Interact with agents

This guide explains how to interact with deployed agents in Managed Agents API on Agent Platform using the Interactions API. You'll learn how to engage with custom agents built using the Agents API and the prebuilt Antigravity base agent, including configuring it dynamically. It also explains how to manage and reuse sandbox environments with environment IDs (env_id) and dynamically override configurations, for example Model Context Protocol (MCP) servers, during interactions.

For more information about the API, see the Interaction API reference documentation.

Before you begin

Before starting interactions with agents, set up your environment:

Sign in to your Google Cloud account. If you're new to Google Cloud, create an account to evaluate how our products perform in real-world scenarios. New customers also get $300 in free credits to run, test, and deploy workloads.
In the Google Cloud console, on the project selector page, select or create a Google Cloud project.
Roles required to select or create a project
• Select a project: Selecting a project doesn't require a specific IAM role—you can select any project that you've been granted a role on.
• Create a project: To create a project, you need the Project Creator role (roles/resourcemanager.projectCreator), which contains the resourcemanager.projects.create permission. Learn how to grant roles.
Go to project selector
Verify that billing is enabled for your Google Cloud project.
Enable the Agent Platform API.
Roles required to enable APIs
To enable APIs, you need the Service Usage Admin IAM role (roles/serviceusage.serviceUsageAdmin), which contains the serviceusage.services.enable permission. Learn how to grant roles.
Enable the API
Make sure that you have the following role or roles on the project: Agent Platform User (roles/aiplatform.user) or Agent Platform Administrator (roles/aiplatform.admin)
Check for the roles
1. In the Google Cloud console, go to the IAM page.

   Go to IAM
2. Select the project.

3. In the Principal column, find all rows that identify you or a group that you're included in. To learn which groups you're included in, contact your administrator.

4. For all rows that specify or include you, check the Role column to see whether the list of roles includes the required roles.
Grant the roles
1. In the Google Cloud console, go to the IAM page.

   Go to IAM
2. Select the project.
3. Click person_add Grant access.

4. In the New principals field, enter your user identifier. This is typically the email address for a Google Account.

5. Click Select a role, then search for the role.
6. To grant additional roles, click add Add another role and add each additional role.
7. Click Save.

In the Google Cloud console, on the project selector page, select or create a Google Cloud project.

Roles required to select or create a project

• Select a project: Selecting a project doesn't require a specific IAM role—you can select any project that you've been granted a role on.
• Create a project: To create a project, you need the Project Creator role (roles/resourcemanager.projectCreator), which contains the resourcemanager.projects.create permission. Learn how to grant roles.

Go to project selector

Verify that billing is enabled for your Google Cloud project.

Enable the Agent Platform API.

Roles required to enable APIs

To enable APIs, you need the Service Usage Admin IAM role (roles/serviceusage.serviceUsageAdmin), which contains the serviceusage.services.enable permission. Learn how to grant roles.

Enable the API

Make sure that you have the following role or roles on the project: Agent Platform User (roles/aiplatform.user) or Agent Platform Administrator (roles/aiplatform.admin)

Check for the roles

1. In the Google Cloud console, go to the IAM page.

   Go to IAM
2. Select the project.

3. In the Principal column, find all rows that identify you or a group that you're included in. To learn which groups you're included in, contact your administrator.

4. For all rows that specify or include you, check the Role column to see whether the list of roles includes the required roles.

Grant the roles

1. In the Google Cloud console, go to the IAM page.

   Go to IAM
2. Select the project.
3. Click person_add Grant access.

4. In the New principals field, enter your user identifier. This is typically the email address for a Google Account.

5. Click Select a role, then search for the role.
6. To grant additional roles, click add Add another role and add each additional role.
7. Click Save.
1. If your agent uses Google Cloud Model Context Protocol (MCP) tools, grant the MCP Tool User (roles/mcp.toolUser) role to both your user account and the associated service account.

Interact with Antigravity agents

The simplest way to use Managed Agents API on Agent Platform is to interact directly with the first-party Antigravity base agent. You don't need to create a custom agent resource; you can invoke the agent on the fly.

