Gemini Enterprise Agent Platform provides a full suite of capabilities for the complete
agentic development lifecycle, to help agent developers and enterprises Build,
Scale, Govern, and Optimize their agentic applications.

Governance provides the framework for discovering, securing, and auditing AI
agents and their underlying infrastructure at scale---both in Google Cloud and on
Kubernetes clusters outside of Google Cloud using
[Agent Gateway for
cross-cloud](https://docs.cloud.google.com/gemini-enterprise-agent-platform/agents/governance/agent-gateway-cross-cloud/overview)
(Limited Preview). As organizations deploy complex agentic workflows, the Govern
suite of capabilities serves as the centralized command center for
administrators and security teams to maintain oversight.
[![Agent Platform governance ecosystem.](https://docs.cloud.google.com/static/gemini-enterprise-agent-platform/images/geap-architecture.png)](https://docs.cloud.google.com/static/gemini-enterprise-agent-platform/images/geap-architecture.png) Agent Platform governance ecosystem (click to enlarge).

## Core governance components

The following Agent Platform components work together to provide a
unified agent governance architecture:

- **[Agent Identity](https://docs.cloud.google.com/gemini-enterprise-agent-platform/govern/agent-identity-overview.md.txt) (Who made the
  request?)**: Assigns a unique, secure ID (a SPIFFE ID) to each agent. This
  identity acts as the agent's digital signature for authentication, access
  control, and auditing.

  Agent identities are secured by default with Context-Aware Access which
  enforces end-to-end cryptographic authentication by using
  [mTLS](https://docs.cloud.google.com/access-context-manager/docs/caa-agent-security.md.txt#mtls) and
  [DPoP](https://docs.cloud.google.com/access-context-manager/docs/caa-agent-security.md.txt#dpop).
- **[Agent Registry](https://docs.cloud.google.com/gemini-enterprise-agent-platform/govern/agent-registry.md.txt) (What
  destinations are approved?)**: Acts as the central directory for all approved
  agents, tools, Model Context Protocol (MCP) servers, and endpoints (such as
  essential Google Cloud APIs) in your organization.
  Agent Gateway uses this directory to check permissions before
  allowing connections.

- **[Policies](https://docs.cloud.google.com/gemini-enterprise-agent-platform/govern/policies/overview-uap.md.txt) (What actions are
  permitted?)**: Lets you implement rich sets of agentic security and governance
  policies that control which agents can reach specific resources and what
  content is allowed to pass through:

  - **[IAM Unified Access
    Policies](https://docs.cloud.google.com/gemini-enterprise-agent-platform/govern/policies/iam-overview-uap)**: Access rules that link an agent's identity to approved tools and endpoints in Agent Registry. By default, all connections are blocked unless an explicit IAM policy grants access.
  - **[Model Armor](https://docs.cloud.google.com/gemini-enterprise-agent-platform/govern/configure-model-armor.md.txt)**: Content security filters attached to gateways. Model Armor scans user prompts and tool responses in real time to block prompt injection attacks, sensitive data leaks, and harmful content.
  - **[Semantic governance
    policies](https://docs.cloud.google.com/gemini-enterprise-agent-platform/govern/policies/semantic-governance-overview)**: Rules written in plain language that control how agents use tools. They enforce business rules at runtime to prevent agents from taking unintended actions, such as running unsafe combinations of tools.
  - **[Token management
    policies](https://docs.cloud.google.com/gemini-enterprise-agent-platform/govern/policies/token-management-overview)**: Policies that monitor and attribute large language model (LLM) token usage, and enforce shared token budgets across your agents and applications to prevent runaway token consumption and unexpected cost spikes.
  - **[Custom authorization
    engines](https://docs.cloud.google.com/gemini-enterprise-agent-platform/govern/gateways/delegate-authorization)**: Custom authorization extensions that let you delegate authorization decisions to third-party systems by using Service Extensions.

