Gemini Deep Research 現已推出預先發布版，提供協作規劃、視覺化、MCP 支援等功能。

Google uses AI technology to translate content into your preferred language. AI translations can contain errors.

建構代管代理程式

Gemini API 的受管理代理可讓您使用自己的指令、技能和資料，擴充 Antigravity 代理。您可以在互動時自訂代理程式內嵌，或將設定儲存為您透過 ID 叫用的受管理代理程式。

自訂 Antigravity 代理程式

如要快速建構自訂代理程式，最快的方法是在建立新互動時，直接傳遞設定，不需要註冊步驟。您可以透過三種方式擴充代理程式：

系統指令：透過 system_instruction 傳遞內嵌文字，塑造模型行為。
工具：覆寫預設工具 (程式碼執行、搜尋、網址背景資訊)。
檔案和技能：將 AGENTS.md 和 SKILL.md 等檔案掛載到環境中。

以下是內嵌傳遞所有三個參數的範例：

Python

from google import genai

client = genai.Client()

interaction = client.interactions.create(
    agent="antigravity-preview-05-2026",
    input="Analyze the Q1 revenue data and create a slide deck.",
    system_instruction="You are a data analyst. Always include visualizations and export results as PDF.",        
    environment={
        "type": "remote",
        "sources": [
            {
                "type": "inline",
                "target": ".agents/AGENTS.md",
                "content": "Always use matplotlib for charts. Include a summary table in every report.",
            },
            {
                "type": "inline",
                "target": ".agents/skills/slide-maker/SKILL.md",
                "content": "---\nname: slide-maker\n---\n# Slide Maker\nCreate HTML slide decks from data analysis results.",
            },
        ],
    },
)

print(interaction.output_text)

JavaScript

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

const client = new GoogleGenAI({});

const interaction = await client.interactions.create({
    agent: "antigravity-preview-05-2026",
    input: "Analyze the Q1 revenue data and create a slide deck.",
    system_instruction: "You are a data analyst. Always include visualizations and export results as PDF.",        
    environment: {
        type: "remote",
        sources: [
            {
                type: "inline",
                target: ".agents/AGENTS.md",
                content: "Always use matplotlib for charts. Include a summary table in every report.",
            },
            {
                type: "inline",
                target: ".agents/skills/slide-maker/SKILL.md",
                content: "---\nname: slide-maker\n---\n# Slide Maker\nCreate HTML slide decks from data analysis results.",
            },
        ],
    },
}, { timeout: 300000 });

console.log(interaction.output_text);

REST

curl -X POST "https://generativelanguage.googleapis.com/v1beta/interactions" \
-H "Content-Type: application/json" \
-H "x-goog-api-key: $GEMINI_API_KEY" \
-H "Api-Revision: 2026-05-20" \
-d '{
    "agent": "antigravity-preview-05-2026",
    "input": "Analyze the Q1 revenue data and create a slide deck.",
    "system_instruction": "You are a data analyst. Always include visualizations and export results as PDF.",
    "environment": {
        "type": "remote",
        "sources": [
            {
                "type": "inline",
                "target": ".agents/AGENTS.md",
                "content": "Always use matplotlib for charts. Include a summary table in every report."
            },
            {
                "type": "inline",
                "target": ".agents/skills/slide-maker/SKILL.md",
                "content": "---\nname: slide-maker\n---\n# Slide Maker\nCreate HTML slide decks from data analysis results."
            }
        ]
    }
}'

所有項目都是在互動時定義。不必事先註冊任何項目，Antigravity 代理程式架構提供執行階段 (程式碼執行、檔案管理、網路存取)，以及頂層的設定層。

工具和系統指令

您可以使用 system_instruction 和 tools 參數，自訂特定互動的代理程式行為和功能。

系統指令：使用 system_instruction 參數傳遞內嵌文字，塑造代理程式的行為。非常適合在每次通話時快速調整。《system_instruction》和《AGENTS.md》是加成效果，兩者都會套用。
工具：根據預設，Antigravity 代理程式可存取 code_execution、google_search 和 url_context。您可以在互動時傳遞 tools 參數，覆寫這份清單。如要進一步瞭解可用的工具和使用方式，請參閱「Antigravity Agent：支援的工具」。