To initiate an interaction, specify the base agent target, such as antigravity-preview-05-2026 (or the latest preview variant), and request an on-the-fly remote environment:

POST https://aiplatform.googleapis.com/v1beta1/projects/PROJECT_ID/locations/LOCATION/interactions

{
  "stream": true,
  "background": true,
  "store": true,
  "agent": "antigravity-preview-05-2026",
  "environment": {
    "type": "remote"
  },
  "input": [
    {
      "type": "user_input",
      "content": [
        {
          "type": "text",
          "text": "Who are you, can you execute python code? Show me an example."
        }
      ]
    }
  ]
}

curl -X POST "https://aiplatform.googleapis.com/v1beta1/projects/PROJECT_ID/locations/LOCATION/interactions" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $(gcloud auth print-access-token)" \
  -H "Api-Revision: 2026-05-20" \
  -d '{
      "stream": true,
      "background": true,
      "store": true,
      "agent": "antigravity-preview-05-2026",
      "environment": {"type": "remote"},
      "input": [
          {
              "type": "user_input",
              "content": [
                  {
                      "type": "text",
                      "text": "Who are you, can you execute python code? Show me an example."
                  }
              ]
          }
      ]
  }'

event: interaction.complete
data: {
  "interaction": {
    "id": "1234567890",
    "status": "completed",
    "usage": {
      "total_tokens": 51132,
      "total_input_tokens": 48984,
      "input_tokens_by_modality": [
        {
          "modality": "text",
          "tokens": 48984
        }
      ],
      "total_output_tokens": 769,
      "output_tokens_by_modality": [
        {
          "modality": "text",
          "tokens": 769
        }
      ],
      "total_thought_tokens": 1379
    },
    "created": "2026-05-15T22:26:05Z",
    "updated": "2026-05-15T22:26:05Z",
    "environment_id": "env_CAE1234567890",
    "object": "interaction"
  },
  "event_type": "interaction.complete"
}

from google import genai

client = genai.Client(
    vertexai=True,
    project="PROJECT_ID",
    location="global",
)

stream = client.interactions.create(
    agent="antigravity-preview-05-2026",
    input="Who are you, can you execute python code? Show me an example.",
    environment={"type": "remote"},
    stream=True,
    background=True,
    store=True,
)

for event in stream:
    print(event)

import { GoogleGenAI } from "@google/genai";

const client = new GoogleGenAI({
    vertexai: true,
    project: "PROJECT_ID",
    location: "global",
});

const stream = await client.interactions.create({
    agent: "antigravity-preview-05-2026",
    input: "Who are you, can you execute python code? Show me an example.",
    environment: { type: "remote" },
    stream: true,
    background: true,
    store: true,
});

for await (const event of stream) {
    console.log(event);
}

Interact with a custom agent created using Agents API

To interact with a custom agent created as described in Create and manage agents, you must specify it by using its agent ID.

For more information on how to retrieve or list custom agents to find their IDs, see List agents.

Environment configuration and initialization

When interacting with a custom agent:

• Default behavior: If you create the agent with a default environment, specify the AGENT_ID in your request.

• Explicitly define the environment: If you didn't define the environment configuration when creating the agent, you need to explicitly define the environment in the environment block of your initial interaction request.

  For example:

  "environment": {"type": "remote"}
  

You can dynamically configure features in the sandbox environment during your initial interaction API call to meet specific task requirements. For example:

• Attach skill using Cloud Storage: Attach Cloud Storage buckets to load large data volumes or persistent file directories into the container file system.

• Attach skills using Skill Registry: Provide a list of custom tools, scripts, or prepackaged agent skills to supply specific functional capabilities or your runtime workflow. See Skill Registry.

For a list of environment configuration structures and examples of how to maintain multi-turn conversation state, see Manage session state with environment IDs.

