Vertex AI Agent Engine (formerly known as LangChain on Vertex AI or Vertex AI Reasoning Engine) is a fully managed Google Cloud service enabling 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 intelligent and impactful applications. Vertex AI Agent Engine offers:
Fully managed: Deploy and scale agents with a managed runtime that provides robust security features including VPC-SC compliance and comprehensive end-to-end management capabilities. Gain CRUD access to multi-agent applications that use Google Cloud Trace (supporting OpenTelemetry) for performance monitoring and tracing. To learn more, see deploy an agent.
Quality and evaluation: Ensure agent quality with the integrated Vertex AI Rapid Evaluation service.
Simplified development: Agent Engine abstracts away low-level tasks such as application server development and configuration of authentication and IAM, allowing you to focus on the unique capabilities of your agent, such as its behavior, tools, and model parameters. Furthermore, your agents can use any of the models and tools, such as function calling, in Vertex AI.
Framework agnostic: Enjoy flexibility when deploying agents that you build using different python frameworks including LangGraph, Langchain, AG2, and CrewAI. If you already have an existing agent, you can adapt it to run on Agent Engine using the custom template in our SDK. Otherwise, you can develop an agent from scratch using one of the framework-specific templates we provide.
Use cases
To learn about Agent Engine with end-to-end examples, see the following resources:
Create and deploy on Agent Engine
Note: For a streamlined, IDE-based development and deployment experience with 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 Agent Engine is:
Steps | Description |
---|---|
1. Set up the environment | Set up your Google project and install the latest version of the Vertex AI SDK for Python. |
2. Develop an agent | Develop an agent that can be deployed on Agent Engine. |
3. Deploy the agent | Deploy the agent on the Agent Engine managed runtime. |
4. Use the agent | Query the agent by sending an API request. |
5. Manage the deployed agent | Manage and delete agents that you have deployed to Agent Engine. |
The steps are illustrated by the following diagram:
Enterprise security
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.
Pricing
Pricing is based on compute (vCPU hours) and memory (GiB hours) resources used by the agents that are deployed to the Agent Engine managed runtime.
Product | SKU ID | Price |
---|---|---|
ReasoningEngine vCPU | 8A55-0B95-B7DC | $0.0994/vCPU-Hr |
ReasoningEngine Memory | 0B45-6103-6EC1 | $0.0105/GiB-Hr |
For more information, see pricing.