以檔案為基礎的自訂

代理程式目錄結構

雖然您可以內嵌傳遞設定，但我們建議您在結構化目錄中整理代理程式的檔案。方便您管理、版本管控，以及掛接到代理程式環境。

典型的代理程式專案目錄如下所示：

my-agent/
├── AGENTS.md        # Instructions on how the agent should operate
├── skills/          # Custom skills (subfolders and SKILL.md files)
│   └── slide-maker/
│       └── SKILL.md
└── workspace/       # Initial data files and knowledge

Antigravity 執行階段會掃描 .agents/ (和環境的根目錄) 是否有這些檔案。

AGENTS.md

代理程式會在啟動時，從環境中自動載入 .agents/AGENTS.md (或 /.agents/AGENTS.md) 做為系統指令。使用 AGENTS.md 進行長期角色定義、詳細規範和指令，並與程式碼一起進行版本管控。

使用內嵌來源掛接 AGENTS.md：

Python

from google import genai

client = genai.Client()

interaction = client.interactions.create(
    agent="antigravity-preview-05-2026",
    input="Analyze the Q1 revenue data and create a report.",
    system_instruction="You are a data analyst. Always include visualizations and export results as PDF.",
    environment={
        "type": "remote",
        "sources": [
            {
                "type": "inline",
                "target": ".agents/AGENTS.md",
                "content": "Always use matplotlib for charts. Include a summary table in every report.",
            },
        ],
    },
)

print(interaction.output_text)

JavaScript

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

const client = new GoogleGenAI({});

const interaction = await client.interactions.create({
    agent: "antigravity-preview-05-2026",
    input: "Analyze the Q1 revenue data and create a report.",
    system_instruction: "You are a data analyst. Always include visualizations and export results as PDF.",
    environment: {
        type: "remote",
        sources: [
            {
                type: "inline",
                target: ".agents/AGENTS.md",
                content: "Always use matplotlib for charts. Include a summary table in every report.",
            },
        ],
    },
}, { timeout: 300000 });

console.log(interaction.output_text);

REST

curl -X POST "https://generativelanguage.googleapis.com/v1beta/interactions" \
  -H "Content-Type: application/json" \
  -H "x-goog-api-key: $GEMINI_API_KEY" \
  -H "Api-Revision: 2026-05-20" \
  -d '{
      "agent": "antigravity-preview-05-2026",
      "input": "Analyze the Q1 revenue data and create a report.",
      "system_instruction": "You are a data analyst. Always include visualizations and export results as PDF.",
      "environment": {
          "type": "remote",
          "sources": [
              {
                  "type": "inline",
                  "target": ".agents/AGENTS.md",
                  "content": "Always use matplotlib for charts. Include a summary table in every report."
              }
          ]
      }
  }'

技能：SKILL.md

技能是擴充代理功能的檔案。將它們放在 .agents/skills/<skill-name>/SKILL.md 下方，線束就會自動探索及註冊。

.agents/
├── AGENTS.md
└── skills/
    └── slide-maker/
        └── SKILL.md

使用內嵌來源掛接技能：

Python

from google import genai

client = genai.Client()

interaction = client.interactions.create(
    agent="antigravity-preview-05-2026",
    input="Create a presentation about our Q1 results.",
    system_instruction="You create presentations from data.",
    environment={
        "type": "remote",
        "sources": [
            {
                "type": "inline",
                "target": ".agents/skills/slide-maker/SKILL.md",
                "content": "---\nname: slide-maker\ndescription: Create HTML slide decks\n---\n# Slide Maker\n\nWhen asked to create a presentation:\n1. Analyze the input data\n2. Create an HTML slide deck with reveal.js\n3. Save to /workspace/output/slides.html",
            },
        ],
    },
)

print(interaction.output_text)

