GCP Agent Platform in 6 hours - Gen AI, Gemini, Agentic AI

Name: GCP Agent Platform in 6 hours - Gen AI, Gemini, Agentic AI
Rating: 4.4 (6 reviews)

GCP Vertex AI - Practical Based Learning into Google Vertex AI, Code with Gemini, AutoML, Custom Training, AI Agents

Created byK8s Point - Training House for GCP, AI & Kubernetes

Last updated 6/2026

English

What you'll learn

Learn Everything you need to know about Vertex AI with Practical Example
Design, build, and deploy AI Agents using Google ADK and Agent Engine
Understand Google’s AI model ecosystem (Gemini, Imagen, Veo, and more)
Use Vertex AI Model Garden and Vertex AI Studio effectively
Authenticate and access Google Models using API keys, service accounts, and ADC
Learn How to access a Gemini Model from Python Code
Work with Vertex AI notebooks, Colab Enterprise, and Jupyterlab Workbench
Understand Vertex AI training options including AutoML and custom training
Build, deploy, and test ML models on Vertex AI
Create embeddings and vector indexes for semantic search
Implement RAG pipelines using RAG Engine and Vertex AI Search
Run agents locally and deploy them on Google Cloud

Course content

7 sections • 65 lectures • 5h 47m total length

Vertex AI Introduction5:28
Vertex AI Console Walkthrough7:24
Course Categories1:39

Google Model Family - Gemini, Imagen, Veo etc7:30
Vertex AI Model Garden4:45
Vertex AI Studio - Introduction8:56
Vertex AI Studio - Walk Through5:31
Explore Vertex AI Studio in this walk-through, generating images, video, music, and code with Nano Banana Pro, and learn to use live API with Gemini to build AI apps.
Vertex AI Studio - AI Apps4:21
Vertex AI Studio - API Key3:32
Create and copy an api key in Vertex AI Studio to enable code use in your local development environment, then paste the key into your program for the next lecture.
Access a Model from Python Program8:28
Access a Model with Service Account9:41
Access a model with Application Default Login7:01

Notebook Options - Choices2:03
Colab Enterprise - Introduction5:16
Colab Enterprise - Runtime & Templates5:59
Explore how to create and manage Colab Enterprise runtimes using templates, selecting machine types, idle time, and networking, then connect, run code, and schedule recurring executions.
Workbench - Create Instance6:06
Learn to create a Workbench instance, attach a notebook, and configure runtimes with machine types, GPUs, JupyterLab versions, and a service account for shared access.
Workbench - Options7:49
Workbench - More Details1:51

GCP Services for Machine Learning6:17
GCP Product Comparison for Machine Learning6:50
Training Option under Vertex AI1:38
Use Vertex AI to train, develop, and deploy models. Link data to a GCS bucket or BigQuery, train with AutoML or custom training, and deploy via endpoints from model registry.
Dataset - An Introduction3:06
Dataset Used in this Example0:01
AutoML- Understand the Input Data1:09
AutoML - Import Data into Vertex AI Dataset4:15
AutoML - Train Your Model6:19
AutoML - Deploy Your Model8:33
AutoML - Test Your Model6:06
Custom Training - Introduction5:28
Dataset Used in this Section0:01
Programs Used in this Section0:01
Custom Training - Dataset2:19
Perform custom training with a pre-built container using tensorflow on a 10,000-row sentiment CSV from kegger.com, uploaded to a GCS bucket, to build a classifier that predicts sentiment levels.
Custom Training - Understand the Project Structure8:48
Custom Training - Train Your Model4:14
Custom Training - Import Your Model5:03
Custom Training - Deploy Your Model2:24
Custom Training - Test Your Model3:04