Send an interaction to a custom agent

Send an interaction to your custom agent by specifying the agent ID:

POST https://aiplatform.googleapis.com/v1beta1/projects/PROJECT_ID/locations/LOCATION/interactions

{
  "stream": true,
  "background": true,
  "store": true,
  "agent": "AGENT_ID",
  "input": [
    {
      "type": "user_input",
      "content": [
        {
          "type": "text",
          "text": "Tell me the name of python packages used for data analysis."
        }
      ]
    }
  ]
}

curl -X POST "https://aiplatform.googleapis.com/v1beta1/projects/PROJECT_ID/locations/LOCATION/interactions" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $(gcloud auth print-access-token)" \
  -H "Api-Revision: 2026-05-20" \
  -d '{
      "stream": true,
      "background": true,
      "store": true,
      "agent": "AGENT_ID",
      "input": [
          {
              "type": "user_input",
              "content": [
                  {
                      "type": "text",
                      "text": "Tell me the name of python packages used for data analysis."
                  }
              ]
          }
      ]
  }'

data: {
  "interaction": {
    "id": "1234567890",
    "status": "completed",
    "usage": {
      "total_tokens": 7558,
      "total_input_tokens": 6822,
      "input_tokens_by_modality": [
        {
          "modality": "text",
          "tokens": 6822
        }
      ],
      "total_output_tokens": 278,
      "output_tokens_by_modality": [
        {
          "modality": "text",
          "tokens": 278
        }
      ],
      "total_thought_tokens": 458
    },
    "created": "2026-05-15T22:38:56Z",
    "updated": "2026-05-15T22:38:56Z",
    "environment_id": "env_CAE1234567890",
    "object": "interaction"
  },
  "event_type": "interaction.complete"
}

from google import genai

client = genai.Client(
    vertexai=True,
    project="PROJECT_ID",
    location="global",
)

stream = client.interactions.create(
    agent="AGENT_ID",
    input="Tell me the name of python packages used for data analysis.",
    stream=True,
    background=True,
    store=True,
)

for event in stream:
    print(event)

import { GoogleGenAI } from "@google/genai";

const client = new GoogleGenAI({
    vertexai: true,
    project: "PROJECT_ID",
    location: "global",
});

const stream = await client.interactions.create({
    agent: "AGENT_ID",
    input: "Tell me the name of python packages used for data analysis.",
    stream: true,
    background: true,
    store: true,
});

for await (const event of stream) {
    console.log(event);
}

Manage session state and multi-turn interactions

By default, interactions are stateless unless you target a specific environment container or conversation history. In multi-turn assistant flows, you can retain local files, code execution context, system modifications, runtime-installed open source software libraries, and conversation history across conversations:

• To continue a conversation: Pass the ID from the previous interaction to the previous_interaction_id parameter.
• To continue using a created environment: Pass the environment ID returned from the previous interaction to the environment parameter.

You can select key environment configurations using the following parameters in the environment field:

To send a subsequent interaction request that reuses the same sandbox container and continues a conversation, pass the returned environment_id in the environment field and specify previous_interaction_id. The following examples demonstrate how to continue a stateful session when interacting with the agent.

POST https://aiplatform.googleapis.com/v1beta1/projects/PROJECT_ID/locations/LOCATION/interactions

{
  "stream": true,
  "background": true,
  "store": true,
  "agent": "AGENT_ID",
  "previous_interaction_id": "PREVIOUS_INTERACTION_ID",
  "environment": "ENV_ID",
  "input": [
    {
      "type": "user_input",
      "content": [
        {
          "type": "text",
          "text": "What did I ask you before and what did you do?"
        }
      ]
    }
  ]
}

curl -X POST "https://aiplatform.googleapis.com/v1beta1/projects/PROJECT_ID/locations/LOCATION/interactions" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $(gcloud auth print-access-token)" \
  -H "Api-Revision: 2026-05-20" \
  -d '{
      "stream": true,
      "background": true,
      "store": true,
      "agent": "AGENT_ID",
      "previous_interaction_id": "PREVIOUS_INTERACTION_ID",
      "environment": "ENV_ID",
      "input": [
          {
              "type": "user_input",
              "content": [
                  {
                      "type": "text",
                      "text": "What did I ask you before and what did you do?"
                  }
              ]
          }
      ]
  }'

from google import genai

client = genai.Client(
    vertexai=True,
    project="PROJECT_ID",
    location="global",
)

