Skip to content
hands-on lab

Building Data-Aware Agents with Agent Search on Gemini Enterprise Agent Platform

Difficulty: Beginner
Duration: Up to 1 hour
Students: 10
Start lab
On average, students complete this lab in1h
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.
About
Author

Description

Agent Search on Gemini Enterprise Agent Platform enables developers to build data-aware AI agents that can understand and interact with large datasets. This process, known as "grounding," involves connecting AI agents to relevant data sources, allowing them to provide more accurate and contextually relevant responses.

In this lab, you will learn how to create a Google Conversational Agent and an Agent Search datastore, and how to enable data-aware capabilities in an AI agent using Agent Search.

Learning objectives

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

  • Create a Google Conversational Agent
  • Create an Agent Search datastore
  • Enable data-aware capabilities in an AI agent using Agent Search

Intended audience

  • AI Developers
  • Data Engineers

Prerequisites

Familiarity with the following will be beneficial but is not required:

  • Agent Search on Gemini Enterprise Agent Platform
  • Google Cloud Storage

The following content can be used to fulfill the prerequisites:

Updates

June 18th, 2026 - Updated lab to reflect the incorporating of Vertex AI into the new Gemini Enterprise Agent Platform

Environment before

Environment after

Covered topics

Artificial Intelligence
Google Cloud Platform
Artificial Intelligence for Google
Hands-on Lab UUID

Lab steps

0 of 4 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. Creating a Google Conversational Agent
  3. Creating an Agent Search Datastore
  4. Evaluating the Grounded Agent with Agent Search Datastore

Lab Rules