End-to-end example of a long-running AI agent that pauses, resumes, and never loses context.

It simulates the onboarding of a new employee.

Here are 3 patterns you’ll learn from this example:

1. How to implement a durable state machine that persists over time.

2. How to build event-driven agents that stay dormant until they receive a webhook event. No active polling or blocked threads.

3. How to build multi-agent delegation instead of relying on a single agent to do everything.

You can deploy this example in the Gemini Enterprise Platform:

https://fandf.co/4nWzg2Q

You’ll find a link to the GitHub repository with the complete source code and a complete explanation of this example in this article:

https://fandf.co/4uVhmPZ

Thanks to the Google Cloud AI team for partnering with me on this post.

Gemini Enterprise Agent Platform (formerly Vertex AI)

Source: https://cloud.google.com/products/gemini-enterprise-agent-platform?utm_source=fnf&utm_medium=x&utm_campaign=google-cloud-june&utm_term=santiago-valdarrama&utm_content=agent-garden

Innovate, build, and deploy enterprise ready agents

Gemini Enterprise Agent Platform is Google Cloud’s comprehensive platform for developers to build, scale, govern and optimize agents. It’s a single destination for technical teams to build agents that can transform enterprise applications and workflows into powerful agentic systems.

New customers get up to $300 in free creditsto try Agent Platform and other Google Cloud products.

Features

Build, scale, govern and optimize enterprise grade AI agents

Agent Platformis our open and comprehensive platform that empowers businesses to rapidly build, scale, govern and optimize enterprise-grade agents grounded in your enterprise data. It provides the full-stack foundation and extensive developer choice you need to transform your applications and workflows into powerful agentic systems at global scale.

Agent-powered development and workflows

Now available through Agent Platform, Google Antigravity provides a centralized app to steer, customize, and orchestrate agents. You can deploy multiple agents to simultaneously execute entire workflows like product launches—automating the code generation for your website, on-brand asset creation, and customer email production.DownloadAntigravity and log in to thedesktop applicationorAntigravity CLIusing your standard Google Cloud credentials.

200+ Google and third-party AI models and tools

Choose from Google’s latest multimodal models like Gemini 3.5, third-party models like Anthropic’s Claude Model Family, and open models likeGemmainModel Garden. You can also customize models to your use case with a variety oftuning options.

OurModel Evaluation serviceprovides enterprise-grade tools for objective, data-driven assessment of generative AI models.

Open and integrated AI platform

Data scientists can move faster with Agent Platform tools for training, tuning, and deploying ML models.

Agent platformnotebooks, including your choice of Colab Enterprise or Workbench, are natively integrated withBigQueryproviding a single surface across all data and AI workloads.

Agent platformTrainingandPredictionhelp you reduce training time and deploy models to production easily with your choice of open source frameworks and optimizedAI infrastructure.

MLOps for predictive and generative AI

Agent Platform provides purpose-builtMLOps toolsfor data scientists and ML engineers to automate, standardize, and manage ML projects.

Modular tools help you collaborate across teams and improve models throughout the entire development lifecycle—identify the best model for a use case withModel Evaluation, orchestrate workflows withPipelines, manage any model withModel Registryserve, share, and reuse ML features withFeature Store, andmonitormodels for input skew and drift.

How It Works

Agent Platform provides several options for agent building, model training and deployment: - Agent Platformenables you to build, scale, govern and optimize enterprise ready agents in one unified platform - Agent Studiogives you access to large generative AI models, includingGemini 3, so you can evaluate, tune, and deploy them for use in your AI-powered applications - Model Gardenlets you discover, test, customize, and deploy in Agent Platform and select open-source (OSS) models and assets - Custom traininggives you complete control over the training process, including using your preferred ML framework, writing your own training code, and choosing hyperparameter tuning options

Common Uses

Build and deploy AI agents

Tutorials, quickstarts, & labs

Tutorials, quickstarts, & labs

Build with Gemini models

Tutorials, quickstarts, & labs

Code sample

Tutorials, quickstarts, & labs

Code sample

Extract, summarize, and classify data

Tutorials, quickstarts, & labs

Tutorials, quickstarts, & labs

Deploy a model for production use

Tutorials, quickstarts, & labs

Tutorials, quickstarts, & labs

Train custom Models

Tutorials, quickstarts, & labs

Tutorials, quickstarts, & labs

Generate a solution

What problem are you trying to solve?

