AI Engineering with the Google Gemini 2.5 Model Family
summary
Hands-on workshop shows live use of Gemini 2.5 Flash (free API tier) and Gemini 2.5 Pro, uploading files to AI Studio, counting tokens (input/output/thought) and controlling a thinking budget to trade cost for reasoning; demos include PDF OCR→structured JSON extraction, multimodal video frames at 1fps, URL context and Google Search native tools, code execution producing plots, function calling and MCP servers for remote tool invocation, and an ADK-based agent flow — all run and debugged in Collab with working examples.
AI-written summary · about
chapters (11)
- 0:00Workshop introduction
- 2:51Setup and authentication
- 5:07Getting started with AI studio
- 7:36Text generation basics
- 10:28Token management and pricing
- 13:21Working with files
- 25:00Multimodal capabilities
- 30:20Structured outputs
- 35:15Function calling and agents
- 40:20Native tools integration
- 43:48Advanced agentic patterns
related talks
18mIntroduction to Gemini APIs and AI Studio
15mBuilding with the Gemini API and AI Studio
39mBuild the new generation of AI Agents
01h 01mBuilding Multimodal Apps with Gemini 2.0 and Gemini SDK
08mAI-Powered transformation: Driving innovation and reshaping organizations
11mapproach to generative AI
49mAbracadabra! Bring Your Ideas to Life with Google AI Studio
37mBuild agents with Gemini API