Gemini in Android Studio

LLM flexibility, Agent Mode improvements, and new agentic experiences in Android Studio Otter 3 Feature Drop

Seharakram60 — Thu, 15 Jan 2026 17:18:00 +0000

Posted by Sandhya Mohan, Senior Product Manager and Trevor Johns, Developer Relations Engineer

We are excited to announce that Android Studio Otter 3 Feature Drop is now stable! This feature-packed release brings a huge update to your agentic workflows in Android Studio, and offers you more flexibility and control for how you use AI to help you build Android apps.

Bring Your Own Model: You can now use any LLM to power the AI functionality in Android Studio.
Agent Mode Enhancements: You can now more easily have Agent Mode interact with your app on devices, review and accept suggested changes, and have multiple conversations threads.
Run user journey tests using natural language: with Journeys in Android Studio.
Enable Agent Mode to connect to more tools: including the ability to connect to remote servers via MCP.
Build, iterate and test your UI: with UI agentic experiences in Android Studio.
Build deep links using natural language: with the new app links assistant.
Debug R8 optimized code: with Automatic Logcat retracing.
Simplify Android library modules: with the Fused library plugin.

Here’s a deep dive into what’s new:

Bring Your Own Model (BYOM)

Every developer has a unique workflow when using AI, and different companies have different policies on AI model usage. With this release, Android Studio now brings you more flexibility by allowing you to choose the LLM that powers the AI functionality in Android Studio, giving you more control over performance, privacy, and cost.

Use a remote model

You can now integrate remote models—such as OpenAI’s GPT, Anthropic’s Claude, or a similar model—directly into Android Studio. This allows you to leverage your preferred model provider without changing your IDE. To get started, configure a remote model provider in Settings by adding your API endpoint and key. Once configured, you can select your custom model directly from the picker in the AI chat window.

Enter the remote model provider information.

Use a local model

If you have limited internet connectivity, strict data privacy requirements, or a desire to experiment with open-source research, Android Studio now supports local models via providers like LM Studio or Ollama. While Gemini in Android Studio remains the default recommendation—tuned specifically for Android development with full context awareness—if you have a specific model preference, Android Studio supports it.

Model picker in Android Studio.

A local model offers an alternative to the LLM support built into Android Studio, and typically requires significant local system RAM and hard drive space to run well. However, Gemini in Android Studio provides the best Android development experience because Gemini is tuned for Android and supports all features of Android Studio. With Gemini, you can choose from a variety of models for your Android development tasks, including the no-cost default model or models accessed with a paid Gemini API key.

Use your Gemini API key

While Android Studio includes access to a default Gemini model with generous quotas at no cost, some developers need more. By adding your Gemini API key, Android Studio can directly access all the latest Gemini models available from Google.

For example, this allows you to use the most recent Gemini 3 Pro and Gemini 3 Flash models (among others) with expanded context windows and quota. This is especially useful for developers who are using Agent Mode for extended coding sessions, where this additional processing power can provide higher fidelity responses.

You can also read more about how we’re rolling out Gemini 3 to all Android Studio users, including Gemini Code Assist subscribers and developers accessing the default Gemini in Android Studio model at no-cost.

Agent Mode enhancements

Agent Mode is the semi-autonomous AI assistant in Android Studio that aids in your software development, used by many developers, including the Ultrahuman team. Get more out of Agent Mode with these new updates.

Run your app and interact with it on devices

Agent Mode can now deploy an application to the connected device, inspect what is currently shown on the screen, take screenshots, check Logcat for errors, and interact with the running application. This lets the agent help you with changes or fixes that involve re-running the application, checking for errors, and verifying that a particular update was made successfully (for example, by taking and reviewing screenshots).

Agent mode uses device actions to deploy and verify changes.

Find and review changes using the changes drawer

You can now see and manage all changes made by the AI agent using the changes drawer. When the agent makes changes to your codebase, you can see the files that were edited in Files to review. From there, you can keep or revert the changes individually or all together. Click an individual file in the drawer to see the code diff in the editor and make refinements if needed. With the changes drawer, you can keep track of edits made by the agent during your chat and revisit specific changes without scrolling back through your conversation history.

See all the files that the agent has proposed edits to in the changes drawer.

Note: If the Don’t ask to edit files setting is disabled in Agent Options , Agent Mode will request permission for every individual change. Each change must be accepted before it appears in the changes drawer. To allow multiple file edits to appear in the drawer simultaneously, enable the Don’t ask to edit files option.

Accept a change to add it to the changes drawer.