  Internally, all of these policy types are enforced by using [authorization
  policies](https://docs.cloud.google.com/gemini-enterprise-agent-platform/govern/gateways/delegate-authorization) or [extension
  bindings](https://docs.cloud.google.com/gemini-enterprise-agent-platform/govern/gateways/extension-bindings-overview) managed
  through Service Extensions.

  > [!WARNING]
  > Support for token management policies and extension bindings is coming soon. Features and timing are subject to change. To request early access, [sign up here for early
  > preview access](https://docs.google.com/forms/d/e/1FAIpQLSeUpnNRtYQjLRblii-KoUbJJ7DjEV6fvQAfO21IAXgVSqFjpw/viewform).

- **[Agent Gateway](https://docs.cloud.google.com/gemini-enterprise-agent-platform/govern/gateways/agent-gateway-overview.md.txt)
  (Where are policies enforced?)** : Serves as the main entry and exit point for
  network traffic between clients-to-agents and agents-to-anywhere, and applies
  security and governance policies to all traffic passing through the gateway.
  To learn more, see [How Agent Gateway enforces
  policies](https://docs.cloud.google.com/gemini-enterprise-agent-platform/govern/gateways/agent-gateway-overview#how-policies-are-enforced).
  You can also extend governance to Kubernetes clusters outside of
  Google Cloud by using [Agent Gateway for
  cross-cloud](https://docs.cloud.google.com/gemini-enterprise-agent-platform/agents/governance/agent-gateway-cross-cloud/overview)
  (Limited Preview).

- **[Agent observability](https://docs.cloud.google.com/gemini-enterprise-agent-platform/optimize/observability/overview.md.txt)**:
  Agent Gateway generates observability telemetry for all agent
  interactions at the network layer and exports it to Agent Observability to
  provide you with a comprehensive understanding of agent actions.

## Recommended order of configuration

To ensure a smooth deployment process, we recommend that you follow this
sequence when setting up a governed Agent Platform environment:

1. **Provision Agent Identities** : Provision workload identities (SPIFFE IDs)
   for your agents. For instructions, see [Agent identities](https://docs.cloud.google.com/gemini-enterprise-agent-platform/govern/agent-identity-overview.md.txt).

2. **Register destinations in Agent Registry** : Register target
   tools, MCP servers, endpoints, and agents in Agent Registry. For
   instructions, see [Agent Registry](https://docs.cloud.google.com/gemini-enterprise-agent-platform/govern/agent-registry.md.txt).

3. **Configure IAM policies** : Define IAM access
   policies that grant agent identities (SPIFFE IDs) access to essential
   platform APIs and your registered destinations. For instructions, see
   [Configure IAM access policies](https://docs.cloud.google.com/gemini-enterprise-agent-platform/govern/policies/configure-iam-policies-uap.md.txt).

   > [!TIP]
   > **Tip:** For testing in audit mode, select **Audit-only** in the Google Cloud console or set `iamEnforcementMode: "DRY_RUN"` in the authorization extension `metadata` block to log evaluations without blocking access. To enable active enforcement, select **Enforce policies** in the Google Cloud console (which writes `iamEnforcementMode: "ENFORCED"` when creating a gateway, or removes `iamEnforcementMode` when updating an existing gateway), or remove `iamEnforcementMode` in your extension configuration.

4. **Configure Model Armor templates** : Set up content
   security templates to inspect prompt payloads and tool responses for prompt
   injections, jailbreaks, and sensitive data leaks. For instructions, see
   [Configure Model Armor](https://docs.cloud.google.com/gemini-enterprise-agent-platform/govern/configure-model-armor.md.txt).

   > [!TIP]
   > **Tip:** For testing in audit mode, set `enforcement_type: "INSPECT_ONLY"` in the authorization extension `metadata` block to log findings without blocking requests. Set `enforcement_type: "INSPECT_AND_BLOCK"` to start active enforcement.

5. **Configure Semantic governance policies** : Define natural
   language constraints that regulate tool usage and prevent unsafe tool
   combinations at runtime. For instructions, see [Configure Semantic governance
   policies](https://docs.cloud.google.com/gemini-enterprise-agent-platform/govern/policies/configure-semantic-governance).

   > [!TIP]
   > **Tip:** For testing in audit mode, you can set `sgpEnforcementMode: "DRY_RUN"` in the authorization extension `metadata` block to evaluate constraints in log-only mode. Remove the `sgpEnforcementMode` parameter (or set it to `"ENFORCE"`) to enforce natural language rules at runtime.

6. **Deploy Agent Gateway and monitor traffic** : Deploy
   Agent Gateway to begin intercepting traffic. If you enabled
   any of the access control mechanisms in audit mode, query Cloud Logging to
   generate a consolidated "would have been blocked" report and confirm that
   access is being evaluated as expected before transitioning your policies to
   active enforcement. For instructions, see [Set up
   Agent Gateway](https://docs.cloud.google.com/gemini-enterprise-agent-platform/govern/gateways/set-up-agent-gateway)
   and [Audit dry-run policy violations across
   controls](https://docs.cloud.google.com/gemini-enterprise-agent-platform/govern/policies/dry-run-report).

## Agent Registry, safety, and sharing

Overview

### [Agent Registry](https://docs.cloud.google.com/gemini-enterprise-agent-platform/govern/agent-registry.md.txt)


Agent Registry is a centralized catalog that lets you store, discover, and govern servers, tools, and AI agents in Google Cloud.

Overview

### [Agent Identity](https://docs.cloud.google.com/gemini-enterprise-agent-platform/govern/agent-identity-overview.md.txt)


Agent identity allows agents to securely authenticate to cloud resources, endpoints, and other agents, acting as themselves or on behalf of the end user.

Guide

### [Share an agent](https://docs.cloud.google.com/gemini-enterprise-agent-platform/govern/share-agent.md.txt)


Learn how to share an agent.

Guide

### [Safety](https://docs.cloud.google.com/gemini-enterprise-agent-platform/govern/safety.md.txt)


Ensure your agents are safe and reliable using Google Agent Platform.

Guide

### [View agent relationships](https://docs.cloud.google.com/gemini-enterprise-agent-platform/govern/topology.md.txt)


View real-time relationships and traffic flows across all agents and MCP servers known to Agent Registry.

## Agent Gateway for cross-cloud

Overview

### [Agent Gateway for cross-cloud overview](https://docs.cloud.google.com/gemini-enterprise-agent-platform/agents/governance/agent-gateway-cross-cloud/overview.md.txt)


Extend Agent Platform governance, identity, and safety policies to Kubernetes clusters outside of Google Cloud.

Guide

### [Set up Agent Gateway for cross-cloud](https://docs.cloud.google.com/gemini-enterprise-agent-platform/agents/governance/agent-gateway-cross-cloud/setup.md.txt)


Learn how to deploy Agent Gateway for cross-cloud on standard Kubernetes clusters.

## Policies

Guide

### [Configure semantic governance policies](https://docs.cloud.google.com/gemini-enterprise-agent-platform/govern/policies/configure-semantic-governance.md.txt)


Semantic governance policies add an additional security layer to ensure agent actions match user intent and organizational constraints.

Overview

### [Policies overview](https://docs.cloud.google.com/gemini-enterprise-agent-platform/govern/policies/overview.md.txt)


Get an overview of policies in Google Agent Platform.

## Agent Gateway

Guide

### [Route Agent Runtime traffic through Agent Gateway](https://docs.cloud.google.com/gemini-enterprise-agent-platform/scale/runtime/agent-gateway-runtime-deploy.md.txt)


Learn how to route Agent Runtime traffic through Agent Gateway for secure and governed connectivity.

Codelab

### [Codelab: Govern agentic workloads with Agent Platform](https://codelabs.developers.google.com/cloudnet-agent-gateway)


Learn how to govern agentic workloads with Agent Gateway on Gemini Enterprise Agent Platform.

