Coursera Flash Sale
40% Off Coursera Plus for 3 Months!
Grab it
This 15-minute talk from Google I/O 2025 demonstrates five practical applications of the Gemini API for developers looking to build innovative applications. Learn how to implement image understanding capabilities for object recognition and scene description, create natural multimodal interactions combining voice, text, and images, and automate complex workflows through function calling. Discover techniques for leveraging Gemini's long context window to enable complex reasoning and multi-step problem solving. Speaker Mark McDonald provides comprehensive examples with links to resources including the Gemini API documentation, GitHub cookbook, GenList demo, and specialized tools for working with maps, plots, and browser integration in Gemini 2.0.