Manage multiple conversation threads

You can now organize your conversations with Gemini in Android Studio into multiple threads. This lets you create a new chat or agent thread when you need to start with a clean slate, and you can go back to older conversations in the history tab. Using separate threads for each distinct task can improve response quality by limiting the scope of the AI’s context to only the topic at hand.

To start a new thread, click New Conversation . To see your conversation history, click Recent Chats.

See prior conversations in the “Recent Chats” tab.

Your conversation history is saved to your account, so if you have to sign out or switch accounts you can resume right where you left off when you come back.

Journeys for Android Studio

Running end-to-end UI tests can improve confidence that you’re shipping a high-quality app to production, but writing and maintaining those tests can be difficult, brittle, and limited in what you’re able to test. Journeys for Android Studio leverages the reasoning and vision capabilities of Gemini to enable you to write and maintain end-to-end UI tests using natural language instructions—and it’s now available in the latest stable release of Android Studio when you enable it from Studio Labs in your Android Studio Settings.

Journeys for Android Studio.

These natural language instructions are converted into interactions that Gemini performs directly on your app. This not only makes your tests easier to write and understand, but also enables you to define complex assertions that Gemini evaluates based on what it “sees” on the device screen. Because Gemini reasons about how to achieve your goals, these tests are more resilient to subtle changes in your app’s layout, significantly reducing flaky tests when running against different app versions or device configurations.

Journeys for Android Studio.

You can write and run journeys directly from Android Studio against any local or remote device. The IDE provides a new editor experience for crafting your test steps in an XML file, using either a code view or a dedicated design view. When you run a journey, Android Studio provides rich, detailed results that help you follow Gemini’s execution. The test panel breaks down the entire journey into its discrete steps, showing you screenshots for each action, what action was taken, and Gemini’s reasoning for why it took that action, making debugging and validation clearer than ever. And because journeys are run as Gradle tasks, you can run them from the command line after you authenticate with a Google Cloud Project. 

Support for remote MCP servers

Android Studio now lets you connect directly to remote Model Context Protocol (MCP) servers such as Figma, Notion, Canva, Linear, and more. This significantly reduces your context switching since it enables the AI agent in Android Studio to leverage external tools, helping you stay in your flow. For example, you can connect to Figma’s remote MCP server to access files and provide this information to Agent Mode, generating more accurate code from your designs. To learn more about how to add an MCP server, see Add an MCP server.

Connect to the Figma remote MCP server in Android Studio Settings.

Quickly add a screen to your app using the Figma remote MCP server.

Supercharge your UI development with Agent Mode

Gemini in Android Studio is now integrated into the UI development workflow directly from within the Compose Preview panel, helping you go from design to a high-quality implementation faster. These new agentic capabilities are designed to assist you at every stage of development, from initial code generation to iteration, refinement, and debugging, with entry points in the context of your work.

Create new UI from a design mock

Accelerate your initial UI implementation by generating Compose code directly from a design mock. Simply click Generate Code From Screenshot in an empty Preview panel, and Gemini will use the image to generate a starting implementation, saving you from writing boilerplate from scratch.

Generate code from a screenshot in an empty Preview panel.

Example turning design into Compose code.

Match your UI with a target image
Once you have an initial implementation, you can iteratively refine it to be pixel-perfect. Right-click your Compose Preview and select AI Actions > Match UI to Target Image. Upload a reference design, and the agent will suggest code changes to make your UI match the design as closely as possible.

Example of using “Match UI to Target Image”

Iterate on your UI with natural language

For more specific or creative changes, right-click on your preview and use the AI Actions >  Change UI. This capability now leverages Agent Mode to validate the results, making it more powerful and accurate. You can use natural language prompts like “change the button color to blue” or “add padding around this text,” and Gemini will apply the code modifications instantly.

Example of using “Change UI”

Find and fix UI quality issues

Verifying your UI is high-quality and more accessible is a critical final step. The AI Actions > Fix all UI check tool audits your UI for common problems, such as accessibility issues. The agent will then propose and apply fixes to resolve the detected issues.

Entry point to trigger “Fix all UI check issues”

You can also find the same functionality by using the Fix with AI button in Compose UI check mode:

“Fix with AI” in UI Check mode

The features mentioned above are also accessible by the toolbar icon in the Preview panel: 

Second entry point to UI development AI features

Beyond iterating on your UI, Gemini also helps streamline your development environment.