Codelab

### [Codelab: Agent Gateway egress from Agent Runtime to Google MCP servers](https://codelabs.developers.google.com/agw-cuj-arun-egress-gmcp)


Learn about Agent Gateway egress governance for AI agents accessing Google Cloud Model Context Protocol (MCP) servers.

Codelab

### [Codelab: Agent Gateway egress from Agent Runtime to external MCP servers](https://codelabs.developers.google.com/agw-cuj-arun-egress-emcp)


Learn about Agent Gateway egress governance for AI agents accessing external MCP servers.

Codelab

### [Codelab: Agent Gateway egress from Agent Runtime to VPC networks](https://codelabs.developers.google.com/agw-cuj-arun-egress-vpc)


Learn about Agent Gateway egress governance for AI agents accessing destinations in a VPC network.

Codelab

### [Codelab: Agent Gateway governance with cross-project Agent Runtime](https://codelabs.developers.google.com/agw-multiproject)


Learn about Agent Gateway governance for cross-project Agent Runtime agents.

Codelab

### [Codelab: Agent Gateway egress from Gemini Enterprise to custom MCP servers](https://codelabs.developers.google.com/agw-ge-custom-mcp-egress-vpc-registry)


Learn about setting up private Agent Gateway egress governance for Gemini Enterprise.

Overview

### [Agent Gateway overview](https://docs.cloud.google.com/gemini-enterprise-agent-platform/govern/gateways/agent-gateway-overview.md.txt)


Get an overview of Agent Gateway.

Guide

### [Delegate authorization for Agent Gateway](https://docs.cloud.google.com/gemini-enterprise-agent-platform/govern/gateways/delegate-authorization.md.txt)


Learn how to delegate authorization for Agent Gateway to IAP, Model Armor, or your own custom authorization service.

Guide

### [Monitor Agent Gateway](https://docs.cloud.google.com/gemini-enterprise-agent-platform/govern/gateways/monitor-agent-gateway.md.txt)


Learn how to monitor Agent Gateway.

Guide

### [Set up an Agent Gateway](https://docs.cloud.google.com/gemini-enterprise-agent-platform/govern/gateways/set-up-agent-gateway.md.txt)


Learn how to set up an Agent Gateway.

Troubleshooting

### [Troubleshoot Agent Gateway](https://docs.cloud.google.com/gemini-enterprise-agent-platform/troubleshooting/troubleshoot-agent-gateway.md.txt)


Learn how to troubleshoot Agent Gateway connectivity.

Guide

### [Route Gemini Enterprise traffic through Agent Gateway](https://docs.cloud.google.com/gemini-enterprise-agent-platform/govern/gateways/agent-gateway-ge-deploy.md.txt)


Learn how to route Gemini Enterprise traffic through Agent Gateway.

## Security

Codelab

### [Codelab: Secure cross-cloud agentic AI applications](https://codelabs.developers.google.com/next26/aiinfra-learning-pod/screen1-securing-cross-cloud-agentic)


Learn how to secure your agentic applications in the Securing Cross-Cloud Agentic AI Applications codelab.

Resource

### [Whitepaper: Building secure multi-agent systems on Google Cloud](https://goo.gle/agent-security-enterprise)


Learn how to build secure multi-agent architectures on Google Cloud's Gemini Enterprise Agent Platform.

Guide

### [View security findings](https://docs.cloud.google.com/gemini-enterprise-agent-platform/govern/view-security-findings.md.txt)


Learn how to view security findings.

Guide

### [Configure Model Armor on a gateway](https://docs.cloud.google.com/gemini-enterprise-agent-platform/govern/configure-model-armor.md.txt)


Learn how to configure Model Armor on a gateway.

Guide

### [Monitor content security](https://docs.cloud.google.com/gemini-enterprise-agent-platform/govern/monitor-content-security.md.txt)


Learn how to monitor content security.

Guide

### [View Model Armor spans](https://docs.cloud.google.com/gemini-enterprise-agent-platform/govern/view-model-armor-spans.md.txt)


Learn how to view Model Armor spans.