> [!WARNING]
>
> **Preview
> --- Agent2Agent (A2A)**
>
>
> This feature is
>
> subject to the "Pre-GA Offerings Terms" in the General Service Terms section of the
> [Service Specific
> Terms](https://docs.cloud.google.com/terms/service-terms#1).
>
> Pre-GA features are available "as is" and might have limited support.
>
> For more information, see the
> [launch stage descriptions](https://cloud.google.com/products/#product-launch-stages).

Cloud Run lets you deploy and scale Agent2Agent
(A2A) agents as Cloud Run services. This architecture helps you run
autonomous multi-agent workflows that collaborate and exchange tasks across
distributed environments.

For an introduction to foundational protocol concepts, see
[Key Concepts in A2A](https://a2a-protocol.org/latest/topics/key-concepts/).

## Relationship of AI Agents and the A2A Protocol

**AI Agents** are software programs that can perceive their environment, make
decisions, and take autonomous actions to achieve specific goals. These agents
are becoming increasingly sophisticated, often leveraging Large Language Models
(LLMs) for complex tasks like reasoning, planning, and natural language
interactions.

As more specialized AI agents are developed, the need for them to communicate
and collaborate becomes essential. The **Agent2Agent (A2A) Protocol** is an open
standard designed to enable seamless and secure communication and
interoperability between AI agents, even if they are built using different
frameworks, by different vendors, or are running on separate servers. A2A allows
agents to work together as peers without exposing their internal state or logic.

The following diagram illustrates the architecture of an A2A Agent system,
showing an A2A Client (user or agent) interacting with the A2A Agent:
![An agent interacting with other agents, hosted on
Cloud Run.](https://docs.cloud.google.com/static/run/docs/images/host-a2a-agents.svg) **Figure 1.**Components of an A2A agents hosted on Cloud Run.

The A2A Agent's core is a serving and orchestration layer, such as
Cloud Run. This layer manages interactions with AI models like
Gemini and Vertex AI, memory storages like AlloyDB and
A2A TaskStore, and external tools through APIs. Clients interact with the agent
by sending requests, such as "Get Agent Card" or "send message," and receive
task updates.

For information about A2A request lifecycle, see the
[A2A Request Lifecycle](https://a2a-protocol.org/latest/topics/what-is-a2a/#a2a-request-lifecycle)
section.

## What's next

- To learn the practical steps for deploying your own A2A agents, see [Build and deploy an A2A agent on Cloud Run](https://docs.cloud.google.com/run/docs/deploy-a2a-agents.md.txt).