To accelerate your setup, you can:

Generate Compose Previews: This feature is now enhanced by Agent Mode to provide more accurate results. When working in a file that has Composable functions but no @Preview annotations, you can right-click on the Composable and select Gemini > Generate [Composable name] Preview. The agent will now better analyze your Composable to generate the necessary boilerplate with correct parameters, to help verify that a successfully rendered preview is added.

Entry point to generate Compose Preview

Fix Preview rendering errors: When a Compose Preview fails to render, Gemini can now analyze the error message and your code to find the root cause and apply a fix.

Using “Fix with AI” on Preview render error

App Links Assistant

The App Links Assistant now integrates with Agent Mode to automate the creation of deep link logic, simplifying one of the most time-consuming steps of implementation. Instead of manually writing code to parse incoming intents and navigate users to the correct screen, you can now let Gemini generate the necessary code and tests. Gemini presents a diff view of the suggested code changes for your review and approval, streamlining the process of handling deep links and ensuring users are seamlessly directed to the right content in your app.

To get started, open the App Links Assistant through the tools menu, then choose Create Applink. In the second step, Add logic to handle the intent, select Generate code with AI assistance. If a sample URL is available, enter it, and then click Insert Code.

App Links Assistant

Automatic Logcat Retracing

Debugging R8-optimized code just became seamless. Previously, when R8 was enabled (minifyEnabled = true in your build.gradle.kts file), it would obfuscate stack traces, changing class names, methods, and line numbers. To find the source of a crash, developers had to manually use the R8 retrace command line tool.

Starting with Android Studio Otter 3 Feature Drop with AGP versions 8.12 and above, this extra step is no longer necessary. Logcat now automatically detects and retraces R8-processed stack traces, so you can see the original, human-readable stack trace directly in the IDE. This provides a much-improved debugging experience with no extra work required.

Logcat now automatically detects and retraces R8-processed stack traces

Fused Library Plugin: Publish multiple Android libraries as one

The new Fused Library plugin bundled with Android Gradle Plugin 9.0 allows you to package multiple Android library modules into a single, publishable Android Library (AAR). This was one of the most requested features for Android Gradle Plugin, and we are making it available for you today. This plugin enables you to modularize your code and resources internally while simplifying the integration process for your users by exposing only a single dependency. In addition to streamlining project setup and version management, distributing a fused library can help reduce library size through improved code shrinking and offer better control over your internal implementation details. To learn more about the Fused Library plugin see Publish multiple Android libraries as one with Fused Library.

Get started

Ready to dive in and accelerate your development? Download Android Studio Otter 3 Feature Drop and start exploring these powerful new features today!

As always, your feedback is crucial to us. Check known issues, report bugs, and be part of our vibrant community on LinkedIn, Medium, YouTube, or X. Let’s build the future of Android apps together!

The post LLM flexibility, Agent Mode improvements, and new agentic experiences in Android Studio Otter 3 Feature Drop appeared first on InShot Pro.

Ultrahuman launches features 15% faster with Gemini in Android Studio

Seharakram60 — Thu, 08 Jan 2026 22:00:00 +0000

Posted by Amrit Sanjeev, Developer Relations Engineer and Trevor Johns, Developer Relations Engineer

Ultrahuman is a consumer health-tech startup that provides daily well-being insights to users based on biometric data from the company’s wearables, like the RING Air and the M1 Live Continuous Glucose Monitor (CGM). The Ultrahuman team leaned on Gemini in Android Studio’s contextually aware tools to streamline and accelerate their development process.

Ultrahuman’s app is maintained by a lean team of just eight developers. They prioritize building features that their users love, and have a backlog of bugs and needed performance improvements that take a lot of time. The team needed to scale up their output of feature improvements, and also needed to handle their performance improvements, without increasing headcount. One of their biggest opportunities was reducing the amount of time and effort for their backlog: every hour saved on maintenance could be reinvested into working on features for their users.

Solving technical hurdles and boosting performance with Gemini

The team integrated Gemini in Android Studio to see if the AI enhanced tools could improve their workflow by handling many Android tasks. First, the team turned to the Gemini chat inside Android Studio. The goal was to prototype a GATT Server implementation for their application’s Bluetooth Low Energy (BLE) connectivity.

As Ultrahuman’s Android Development Lead, Arka, noted, “Gemini helped us reach a working prototype in under an hour—something that would have otherwise taken us several hours.” The BLE implementation provided by Gemini worked perfectly for syncing large amounts of health sensor data while the app ran in the background, improving the data syncing process and saving battery life on both the user’s Android phone and Ultrahuman’s paired wearable device.

