Vertex AI Agent Engine overview

Stay organized with collections Save and categorize content based on your preferences.

Vertex AI Agent Engine (formerly known as LangChain on Vertex AI or Vertex AI Reasoning Engine) is a Google Cloud platform that enables developers to deploy, manage, and scale AI agents in production. Agent Engine handles the infrastructure to scale agents in production so you can focus on creating applications. Vertex AI Agent Engine offers the following features:

• Managed runtime:

  • Deploy and scale agents with a managed runtime and end-to-end management capabilities.
  • Use security features including VPC-SC compliance and configuration of authentication and IAM.
  • Access models and tools such as function calling.
  • Deploy agents built using different Python frameworks:

• Quality and evaluation:

  • Ensure agent quality with the integrated Gen AI Evaluation service.
  • Improve agent performance with Example Store.
  • Optimize agents with Gemini model training runs.

• Manage context:

  • Sessions: Agent Engine Sessions lets you store individual interactions between users and agents, providing definitive sources for conversation context.

  • Example Store: Example Store lets you store and dynamically retrieve few-shot examples.

• Monitoring:

  • Understand agent behavior with Google Cloud Trace (supporting OpenTelemetry), Cloud Monitoring, and Cloud Logging.

Vertex AI Agent Engine is part of Vertex AI Agent Builder, a suite of features for discovering, building, and deploying AI agents.

Create and deploy on Vertex AI Agent Engine

Note: For a streamlined, IDE-based development and deployment experience with Vertex AI Agent Engine, consider the agent-starter-pack. It provides ready-to-use templates, a built-in UI for experimentation, and simplifies deployment, operations, evaluation, customization, and observability.

The workflow for building an agent on Vertex AI Agent Engine is:

The steps are illustrated by the following diagram:

Supported frameworks

The following table describes the level of support Vertex AI Agent Engine provides for various agent frameworks:

Deploy in production with Agent Starter Pack

The Agent Starter Pack is a collection of production-ready generative AI agent templates built for Vertex AI Agent Engine. The Agent Starter Pack provides the following:

• Pre-built agent templates: ReAct, RAG, multi-agent, and other templates.
• Interactive playground: Test and interact with your agent.
• Automated infrastructure: Uses Terraform for streamlined resource management.
• CI/CD pipelines: Automated deployment workflows leveraging Cloud Build.
• Observability: Built-in support for Cloud Trace and Cloud Logging.

To get started, see the Quickstart.

Use cases

To learn about Vertex AI Agent Engine with end-to-end examples, see the following resources:

Enterprise security

Vertex AI Agent Engine supports VPC Service Controls to strengthen data security and mitigate the risks of data exfiltration. When VPC Service Controls is configured, the deployed agent retains secure access to Google APIs and services, such as BigQuery API, Cloud SQL Admin API, and Vertex AI API, ensuring seamless operation within your defined perimeter. Critically, VPC Service Controls effectively blocks all public internet access, confining data movement to your authorized network boundaries and significantly enhancing your enterprise security posture.

Supported regions

Vertex AI Agent Engine is supported in the following regions:

For Agent Engine Sessions, the following regions are supported:

Quota

Pricing

Pricing is based on compute (vCPU hours) and memory (GiB hours) resources used by the agents that are deployed to the Vertex AI Agent Engine managed runtime.

For more information, see pricing.

What's next

• Set up the environment.
• Get support.