JavaScript

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

const client = new GoogleGenAI({});

const interaction = await client.interactions.create({
    agent: "antigravity-preview-05-2026",
    input: "Create a presentation about our Q1 results.",
    system_instruction: "You create presentations from data.",
    environment: {
        type: "remote",
        sources: [
            {
                type: "inline",
                target: ".agents/skills/slide-maker/SKILL.md",
                content: "---\nname: slide-maker\ndescription: Create HTML slide decks\n---\n# Slide Maker\n\nWhen asked to create a presentation:\n1. Analyze the input data\n2. Create an HTML slide deck with reveal.js\n3. Save to /workspace/output/slides.html",
            },
        ],
    },
}, { timeout: 300000 });

console.log(interaction.output_text);

REST

curl -X POST "https://generativelanguage.googleapis.com/v1beta/interactions" \
  -H "Content-Type: application/json" \
  -H "x-goog-api-key: $GEMINI_API_KEY" \
  -H "Api-Revision: 2026-05-20" \
  -d '{
      "agent": "antigravity-preview-05-2026",
      "input": "Create a presentation about our Q1 results.",
      "system_instruction": "You create presentations from data.",
      "environment": {
          "type": "remote",
          "sources": [
              {
                  "type": "inline",
                  "target": ".agents/skills/slide-maker/SKILL.md",
                  "content": "---\nname: slide-maker\ndescription: Create HTML slide decks\n---\n# Slide Maker\n\nWhen asked to create a presentation:\n1. Analyze the input data\n2. Create an HTML slide deck with reveal.js\n3. Save to /workspace/output/slides.html"
              }
          ]
      }
  }'

系統會自動探索從 .agents/skills/ 和 /.agents/skills/ 載入的技能。

建立代管代理程式

完成設定的疊代作業後，您可以使用 agents.create 將設定建立為受管理代理程式。這樣一來，您就能透過 ID 叫用代理程式，不必每次都重複設定。

來自來源

指定 base_agent、id、system_instruction 和 base_environment 的來源。平台會在每次叫用時，使用您的檔案佈建新的沙箱。如要瞭解可用的來源類型 (Git、GCS、內嵌)，請參閱「環境」。

Python

from google import genai

client = genai.Client()

agent = client.agents.create(
    id="data-analyst",
    base_agent="antigravity-preview-05-2026",
    system_instruction="You are a data analyst. Always include visualizations and export results as PDF.",
    base_environment={
        "type": "remote",
        "sources": [
            {
                "type": "inline",
                "target": ".agents/AGENTS.md",
                "content": "Always use matplotlib for charts. Include a summary table in every report.",
            },
            {
                "type": "inline",
                "target": ".agents/skills/slide-maker/SKILL.md",
                "content": "---\nname: slide-maker\n---\n# Slide Maker\nCreate HTML slide decks from data analysis results.",
            },
            {
                "type": "repository",
                "source": "https://github.com/my-org/analysis-templates",
                "target": "/workspace/templates",
            },
        ],
    },
)

print(f"Created agent: {agent.id}")

JavaScript

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

const client = new GoogleGenAI({});

const agent = await client.agents.create({
    id: "data-analyst",
    base_agent: "antigravity-preview-05-2026",
    system_instruction: "You are a data analyst. Always include visualizations and export results as PDF.",
    base_environment: {
        type: "remote",
        sources: [
            {
                type: "inline",
                target: ".agents/AGENTS.md",
                content: "Always use matplotlib for charts. Include a summary table in every report.",
            },
            {
                type: "inline",
                target: ".agents/skills/slide-maker/SKILL.md",
                content: "---\nname: slide-maker\n---\n# Slide Maker\nCreate HTML slide decks from data analysis results.",
            },
            {
                type: "repository",
                source: "https://github.com/my-org/analysis-templates",
                target: "/workspace/templates",
            },
        ],
    },
});

console.log(`Created agent: ${agent.id}`);