Beyond this core challenge, Gemini also proved invaluable for finding algorithmic optimizations in a custom open-source library, pointing to helpful documentation, assisting with code commenting, and analyzing crash logs. The Ultrahuman team also used code completion to help them breeze through writing otherwise repetitive code, Jetpack Compose Preview Generation to enable rapid iteration during UI design, and Agent Mode for managing complex, project-wide changes, such as rendering a new stacked bar graph that mapped to backend data models and UI models.

Transforming productivity and accelerating feature delivery

These improvements have saved the team dozens of hours each week. This reclaimed time is being used to deliver new features to Ultrahuman’s beta users 10-15% faster. For example, the team built a new in-app AI assistant for users, powered by Gemini 2.5 Flash. The UI design, architecture, and parts of the user experience for this new feature were initially suggested by Gemini in Android Studio—showcasing a full-circle AI-assisted development process.

Accelerate your Android development with Gemini

Gemini’s expert Android advice, closely integrated throughout Android Studio, helps Android developers spend less time digging through documentation and writing boilerplate code—freeing up more time to innovate.

Learn how Gemini in Android Studio can help your team resolve complex issues, streamline workflows, and ship new features faster.

The post Ultrahuman launches features 15% faster with Gemini in Android Studio appeared first on InShot Pro.

Gratitude’s developers released 2X the amount of innovative experiments with the help of Gemini in Android Studio

Seharakram60 — Thu, 18 Sep 2025 21:00:00 +0000

Posted by Sandhya Mohan, Product Manager

Gratitude is a mental wellness Android app that encourages self-care and positivity with techniques like in-app journaling, affirmations, and vision boards. These mindfulness exercises need to be free from performance bottlenecks, bugs, and errors for the app to be truly immersive and helpful—but researching solutions and debugging code took away valuable time from the team experimenting on new features. To find a better balance, Gratitude used Gemini in Android Studio to help improve the app’s code and streamline the development process, enabling the team to implement those exciting new features faster.

Gratitude’s AI image generation feature, built in record time with the help of Gemini in Android Studio

Unlocking new efficiencies with Gemini in Android Studio

The Gratitude team decided to try Gemini in Android Studio, an AI assistant that supports developers throughout all stages of development, helping them be more productive. Developers can ask Gemini questions and receive context-aware solutions based on their code. Divij Gupta, senior Android developer at Gratitude, shared that the Gratitude team needed to know if it was possible to inject any object into a Kotlin object class using Hilt. Gemini suggested using an EntryPoint to access dependencies in classes where standard injection isn’t possible, which helped solve their “tricky problem,” according to Divij.

Gemini eliminated the need to search for Android documentation as well, enabling the Gratitude team to learn and apply their knowledge without having to leave Android Studio. “Gemini showed me how to use Android Studio’s CPU and memory profilers more effectively,” recalled Divij. “I also learned how to set up baseline profiles to speed up cold starts.”

Identifying performance bottlenecks became easier too. When analyzing the Gratitude team’s code, Gemini suggested using collectAsStateWithLifecycle instead of collectAsState to collect flows in composables, which helps the app handle lifecycle events more effectively and improves overall performance. Gemini also analyzes the app’s crash reports in the App Quality Insights panel and provides guidance on how to address each issue, which enabled the Gratitude team to “identify root causes faster, catch edge cases we might have missed, and improve overall app stability,” according to Divij.

Experimenting with new features using Gemini in Android Studio

Gemini in Android studio helped the Gratitude team significantly improve their development speed and morale. “This faster cycle has made the team feel more productive, motivated, and excited to keep innovating,” said Divij. Developers are able to spend more time ideating and experimenting on new features, leading to innovative new experiences.

One feature the developers built with their new found time is an image generation function for the app’s vision boards feature. Users can now upload a photo with a prompt, and then receive an AI-generated image that they can instantly pin to their board. The team was able to build the UI using Gemini in Android Studio’s Compose Preview Generation — allowing them to quickly visualize their Jetpack Compose code and craft the pixel-perfect UI their designers intended.

Going forward, the Gratitude team is looking forward to using Gemini to implement more improvements to its code, including correcting glitches, memory leaks, and improving performance based on more insights from Gemini, which will further improve user experience.

Build with Gemini in Android Studio

Discover all of the features available as part of Gemini in Android Studio that can accelerate your development such as code completion, code explanation, that can accelerate your development such as Agent Mode, document generation, and more.

The post Gratitude’s developers released 2X the amount of innovative experiments with the help of Gemini in Android Studio appeared first on InShot Pro.

