Uploaded June 2026 | Updated September 2026, 2 weeks ago
Join this session for insights and best practices to optimize Gemini 3 applications for quality, cost, and scalability, gathered from our collaboration with top Google Cloud enterprise customers. We’ll deconstruct real-world implementation questions – ranging from complex agentic setups to high-volume data processing – and share the practical lessons learned. Learn how to adapt your prompting strategy to get the most from Gemini 3’s capabilities. Get concrete steps to reduce latency and manage token costs. Discover how to design prompts that are robust against production data distributions. Dive deep into advanced use cases for agents, long-context retrieval, and autoraters. And explore methods for updating existing prompts to align with Gemini 3’s standards.
Watch more Google Cloud Next 2026 Sessions → https://goo.gle/gcloud-next-2026
Subscribe to Google Cloud Tech → https://goo.gle/GoogleCloudTech
Speakers: Daniel Kyme, Skander Hannachi, Darvish Shadravan
BRK2-086
#GoogleCloudNext
Join this session for insights and best practices to optimize Gemini 3 applications for quality, cost, and scalability, gathered from our collaboration with top Google Cloud enterprise customers. We’ll deconstruct real-world implementation questions – ranging from complex agentic setups to high-volume data processing – and share the practical lessons learned. Learn how to adapt your prompting strategy to get the most from Gemini 3’s capabilities. Get concrete steps to reduce latency and manage token costs. Discover how to design prompts that are robust against production data distributions. Dive deep into advanced use cases for agents, long-context retrieval, and autoraters. And explore methods for updating existing prompts to align with Gemini 3’s standards.
Watch more Google Cloud Next 2026 Sessions → https://goo.gle/gcloud-next-2026
Subscribe to Google Cloud Tech → https://goo.gle/GoogleCloudTech
Speakers: Daniel Kyme, Skander Hannachi, Darvish Shadravan
BRK2-086
#GoogleCloudNext