REST

curl -X POST "https://generativelanguage.googleapis.com/v1beta/agents" \
-H "Content-Type: application/json" \
-H "x-goog-api-key: $GEMINI_API_KEY" \
-H "Api-Revision: 2026-05-20" \
-d '{
    "id": "data-analyst",
    "base_agent": "antigravity-preview-05-2026",
    "system_instruction": "You are a data analyst. Always include visualizations and export results as PDF.",
    "base_environment": {
        "type": "remote",
        "sources": [
            {
                "type": "inline",
                "target": ".agents/AGENTS.md",
                "content": "Always use matplotlib for charts. Include a summary table in every report."
            },
            {
                "type": "inline",
                "target": ".agents/skills/slide-maker/SKILL.md",
                "content": "---\nname: slide-maker\n---\n# Slide Maker\nCreate HTML slide decks from data analysis results."
            },
            {
                "type": "repository",
                "source": "https://github.com/my-org/analysis-templates",
                "target": "/workspace/templates"
            }
        ]
    }
}'

從現有環境 (分叉)

使用基礎 Antigravity 代理程式進行疊代，直到環境正確為止 (已安裝套件、檔案就位)，然後將其分叉到受管理代理程式。

Python

from google import genai

client = genai.Client()

# Step 1: set up the environment interactively
interaction = client.interactions.create(
    agent="antigravity-preview-05-2026",
    input="Install pandas, matplotlib, and seaborn. Create an analysis template at /workspace/template.py.",
    environment="remote",
)

# Step 2: fork that environment into a managed agent

agent = client.agents.create(
    id="my-data-analyst",
    base_agent="antigravity-preview-05-2026",
    system_instruction="You are a data analyst. Use the template at /workspace/template.py for all reports.",
    base_environment=interaction.environment_id,
)

print(f"Forked agent successfully: {agent.id}")

JavaScript

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

const client = new GoogleGenAI({});

const interaction = await client.interactions.create({
    agent: "antigravity-preview-05-2026",
    input: "Install pandas, matplotlib, and seaborn. Create an analysis template at /workspace/template.py.",
    environment: "remote",
}, { timeout: 300000 });

const agent = await client.agents.create({
    id: "my-data-analyst",
    base_agent: "antigravity-preview-05-2026",
    system_instruction: "You are a data analyst. Use the template at /workspace/template.py for all reports.",
    base_environment: interaction.environment_id,
});

console.log(`Forked agent successfully: ${agent.id}`);

REST

curl -X POST "https://generativelanguage.googleapis.com/v1beta/interactions" \
  -H "Content-Type: application/json" \
  -H "x-goog-api-key: $GEMINI_API_KEY" \
  -H "Api-Revision: 2026-05-20" \
  -d '{
      "agent": "antigravity-preview-05-2026",
      "input": "Install pandas, matplotlib, and seaborn. Create an analysis template at /workspace/template.py.",
      "environment": "remote"
  }'

使用網路規則

儲存受管理代理程式時，您可以鎖定輸出存取權或插入憑證。如需完整的許可清單結構定義、憑證模式和萬用字元，請參閱「環境：網路設定」。

以下範例會建立只能存取 GitHub 和 PyPI 的 issue-resolver 代理程式，並為 GitHub 插入憑證：

Python

from google import genai

client = genai.Client()

agent = client.agents.create(
    id="issue-resolver",
    base_agent="antigravity-preview-05-2026",
    system_instruction="You resolve GitHub issues. Clone the repo, find the bug, write the fix, run the tests, and open a PR.",
    base_environment={
        "type": "remote",
        "sources": [
            {
                "type": "repository",
                "source": "https://github.com/my-org/backend",
                "target": "/workspace/repo",
            }
        ],
        "network": {
            "allowlist": [
                {
                    "domain": "api.github.com",
                    "transform": {
                        "Authorization": "Basic YOUR_BASE64_TOKEN"
                    },
                },
                {"domain": "pypi.org"},
            ]
        },
    },
)

print(f"Created issue-resolver agent successfully: {agent.id}")

JavaScript

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

const client = new GoogleGenAI({});

const agent = await client.agents.create({
    id: "issue-resolver",
    base_agent: "antigravity-preview-05-2026",
    system_instruction: "You resolve GitHub issues. Clone the repo, find the bug, write the fix, run the tests, and open a PR.",
    base_environment: {
        type: "remote",
        sources: [
            {
                type: "repository",
                source: "https://github.com/my-org/backend",
                target: "/workspace/repo",
            }
        ],
        network: {
            allowlist: [
                {
                    domain: "api.github.com",
                    transform: {
                        "Authorization": "Basic YOUR_BASE64_TOKEN"
                    },
                },
                { domain: "pypi.org" },
            ]
        }
    },
});

console.log(`Created issue-resolver agent successfully: ${agent.id}`);

REST

curl -X POST "https://generativelanguage.googleapis.com/v1beta/agents" \
  -H "Content-Type: application/json" \
  -H "x-goog-api-key: $GEMINI_API_KEY" \
  -H "Api-Revision: 2026-05-20" \
  -d '{
      "id": "issue-resolver",
      "base_agent": "antigravity-preview-05-2026",
      "system_instruction": "You resolve GitHub issues. Clone the repo, find the bug, write the fix, run the tests, and open a PR.",
      "base_environment": {
          "type": "remote",
          "sources": [
              {
                  "type": "repository",
                  "source": "https://github.com/my-org/backend",
                  "target": "/workspace/repo"
              }
          ],
          "network": {
              "allowlist": [
                  {
                      "domain": "api.github.com",
                      "transform": {
                          "Authorization": "Basic YOUR_BASE64_TOKEN"
                      }
                  },
                  {"domain": "pypi.org"}
              ]
          }
      }
  }'

叫用代理程式

建立新的互動，並使用代理程式 ID 呼叫受管理代理程式。每次叫用都會分叉基本環境，因此每次執行都會從乾淨的狀態開始。

Python

result = client.interactions.create(
    agent="data-analyst",
    input="Analyze Q1 revenue data from /workspace/templates/sample.csv and create a slide deck.",
    environment="remote",
)

print(result.output_text)

JavaScript

const result = await client.interactions.create({
    agent: "data-analyst",
    input: "Analyze Q1 revenue data from /workspace/templates/sample.csv and create a slide deck.",
    environment: "remote",
}, { timeout: 300000 });

console.log(result.output_text);

REST

curl -X POST "https://generativelanguage.googleapis.com/v1beta/interactions" \
  -H "Content-Type: application/json" \
  -H "x-goog-api-key: $GEMINI_API_KEY" \
  -H "Api-Revision: 2026-05-20" \
  -d '{
      "agent": "data-analyst",
      "input": "Analyze Q1 revenue data from /workspace/templates/sample.csv and create a slide deck.",
      "environment": "remote"
  }'

如要瞭解多輪對話和串流功能，請參閱快速入門導覽課程。受管理代理程式也適用相同的 previous_interaction_id 和 environment 模式。

在叫用時覆寫設定

建立互動時，您可以覆寫代理程式的預設 system_instruction 和 tools。這樣一來，您就能在特定執行作業中修改代理程式的行為或功能，而不必變更儲存的代理程式定義。

Python

result = client.interactions.create(
    agent="data-analyst",
    input="Analyze Q1 revenue data, but do not create a slide deck. Just output a summary table.",
    system_instruction="You are a data analyst. Focus ONLY on summary tables. Ignore default instructions about slides.",
    tools=[{"type": "code_execution"}], # Override to only use code execution
    environment="remote",
)
print(result.output_text)