Android Studio Narwhal 3 Feature Drop: Resizable Compose Preview, monthly releases and smarter AI

Seharakram60 — Sat, 06 Sep 2025 12:06:28 +0000

Posted by Paris Hsu – Product Manager, Android Studio

Welcome to the Android Studio Narwhal Feature Drop 3 release. This update delivers significant improvements across the board to enhance your productivity. While we continue to innovate with powerful, project-aware AI assistance in Gemini, this release also brings fundamental upgrades to core development workflows. Highlights include a resizable Compose Preview for faster UI iteration and robust app Backup & Restore tools to ensure smooth app transfers across devices for your users. These additions, alongside a more context-aware Gemini, aim to streamline every phase of your development process.

These features are delivered as part of our new monthly release cadence for Android Studio, which allows us to provide improvements more frequently. Learn more about this change and how we’re accelerating development with monthly releases for Android Studio.

What’s New in Android Studio Narwhal 3 Feature Drop

Develop with AI

Since launching Gemini in Android Studio, we’ve been working hard to introduce features and integrations across Studio with the needs of Android developers in mind. Developers have been telling us about the productivity benefits AI brings to their workflow — such as Entri, who reduced their UI development time per screen by 40%.

With this release, enhanced how you interact with Gemini — with improved options for providing project context, file attachments, and support for image attachments.

AGENTS.md: providing project-level context to Gemini

AGENTS.md is a Markdown file that lets you provide project-specific instructions, coding style rules, and other guidance that Gemini automatically uses for context. The AGENTS.md file can be checked into your version control system (like Git), ensuring your entire team shares the same core instructions and receives consistent, context-aware AI assistance. AGENTS.md files are located right alongside your code; use multiple AGENTS.md files across different directories for more granular control over your codebase.

AGENTS.md automatically included in Context Drawer

Sample AGENTS.md file

We’re making it much easier to provide rich, on-the-fly context. That’s why we are also excited to share that two powerful features, Image Attachment and the @File Context, are graduating from Studio Labs and are now stable:

Image attachment – Gemini in Android Studio

The ability to attach images to your queries with Gemini is now available in the stable channel! This feature accelerates UI development and improves architectural understanding. You can:

Generate UI from a mock-up: Provide a design image and ask Gemini to generate the Compose code.
Understand an existing screen: Upload a screenshot and ask Gemini to explain the UI’s component structure and data flow.
Debug UI bugs: Take a screenshot of a bug, circle the issue, and ask Gemini for solutions.

Image attachment in Gemini in Android Studio

@file attachment – Gemini in Android Studio

The File attachment and context drawer are also graduating from Studio Labs! Easily attach relevant project files to your prompts by typing @ in the chat window. Gemini can then use the full context of those files to provide more accurate and relevant answers. Gemini will also suggest files it thinks are relevant, which you can easily add or remove.

Evoke @file attachment

What’s next: Deeper integration with MCP support

Looking ahead, in our summer episode of #TheAndroidShow, we went behind the scenes with Android Studio’s new MCP (Model Context Protocol) support. This protocol enhances Gemini’s interoperability with the broader developer ecosystem, allowing it to connect to tools like GitHub. Learn how MCP support can make Gemini’s Agent Mode even more helpful for your workflow, and try it today in the Canary channel.

Optimize and refine

This release includes several new features to help you optimize your app, improve project organization, and ensure compliance.

Test app backup and restore

With new Android hardware devices coming out, ensuring a smooth app transfer experience for your users switching to a new device is critical. Android Studio now provides tools to generate a backup of your app’s data and restore it to another device. This makes it much easier to test your app’s backup and restore functionality and protect users from data loss. Additionally, you can create and attach backups to your run configurations, making it easy to utilize Backup and Restore for your day-to-day development.

Backup and restore dialog

Play policy insights

Get early warnings about potential Play policy violations to help you build more compliant apps with Play Policy Insights, now in Android Studio. The IDE now shows lint warnings directly in your code when it relates to a Google Play policy requirement. You can also integrate these lint checks into your CI/CD pipelines. These insights provide an overview of the policy, dos and don’ts, and links more resources, helping you address potential issues early in your development cycle.

Play policy insights example

Proguard inspections for overly broad keep rules

Android Studio’s Proguard file editor now warns you about keep rules that are overly broad. These rules can limit R8’s ability to optimize your code, potentially impacting app size and performance. This inspection helps you write more precise rules for a more optimized app.

