This event is a combined session and hands-on workshop focused on building a zero-ops corporate AI assistant using a serverless AI stack on Google Cloud.

The session will begin with a conceptual walkthrough, where we’ll break down the architecture of a modern serverless AI application — covering design patterns, scalability, security, and real-world production considerations. You’ll understand how AI assistants can be built and deployed without managing infrastructure, enabling teams to focus purely on innovation and business value.

In the second half, the event transitions into a guided hands-on workshop. Participants will implement a working AI assistant using Cloud Run and Gemini via Vertex AI, following a step-by-step walkthrough. This practical exercise will demonstrate how to move from idea to production-ready AI applications using cloud-native, serverless components.

Key Takeaways

• End-to-end understanding of a serverless AI architecture

• Practical experience with Cloud Run and Gemini (Vertex AI)

• Best practices for scalability, reliability, and zero-ops deployments

• Insights into taking AI applications from prototype to production

Important Note:
This session includes a hands-on demo so all attendees are requested to carry their laptops to actively participate.