn how to build a GPU-accelerated sustainability intelligence app from scratch.
You’ll learn how to orchestrate a team of specialist agents using the open-source Google Agent Development Kit (ADK), serve Gemma 4 efficiently on Cloud Run using NVIDIA RTX PRO 6000 GPUs, and connect them with Milvus for policy retrieval.
Whether you are looking to deploy local models or scale production agentic workflows, this is the architecture blueprint you need.
This livestream originally aired on May 12, 2026 at 9:00 A.M. PDT / 12:00 P.M. EDT.
Chapters:
0:00 - Countdown
1:48 - Intro
3:58 - What are AI agents enabling?
13:40 - G4 powered by NVIDIA RTX PRO 6000 Blackwell GPUs
18:28 - GPU accelerated sustainability intelligence
21:32 - [Demo] Sustainability Agent
27:43 - What is Model Context Protocol (MCP)?
30:03 - Where is agentic AI being used for workloads?
36:56 - How can developers stop AI agents from getting stuck in a loop?
39:39 - When should organizations transition from human-in-the-loop to agentic AI?
42:02 - Does Gemini Enterprise have access to GPUs?
42:50 - What challenges do AI agents face when retrieving accurate policy data?
46:13 - How do organizations approach security, privacy, and regulations when multi-agent orchestration is used?
49:08 - Where is Jay Rodge using AI agents?
53:32 - How to get started with agentic AI on GPUs
56:09 - Wrap up
Speakers: Chelsie Czop, Jay Rodge
Products: Agent Development Kit, Gemma 4, Cloud Run Building GPU-accelerated multi-agent apps with Google ADK and Gemma 4](https://i.ytimg.com/vi/vIyhQGBkn34/mqdefault.jpg)