Introduction to Vector Space & Embedding9:25
Vector Search, RAG Engine & Vertex AI Search- Differences5:22
Create Embedding6:37
Create Index and Index Endpoint and Deploy4:26
Create a 768-dimension embedding index with cosine distance, set an index ID, choose batch or stream updates and an approximate neighbor count, then deploy a public endpoint in London.
Query Your Vector Search5:18
Introduction to RAG Engine2:52
Explore how retrieval augmented generation grounds an llm with private data by converting it into vector space embeddings for semantic search, enabling llm-powered private data insights.
Creating Corpus and Configuring RAG Engine4:36
Configure a RegEngine in basic tier, create a corpus from Google Cloud Storage, attach two text files about global warming, and generate embeddings for vector search.
Querying the RAG Engine with the Power of LLM6:06
Introduction to Vertex AI Search2:52
Create your Datastore5:23
Implement a Custom Search using Vertex AI Search8:04
Create and configure a custom search app with Vertex AI Search, linking multiple datastores, testing via curl, and integrating with websites through a widget or application programming interface.
Implement Agentspace / Gemini Enterprise using Vertex AI Search8:27

Introduction to AI Agents8:04
Introduction to Google ADK5:11
Explore google adk as an open-source, cloud-integrated framework for building ai agents. It offers multimodal outputs, memory handling, multistep reasoning, and tool integrations within a multi-agent system.
GCP Console Options for ADK Agent3:06
Explore the GCP Vertex AI console options for ADK agents, focusing on four direct development paths: agent designer, agent garden, agent engine, and advanced MCP integration.
Setting up the Agent Project8:26
Authentication Option - Create Gemini API Key4:48
Running your Agent Locally with Different Options6:00
Authentication Option - Vertex AI5:49
Deploy Your Agent to Agent Engine7:50
Test Your Agent8:23
Agent Designer5:15
Agent Garden5:07
Using Tools with ADK Agent7:00
Understanding Multi-Agent System6:38
A multi-agent system coordinates a root agent with sub-agents for hotel, flight, and itinerary, and uses A2A protocols to connect to external services.
Multi-Agent System - Demo14:40
What Next on Agents2:29

Requirements

Very Basic of Python
GCP Basics

Description

A fast, hands-on guide for developers to build Generative AI, RAG pipelines, and AI Agents using Google Vertex AI.

Google Vertex AI has become the backbone for building production-grade Generative AI applications using Gemini models, vector search, RAG engines, and agentic workflows.

This crash course is designed to take you from zero to building real GenAI systems on Vertex AI.

In around 6 hours, you’ll gain practical, working knowledge of:

Gemini and Google’s model ecosystem
Google GenAI SDK with Python Code
Vertex AI Studio and Model Garden
Notebooks and development environments
Core ML concepts on Vertex AI
Retrieval-Augmented Generation (RAG)
AI Agents using Google ADK and Agent Engine
Multi Agent System with ADK
Colab Enterprise
Jupyterlab Workbench
Train with AutoML
Custom Training
Deploy with Vertex AI Endpoints
Model Registry

By the end of this course, you will be able to:

Understand Google’s AI model ecosystem (Gemini, Imagen, Veo, and more)
Use Vertex AI Model Garden and Vertex AI Studio effectively
Authenticate and access models using API keys, service accounts, and ADC
Work with Vertex AI notebooks, Colab Enterprise, and Workbench
Understand Vertex AI training options including AutoML and custom training
Build, deploy, and test ML models on Vertex AI
Create embeddings and vector indexes for semantic search
Implement RAG pipelines using RAG Engine and Vertex AI Search
Design, build, and deploy AI Agents using Google ADK and Agent Engine
Run agents locally and deploy them on Google Cloud

Who this course is for:

Anyone wants to Learn Vertex AI
All GCP Engineers - The Natural Next Step

GCP Agent Platform in 6 hours - Gen AI, Gemini, Agentic AI

What you'll learn

Explore related topics

Course content

Introduction3 lectures • 15min

Generative AI & Gemini9 lectures • 1hr

Notebook Options6 lectures • 29min

Machine Learning19 lectures • 1hr 16min

Retrieval-Augmented Generation (RAG) in Vertex AI12 lectures • 1hr 9min

AI Agents15 lectures • 1hr 39min

What Next!1 lecture • 1min

Requirements

Description

Who this course is for: