Stay organized with collections
Save and categorize content based on your preferences.
Gemini in Android Studio's Agent Mode is designed to handle complex, multi-stage
development tasks that go beyond what you can experience by just chatting with
Gemini. You can describe a high-level goal, and the agent creates and
executes a plan, invoking the necessary tools, making changes
across multiple files, and iteratively fixing bugs. This agent-assisted workflow
lets you tackle intricate challenges, accelerating your development
process.
Figure 1: Gemini in Android Studio's Agent Mode.
Get started
To get started in Agent Mode in Android Studio, follow these steps:
Click Gemini
in the tool window bar. Sign in and onboard if you need to.
Select the Agent tab.
Describe the task you want the agent to perform.
Review and approve any changes as the agent works to accomplish the task.
Figure 2: Agent Mode waits for you to accept or reject a change.
Figure 3: Auto-approve changes suggested by the agent.
Use cases
Here are some examples of use cases that the agent can help you with:
Fix build errors. When you ask the agent to fix a build error using a
prompt like "Fix build errors in my project," it applies a recommended fix,
builds the project to verify the solution, and iterates until the issue is
resolved.
Figure 4: The agent builds your project and assesses if there are errors.
Add or update UI elements. The agent can add or update UI elements.
For example, ask the agent to "Make dark theme the default in user
preferences" and it searches for the relevant files and suggests changes to
accomplish the task. You can immediately preview the UI updates in the
Running devices tool window.
Figure 5: The agent updating UI elements.
Generate mock data. When prototyping and testing your app, you can ask
the agent to generate mock data instead of manually creating it. For
example, when prompted to "Add two more sessions to the fake data," the
agent finds the relevant file and adds two more events to the mockSessions
list.
Figure 6: The agent generating mock data.
Some other prompts to try:
"Write unit tests for <class> in <module>"
"Generate documentation for the open file"
"Change the app title from <current name> to <new name>"
"Resolve the null pointer exception"
"Refactor my code by moving the <composable name> composable to a new
file. Verify that all imports are updated"
"Add a new button to the app's home screen called 'Follow' that takes you to
a list of topics"
"In the <composable name> composable, reduce the padding of the
<modifier name> modifier"
"Create a share button to share to social media"
How the agent works
In Agent Mode, your prompt is sent to the Gemini API with a list of tools that
are available. You can think of tools as skills: they include the ability to
search for files, read files, search the text within files, use any
MCP servers you have configured, and more.
When you give the agent a task, it creates a plan and determines which
tools are needed. Some of these tools might need you to grant permission before
the agent can use them. Once you grant permission, the agent uses the tool to
perform the necessary action and sends the result back to the Gemini API. Gemini
processes the result of the action and generates another response. This cycle of
action and evaluation continues until the task is complete.
Content and code samples on this page are subject to the licenses described in the Content License. Java and OpenJDK are trademarks or registered trademarks of Oracle and/or its affiliates.
Last updated 2025-09-03 UTC.
[[["Easy to understand","easyToUnderstand","thumb-up"],["Solved my problem","solvedMyProblem","thumb-up"],["Other","otherUp","thumb-up"]],[["Missing the information I need","missingTheInformationINeed","thumb-down"],["Too complicated / too many steps","tooComplicatedTooManySteps","thumb-down"],["Out of date","outOfDate","thumb-down"],["Samples / code issue","samplesCodeIssue","thumb-down"],["Other","otherDown","thumb-down"]],["Last updated 2025-09-03 UTC."],[],[],null,["Gemini in Android Studio's Agent Mode is designed to handle complex, multi-stage\ndevelopment tasks that go beyond what you can experience by just chatting with\nGemini. You can describe a high-level goal, and the agent creates and\nexecutes a plan, invoking the necessary [tools](#how-it-works), making changes\nacross multiple files, and iteratively fixing bugs. This agent-assisted workflow\nlets you tackle intricate challenges, accelerating your development\nprocess.\n**Figure 1:** Gemini in Android Studio's Agent Mode.\n\nGet started\n\nTo get started in Agent Mode in Android Studio, follow these steps:\n\n1. Click **Gemini** in the tool window bar. Sign in and onboard if you need to.\n2. Select the **Agent** tab.\n3. Describe the task you want the agent to perform.\n4. Review and approve any changes as the agent works to accomplish the task.\n\n**Figure 2:** Agent Mode waits for you to accept or reject a change.\n\n1. Optional: To automatically approve changes, select **Agent options\n \\\u003e Auto-approve changes**.\n\n**Figure 3:** Auto-approve changes suggested by the agent.\n\nUse cases\n\nHere are some examples of use cases that the agent can help you with:\n\n- **Fix build errors.** When you ask the agent to fix a build error using a prompt like \"Fix build errors in my project,\" it applies a recommended fix, builds the project to verify the solution, and iterates until the issue is resolved.\n\n**Figure 4:** The agent builds your project and assesses if there are errors.\n\n- **Add or update UI elements.** The agent can add or update UI elements. For example, ask the agent to \"Make dark theme the default in user preferences\" and it searches for the relevant files and suggests changes to accomplish the task. You can immediately preview the UI updates in the **Running devices** tool window.\n\n**Figure 5:** The agent updating UI elements.\n\n- **Generate mock data.** When prototyping and testing your app, you can ask the agent to generate mock data instead of manually creating it. For example, when prompted to \"Add two more sessions to the fake data,\" the agent finds the relevant file and adds two more events to the `mockSessions` list.\n\n**Figure 6:** The agent generating mock data.\n\nSome other prompts to try:\n\n- \"Write unit tests for \\\u003cclass\\\u003e in \\\u003cmodule\\\u003e\"\n- \"Generate documentation for the open file\"\n- \"Change the app title from \\\u003ccurrent name\\\u003e to \\\u003cnew name\\\u003e\"\n- \"Resolve the null pointer exception\"\n- \"Refactor my code by moving the \\\u003ccomposable name\\\u003e composable to a new file. Verify that all imports are updated\"\n- \"Add a new button to the app's home screen called 'Follow' that takes you to a list of topics\"\n- \"In the \\\u003ccomposable name\\\u003e composable, reduce the padding of the \\\u003cmodifier name\\\u003e modifier\"\n- \"Create a share button to share to social media\"\n\nHow the agent works\n\nIn Agent Mode, your prompt is sent to the Gemini API with a list of *tools* that\nare available. You can think of tools as skills: they include the ability to\nsearch for files, read files, search the text within files, use any\n[MCP servers](/studio/gemini/add-mcp-server) you have configured, and more.\n\nWhen you give the agent a task, it creates a plan and determines which\ntools are needed. Some of these tools might need you to grant permission before\nthe agent can use them. Once you grant permission, the agent uses the tool to\nperform the necessary action and sends the result back to the Gemini API. Gemini\nprocesses the result of the action and generates another response. This cycle of\naction and evaluation continues until the task is complete."]]