hands-on lab

Introduction to Agentic AI on Google Cloud

Difficulty: Beginner
Duration: Up to 1 hour and 30 minutes
Students: 2
Get guided in a real environmentPractice with a step-by-step scenario in a real, provisioned environment.
Learn and validateUse validations to check your solutions every step of the way.
See resultsTrack your knowledge and monitor your progress.

Description

Agentic AI goes beyond single-turn chat: it reasons toward a goal, decides when to use tools, and grounds answers in external evidence rather than guessing. You can apply agentic patterns with or without a formal “agent” construct.

In this hands-on lab, you’ll progress from model-only prompting in Vertex AI Studio to configuring your first Vertex AI Agent in Agent Builder. You’ll define agent scope and instructions, enable a basic built-in grounding capability (e.g., Google Search tool) to demonstrate Reason → Act → Observe, and use the Preview experience to see how tool use changes behavior.

Learning objectives

Upon completion of this beginner-level course, you will be able to:

  • Explain how agentic AI differs from a traditional chatbot and single-turn LLM prompts, including the roles of reasoning, grounding, and action in intelligent systems.

  • Navigate the Vertex AI ecosystem (Vertex AI Studio, Agent Builder, and related capabilities) and describe how these components integrate within Google Cloud.

  • Create and configure a first agent using Vertex AI Agent Builder (Agent Designer), including defining agent identity, instructions, scope boundaries, and basic tool/grounding behavior.

  • Apply best practices for designing and scoping a first agent (clear purpose, bounded behavior, observable outcomes) and understand how templates/connectors accelerate future development.

Intended audience

  • Cloud Solution Architects

  • Platform / DevOps Engineers exploring AI capabilities on GCP

  • Developers and Technical Consultants new to Vertex AI

  • Innovation, R&D, and AI Enablement teams evaluating agentic approaches

  • Technical Program Managers supporting AI platform adoption

Prerequisites

Basic familiarity with the Google Cloud Console (projects, navigation, permissions)

General understanding of what an LLM is (no ML training required)

Environment before

Environment after

Covered topics

Hands-on Lab UUID

Lab steps

0 of 6 steps completed.Use arrow keys to navigate between steps. Press Enter to go to a step if available.
  1. Signing In to the Google Cloud Console
  2. Using a baseline Large Language Model in Vertex AI Studio
  3. Creating your first agent in Designer
  4. Adding an action tool to the Agent
  5. Exploring templates and connectors in the Agent Garden
  6. Comparing Studio AI and Agentic AI prompts and responses