JavaScript

const result = await client.interactions.create({
    agent: "data-analyst",
    input: "Analyze Q1 revenue data, but do not create a slide deck. Just output a summary table.",
    system_instruction: "You are a data analyst. Focus ONLY on summary tables. Ignore default instructions about slides.",
    tools: [{ type: "code_execution" }], // Override to only use code execution
    environment: "remote",
}, { timeout: 300000 });

console.log(result.output_text);

REST

curl -X POST "https://generativelanguage.googleapis.com/v1beta/interactions" \
  -H "Content-Type: application/json" \
  -H "x-goog-api-key: $GEMINI_API_KEY" \
  -H "Api-Revision: 2026-05-20" \
  -d '{
      "agent": "data-analyst",
      "input": "Analyze Q1 revenue data, but do not create a slide deck. Just output a summary table.",
      "system_instruction": "You are a data analyst. Focus ONLY on summary tables. Ignore default instructions about slides.",
      "tools": [{"type": "code_execution"}],
      "environment": "remote"
  }'

管理代理

您可以列出、取得及刪除代理程式。

列出代理程式

Python

agents = client.agents.list()
for a in agents.agents:
    print(f"{a.id}: {a.description}")

JavaScript

const agents = await client.agents.list();
if (agents.agents) {
    for (const a of agents.agents) {
        console.log(`${a.id}: ${a.description}`);
    }
}

REST

curl -X GET "https://generativelanguage.googleapis.com/v1beta/agents" \
  -H "x-goog-api-key: $GEMINI_API_KEY"

取得代理程式

Python

agent = client.agents.get(id="data-analyst")
print(agent)

JavaScript

const agent = await client.agents.get("data-analyst");
console.log(agent);

REST

curl -X GET "https://generativelanguage.googleapis.com/v1beta/agents/data-analyst" \
  -H "x-goog-api-key: $GEMINI_API_KEY"

刪除代理程式

刪除後，系統會移除設定。代理程式建立的現有環境和互動不會受到影響。

Python

client.agents.delete(id="data-analyst")

JavaScript

await client.agents.delete("data-analyst");

REST

curl -X DELETE "https://generativelanguage.googleapis.com/v1beta/agents/data-analyst" \
  -H "x-goog-api-key: $GEMINI_API_KEY"

代理程式定義參考資料

欄位	類型	必要	說明
`id`	字串	是	專屬代理程式 ID。用於叫用代理程式。
`description`	字串	否	使用者可理解的代理說明。
`base_agent`	字串	是	基本代理商 ID (例如 `antigravity-preview-05-2026`)。
`system_instruction`	字串	否	定義行為和角色的系統提示。
`tools`	字串或物件	否	代理可使用的工具，省略則可存取 `code_execution`、`google_search` 和 `url_context`。
`base_environment`	字串或物件	否	`"remote"`、`environment_id`，或是包含 `sources` 和 `network` 的設定物件。請參閱「環境」。

疊代工作流程

以基礎 Antigravity 代理原型為基礎。內嵌傳遞系統指令和環境來源。以互動方式測試指令、技能和環境設定。
穩定環境。安裝套件、掛接來源，並確認一切正常運作。
建立新代理程式 (可從來源建立，或透過環境分叉建立)，以保留為受管理代理程式。
更新代理程式定義。變更系統指示、更換技能或新增來源。下次叫用時，系統會採用新設定。

限制

預覽狀態：受管理代理程式目前為預覽版。功能和結構定義可能會有所異動。
基礎代理程式：僅支援 antigravity-preview-05-2026 做為 base_agent。
不支援版本管理：目前不支援代理程式版本管理和復原。
不支援子代理巢狀結構：目前不支援子代理委派。
最多可有 1000 個受管理代理程式。

後續步驟

代理程式總覽：瞭解受管理代理程式的核心概念。
快速入門導覽課程：開始建構多輪對話和串流。
Antigravity Agent：瞭解預設代理的功能、工具和價格。
代理程式環境：設定沙箱、來源和網路。