The term *agent* can mean different things.
In a *Multi-Agent System* ,
which forms a hierarchical agent tree,
the entire agent tree is referred to as the *agent application*.

An agent application is composed of one or more agents,
where each agent can be either the *root agent* or a *sub-agent*.

A *root agent* (also known as steering agent)
acts as the primary entry point and orchestrator
for the overall agent application.
It typically handles the main interaction with the end-user,
it is responsible for understanding the overall goals,
and it delegates specific tasks to appropriate *sub-agents*.

A *sub-agent* (also known as child agent)
is a more specialized agent designed to handle a specific task,
domain, or capability.
For example, a sub-agent could be tasked with searching a specific database
or analyzing a particular type of data.
Sub-agents promote modularity and reusability in your agent application.

Root agents can invoke sub-agents, and sub-agents can invoke other sub-agents.

![Route and sub-agent diagram](https://docs.cloud.google.com/static/gemini-enterprise-cx/cx-agent-studio/images/root-sub-agent.png)

## Create an agent application and root agent

To create an agent application and root agent:

1. Open the [CX Agent Studio console](https://ces.cloud.google.com).
2. Select your project.
3. Click **Create your first AI agent** or **Create agent**.
4. Provide an agent application name.
5. Click **Create**.
6. Click **Instructions** to add [instructions](https://docs.cloud.google.com/gemini-enterprise-cx/cx-agent-studio/instruction.md.txt) for the root agent.
7. Click **Tools** , then the **+** button to add [tools](https://docs.cloud.google.com/gemini-enterprise-cx/cx-agent-studio/tool.md.txt) for the root agent.

As an alternative,
you can use the dropdown options when creating an agent:

- **Import as new** : Create a new agent by [importing one](https://docs.cloud.google.com/gemini-enterprise-cx/cx-agent-studio/export.md.txt)
- **Create from template** : Create an agent using a [template](https://docs.cloud.google.com/gemini-enterprise-cx/cx-agent-studio/agent.md.txt#template).

## Create a sub-agent

To create a sub-agent:

1. Click the plus sign at the bottom of the root agent.
2. Click **Add sub-agent**.

## Manage agent applications

To manage agent applications for your project:

1. Open the [CX Agent Studio console](https://ces.cloud.google.com).
2. Select your project. The list of agent applications for your project are shown.

For each agent application,
the following information and actions are available:

- Click the agent application name to open the application in the agent builder.
- **Deployed to** column shows the number of channels the application is deployed to.
- **Sessions** column shows the number of sessions in the past 24 hours that use a deployment channel.
- **Escalation** column shows the number of escalations in the past 24 hours that use a deployment channel.
- The latest update time for the agent application is shown.
- You can click the context menu for a particular agent application, then **Import agent** , **Export agent** , or **Delete agent** . For more information, see [Export and import](https://docs.cloud.google.com/gemini-enterprise-cx/cx-agent-studio/export.md.txt).

## Language support

You should design your agents using English,
but agents can automatically detect the language of end-user input,
and they will automatically respond using the same language.
For the list of supported languages,
see the
[languages reference](https://docs.cloud.google.com/gemini-enterprise-cx/cx-agent-studio/reference/language.md.txt).

## Model support

CX Agent Studio uses Gemini foundation models to power generative reasoning, instruction following, and multimodal capabilities. You can select a global model for the entire agent application or override it for specific sub-agents. For step-by-step instructions on switching models, evaluating performance, and rolling out changes safely, see [Migrate to a new model](https://docs.cloud.google.com/gemini-enterprise-cx/cx-agent-studio/deploy/migrate-model.md.txt).

Models in CX Agent Studio are performance-tuned for customer experience,
potentially differing from
[standard Gemini Enterprise Agent Platform offerings](https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/google-models.md.txt).

> [!NOTE]
> **Note:** All models in CX Agent Studio are considered General Availability (GA) unless explicitly marked as "Preview" in the UI. This launch stage is specific to CX Agent Studio and operates independently of a model's status in other Google Cloud products.

For CX Agent Studio, the following models are supported:

| Model | Optimization | Launch stage |
|---|---|---|
| [`gemini-composite-v2`](https://docs.cloud.google.com/gemini-enterprise-cx/cx-agent-studio/agent.md.txt#composite-v2) | Voice Optimized | GA |
| [`gemini-composite-v1`](https://docs.cloud.google.com/gemini-enterprise-cx/cx-agent-studio/agent.md.txt#composite-v1) | Voice Optimized | GA |
| [`gemini-3.7-flash`](https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/gemini/3-7-flash.md.txt) | Text Optimized | GA |
| [`gemini-3.5-flash`](https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/gemini/3-5-flash.md.txt) | Text Optimized | GA |
| [`gemini-3-flash`](https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/gemini/3-flash.md.txt) | Text Optimized | Preview |
| [`gemini-2.5-flash`](https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/gemini/2-5-flash.md.txt) | Text Optimized | GA |
| `gemini-3.1-flash-live` | Voice Optimized | GA |

### Gemini Composite V2 model

The Gemini Composite V2 model is the next version of the
[Composite V1 model](https://docs.cloud.google.com/gemini-enterprise-cx/cx-agent-studio/agent.md.txt#composite-v1) for enterprise voice agents.
It uses the same Listener and Thinking models as Composite V1,
with an upgraded Speaker model that provides the following improvements:

- **More natural speech:** Better pacing, tone, and expression.
- **Precise delivery control:** Inline tags add pauses, breaths, laughs, and tone shifts exactly where you place them.
- **Improved alphanumeric accuracy:** More accurate reading of values such as tracking numbers, phone numbers, and addresses.