stream = client.interactions.create(
    agent="AGENT_ID",
    input="What did I ask you before and what did you do?",
    previous_interaction_id="PREVIOUS_INTERACTION_ID",
    environment="ENV_ID",
    stream=True,
    background=True,
    store=True,
)

for event in stream:
    print(event)

import { GoogleGenAI } from "@google/genai";

const client = new GoogleGenAI({
    vertexai: true,
    project: "PROJECT_ID",
    location: "global",
});

const stream = await client.interactions.create({
    agent: "AGENT_ID",
    input: "What did I ask you before and what did you do?",
    previous_interaction_id: "PREVIOUS_INTERACTION_ID",
    environment: "ENV_ID",
    stream: true,
    background: true,
    store: true,
});

for await (const event of stream) {
    console.log(event);
}

Override configurations during interaction

While custom agent definitions typically include default configurations for tools, skills, and third-party connections, you can dynamically adjust these definitions on a per-interaction basis without modifying the underlying agent resource configuration.

A common use case is dynamically overriding connections to Model Context Protocol (MCP) servers at runtime. Any tools or MCP servers specified in the interaction request body completely override the agent's preconfigured tools for the duration of that interaction turn.

To override or define an MCP server at interaction time, add an mcp_server type tool inside the tools list of your interaction request:

POST https://aiplatform.googleapis.com/v1beta1/projects/PROJECT_ID/locations/LOCATION/interactions

{
  "stream": true,
  "background": true,
  "store": true,
  "agent": "agents/AGENT_ID",
  "input": [
    {
      "type": "user_input",
      "content": [
        {
          "type": "text",
          "text": "Analyze our database and summarize recent purchase events."
        }
      ]
    }
  ],
  "tools": [
    {
      "type": "mcp_server",
      "url": "MCP_SERVER_URL",
      "name": "MCP_SERVER_NAME",
      "headers": {
        "MCP_HEADER_KEY": "MCP_HEADER_VALUE"
      }
    }
  ]
}

curl -X POST "https://aiplatform.googleapis.com/v1beta1/projects/PROJECT_ID/locations/LOCATION/interactions" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $(gcloud auth print-access-token)" \
  -H "Api-Revision: 2026-05-20" \
  -d '{
     "stream": true,
     "background": true,
     "store": true,
     "agent": "agents/AGENT_ID",
     "input": [
         {
             "type": "user_input",
             "content": [
                 {
                     "type": "text",
                     "text": "Analyze our database and summarize recent purchase events."
                 }
             ]
         }
     ],
     "tools": [
         {
             "type": "mcp_server",
             "url": "MCP_SERVER_URL",
             "name": "MCP_SERVER_NAME",
             "headers": {
                 "MCP_HEADER_KEY": "MCP_HEADER_VALUE"
             }
         }
     ]
  }'

from google import genai

client = genai.Client(
    vertexai=True,
    project="PROJECT_ID",
    location="global",
)

stream = client.interactions.create(
    agent="AGENT_ID",
    input="Analyze our database and summarize recent purchase events.",
    tools=[
        {
            "type": "mcp_server",
            "url": "MCP_SERVER_URL",
            "name": "MCP_SERVER_NAME",
            "headers": {
                "MCP_HEADER_KEY": "MCP_HEADER_VALUE"
            },
        }
    ],
    stream=True,
    background=True,
    store=True,
)

for event in stream:
    print(event)

import { GoogleGenAI } from "@google/genai";

const client = new GoogleGenAI({
    vertexai: true,
    project: "PROJECT_ID",
    location: "global",
});

const stream = await client.interactions.create({
    agent: "AGENT_ID",
    input: "Analyze our database and summarize recent purchase events.",
    tools: [
        {
            type: "mcp_server",
            url: "MCP_SERVER_URL",
            name: "MCP_SERVER_NAME",
            headers: {
                "MCP_HEADER_KEY": "MCP_HEADER_VALUE",
            },
        },
    ],
    stream: true,
    background: true,
    store: true,
});

for await (const event of stream) {
    console.log(event);
}

What's next