What you’ll get:

Step-by-step guide

Reference architecture

Available pre-built solutions

Pricing

How Agent Platform pricing worksPay for Agent Platform tools, storage, compute and Cloud resources used. New customers get $300 free credits to try Agent Platform and Google Cloud products.Tools and usageDescriptionPriceGenerative AI

Imagen model for image generation

Based on image input, character input, or custom trainingpricing.

Starting at

$0.0001

Text, chat, and code generation

Based on every 1,000 characters of input (prompt) and every 1,000 characters of output (response).

Starting at

$0.0001

per 1,000 characters

Custom-trained models

Custom model training

Based on machine type used per hour, region, and any accelerators used. Get an estimate usingsalesor ourpricing calculator.

Contact sales

Agent Platform notebooks

Compute and storage resources

Based on the same rates asCompute EngineandCloud Storage.

Refer to products

Management fees

In addition to the above resource usage, management fees apply based on region, instances, notebooks, and managed notebooks used.View details.

Refer to details

Agent Platform Pipelines

Execution and additional fees

Based on execution charge, resources used, and any additional service fees.

Starting at

$0.03

per pipeline run

Agent Platform Vector Search

Serving and building costs

Based on the size of your data, the amount of queries per second (QPS) you want to run, and the number of nodes you use.View example.

Refer to example

How Agent Platform pricing works

Pay for Agent Platform tools, storage, compute and Cloud resources used. New customers get $300 free credits to try Agent Platform and Google Cloud products.

Description

Imagen model for image generation

Based on image input, character input, or custom trainingpricing.

Price

Text, chat, and code generation

Based on every 1,000 characters of input (prompt) and every 1,000 characters of output (response).

Description

Starting at

$0.0001

per 1,000 characters

Description

Custom model training

Based on machine type used per hour, region, and any accelerators used. Get an estimate usingsalesor ourpricing calculator.

Price

Contact sales

Description

Price

Refer to products

Management fees

In addition to the above resource usage, management fees apply based on region, instances, notebooks, and managed notebooks used.View details.

Description

Refer to details

Description

Execution and additional fees

Based on execution charge, resources used, and any additional service fees.

Price

Starting at

$0.03

per pipeline run

Agent Platform Vector Search

Description

Serving and building costs

Based on the size of your data, the amount of queries per second (QPS) you want to run, and the number of nodes you use.View example.

Price

Refer to example

Pricing calculator

Estimate your Agent Platform costs, including region-specific pricing and fees.

Custom quote

Connect with our sales team to get a custom quote for your organization.

Start your proof of concept

New customers get up to $300 in free credits to try Agent Platform and other Google Cloud products

Have a large project?

Browse, customize, and deploy machine learning models

Learn how to set up a Agent Platform project environment

Get started with notebooks for machine learning

Business Case

Unlock the full potential of gen AI

“The accuracy of Google Cloud’s generative AI solution and practicality of the Agent Platform gives us the confidence we needed to implement this cutting-edge technology into the heart of our business and achieve our long-term goal of a zero-minute response time.”

Abdol Moabery, CEO of GA Telesis

Google named a Leader in the 2025 IDC MarketScape for Worldwide GenAI Life-Cycle Foundation Model Software.Download the report

Google Named a Leader in the Gartner Magic Quadrant™ for AI Application Development Platforms, Q4 2025.Read the report

Google named a leader in the Forrester Wave™: AI/ML Platforms, Q3 2024.Read the report