From Zero to Agentic AI with Google Gemini & MCP

Topics include:

• Introduction to Google AI, Google AI Studio, and Gemini Models
• Using the Google AI Client for Gemini with Angular: Best Practices
• Leveraging the Gemini API through the Google GenAI SDK
• Advanced Prompt Engineering Techniques (Chain-of-Thought, In-Context Learning)
• Lab: Mastering Prompt Engineering Best Practices
• Utilizing the Gemini API for Multimodal Inputs (Images, Audio, Video, and WebSockets)
• Introduction to Embeddings and Retrieval-Augmented Generation (RAG) with Vector Databases
• Lab: Developing a Gemini-Powered Chatbot
• Exploring Foundational Models: Text, Code, Images, Video, and Voice
• Lab: Creating Avatars with Gemini Nano Banana
• Building an AI Agent with the Model Context Protocol (MCP) SDK
• Lab: Constructing an AI Agent with Tool Access via MCP (Search, Tools, and APIs)
• Developing a Gemini Live Client with Angular (WebRTC, Streaming Voice and Video via WebSockets)
• Advanced Gemini Live Voice Features (Streaming, Half-Cascade, and On-Demand Text-to-Speech)
• Lab: Producing a Multi-Speaker Podcast Using Gemini (like NotebookML)
• Responsible AI Principles

Participant should have:

• Intermediate Angular skills
• Basic knowledge of Node

Duration:

• 2 day
• 9:00 am to 5:00 pm
• 1 hour lunch break included at the hotel's restaurant
• 15 min coffee break every morning and afternoon