To use Composite V2, select `gemini-composite-v2` as the
[global model](https://docs.cloud.google.com/gemini-enterprise-cx/cx-agent-studio/settings.md.txt#application)
for your agent application.
If you're moving an agent from Composite V1,
see [Migrate from Composite V1](https://docs.cloud.google.com/gemini-enterprise-cx/cx-agent-studio/agent.md.txt#migrate-composite-v1).

### Gemini Composite V1 model

The Gemini Composite V1 model is engineered
for enterprise voice agents.
It combines three sub-component models to deliver strict instruction adherence,
superior tool execution, and exceptional voice stability:

This composite model is a combination of three underlying sub-component models:

- **Listener Model:** Converts incoming audio into transcripts with real-time noise rejection.
- **Thinking Model:** Processes inputs, enforces instructions, and executes backend tools.
- **Speaker Model:** Converts text responses into natural, low-latency speech.

> [!NOTE]
> **Note:** Automatic updates may trigger a change of minor version of the composite model or the sub-components.

### Best practices for composite models

Follow these best practices to get natural, reliable speech
from the Composite V2 model.
Composite V2 uses punctuation and context to shape delivery,
so most responses sound natural without extra direction.
Start simple, and add direction only where it improves the conversation.

#### Speaking style

The **Speaking style** in
[voice settings](https://docs.cloud.google.com/gemini-enterprise-cx/cx-agent-studio/voice.md.txt#voice)
shapes the voice for every response.
Follow these guidelines:

- **Start with an empty speaking style.** Test your agent without a speaking style first, and then add one only if it helps.
- **Keep it short.** Describe the speaker in about a dozen words, such as their age, vocal timbre, pitch, accent, and pace. For example: `Friendly woman in her early 30s, warm mid-pitch voice, relaxed conversational pace`.
- **Describe who the speaker is, not how they feel.** Use [inline tags](https://docs.cloud.google.com/gemini-enterprise-cx/cx-agent-studio/agent.md.txt#composite-inline-tags) for emotions that change from moment to moment.
- **Avoid long prompts.** Long, multi-section prompts, such as an audio profile with scene and director's notes, can cause the voice to drift during a call and can conflict with inline tags.

#### Inline tags

Inline tags in an agent response control delivery at a specific point.
To use them, tell the agent in its
[instructions](https://docs.cloud.google.com/gemini-enterprise-cx/cx-agent-studio/instruction.md.txt)
when to add tags to its responses.

The following table lists common tags:

| Tag type | Examples | Effect |
|---|---|---|
| Pause | `<short pause>`, `<long pause>` | Adds a short or long silence. |
| Sound | `<breath>`, `<sigh>`, `<chuckles>`, `<exhales>` | Adds a non-verbal sound once, where you place it. |
| Tone | `<warm>`, `<calm>`, `<empathetic>`, `<positive>`, `<clear>` | Sets the tone until the next tone tag. |

In the following example response,
the agent shifts from an empathetic tone to a positive tone:

    <calm><empathetic> I'm so sorry your flight was canceled. <positive> The good news is that I've already rebooked you on the next flight out.

Follow these guidelines when you use inline tags:

- **Use angle brackets.** Write tags as `<sigh>`, not `[sigh]`.
- **Put tags at the start of a sentence.** You can stack tags there, such as `<calm><empathetic>`. Only pause tags belong mid-sentence, after punctuation. For example: `I checked your account, <short pause> everything is in order.`
- **Use one or two tags per turn.** Most customer conversations don't need more.
- **Don't use closing tags** , such as `</warm>`. A tone tag stays in effect until the next one.
- **Keep tags in English**, even when your agent responds in another language.
- **Use capitalization and punctuation for emphasis.** Capitalize a word to stress it, and use an ellipsis for a natural hesitation.

For the full list of tags, see the
[Gemini TTS prompting guide](https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/text-to-speech/prompting-guide.md.txt#vocal-bursts).

#### Numbers and identifiers

To make sure that the agent speaks numbers, currency, dates, phone numbers,
and alphanumeric IDs correctly,
add text normalization rules to your
[global instructions](https://docs.cloud.google.com/gemini-enterprise-cx/cx-agent-studio/instruction.md.txt#global).
For example, tell the agent to speak `$87.25` as
"eighty-seven dollars and twenty-five cents"
and to read the order ID `XED1234` one character at a time.
State that these rules apply only to spoken responses,
so the agent still passes original values, such as `XED1234`, to tools.

#### Migrate from Composite V1

To move an existing agent from Composite V1 to Composite V2:

1. In voice settings, replace any long speaking style prompt with a short description, or leave it empty.
2. In your instructions and tools, change square-bracket tags to angle brackets. For example, change `[sigh]` to `<sigh>`.
3. Set the model to `gemini-composite-v2` for the agent application and for any sub-agents that override the global model.
4. Test the agent with your usual [evaluations](https://docs.cloud.google.com/gemini-enterprise-cx/cx-agent-studio/evaluation.md.txt) and user acceptance testing before you deploy it.

## Agent templates

When initially creating an agent application,
you can optionally create one based on one of many templates
that handle common scenarios by using the **Create from template**
dropdown option when creating the agent application.

## Agent application settings

See
[settings](https://docs.cloud.google.com/gemini-enterprise-cx/cx-agent-studio/settings.md.txt).

## Agent settings

See
[settings](https://docs.cloud.google.com/gemini-enterprise-cx/cx-agent-studio/settings.md.txt).