Proguard inspections example

Improved Android view for multi-module projects

For those working on large projects, the Android view has a new setting to display build files directly under their corresponding modules. This change makes it easier to navigate and manage build scripts in projects with many modules.

Option to display build files in module

More control over automatic project sync

For developers working on large projects, automatic Gradle syncs can sometimes interrupt your workflow. To give you more control, we’re introducing an option to switch to manual project sync with reminders. When enabled, Android Studio will inform you when a sync is needed, but lets you decide when to run it, so there aren’t unexpected interruptions. You can try this feature by navigating to Settings > Build, Execution, Deployment > Build Tools.

Enable / Disable auto project sync

Faster UI iteration

Resizable compose preview

Building responsive UIs just got easier: Compose Preview now supports dynamic resizing, giving you instant visual feedback on how your UI adapts to different screen sizes. Simply enter Focus mode in the Compose Preview and drag the edges to see your layout change in real-time. You can even save a specific size as a new @Preview annotation with a single click, streamlining your multi-device development process.

Resizable compose preview

Summary

To recap, Android Studio Narwhal Feature Drop 3 includes the following enhancements and features:

Develop with AI

AGENTS.md support: Provide project-specific context to Gemini for more tailored responses.
Image attachment (Stable): Easily attach image files for Gemini in Android Studio.
@File attachment (Stable): Easily attach project files as context for Gemini in Android Studio.

Optimize and refine

Backup and restore support: Easily test your app’s data backup and restoration flow.
Play policy insights: Get early warnings about potential Play Policy violations.
Proguard inspections: Identify and fix overly broad keep rules for better optimization.
Display build files under module: Improve project navigation in the Android view.
Manual project sync: Gain more control over when Gradle syncs occur in large projects.

Faster UI iteration

Resizable compose preview: Dynamically resize your previews to test responsive UIs instantly.

Get started

Ready to accelerate your development? Download Android Studio Narwhal 3 Feature Drop from the stable channel today!

Your feedback is essential. Please continue to share your thoughts by reporting bugs or suggesting features. For early access to the latest features, download Android Studio from the Canary channel.

Join our vibrant Android developer community on LinkedIn, Medium, YouTube, or X. We can’t wait to see what you build!

The post Android Studio Narwhal 3 Feature Drop: Resizable Compose Preview, monthly releases and smarter AI appeared first on InShot Pro.

Entri cut UI development time by 40% with Gemini in Android Studio

Seharakram60 — Wed, 03 Sep 2025 18:07:00 +0000

Posted by Paris Hsu – Product Manager

Entri delivers online learning experiences across local languages to over 15 million people in India, empowering them to secure jobs and advance in their careers. To seize on the latest advancements in AI, the Entri team explored a variety of tools to help their developers create better experiences for users.

Their latest experiment? Adopting Gemini in Android Studio to enable them to move faster. Not only did Gemini speed up the teams’ work, trim tedious tasks, and foster ongoing learning, it streamlined collaboration between design and development and became an enjoyable, go-to resource that boosted the team’s productivity overall.

Turning screenshots to code—fast

To tighten build time, developers at Entri used Gemini in Android Studio to generate Compose UI code directly from mockups. By uploading screenshots of Figma designs, Gemini produced the UI structures they needed to build entire screens in minutes. Gemini played a key role in revamping the platform’s Sign-Up flow, for example, fast-tracking a process that typically takes hours to just under 45 minutes.

By streamlining the creation of Compose UIs—often from just a screenshot and a few prompts—Gemini also made it significantly easier to quickly prototype new ideas and create MVPs. This allowed their team to test concepts and validate business needs without getting bogged down by repetitive UI tweaks up front.

Entri developers found that the ability to generate code by attaching images in Gemini in Android Studio drastically reduced boilerplate work and improved alignment between design and engineering. Over time, this approach became a standard part of their prototyping process, with the team reporting 40% reduction in average UI build time per screen.

Faster experimentation to create a better app experience

The Entri team has a strong culture of experimentation, and often has multiple user-facing experiments running at once. The team found Gemini in Android Studio particularly valuable in speeding up their experimentation processes. The tool quickly produced code for A/B testing, including UI changes and feature toggles, allowing the team to conduct experiments faster and iterate in more informed ways. It also made it faster for them to get user feedback and apply it. By simplifying the early build phase and allowing for sharper testing, Gemini boosted their speed and confidence, freeing them up to create more, test faster, and refine smarter.

When it came to launching new AI learning features, Entri wanted to be first to market. With Gemini in Android Studio’s help, the Entri team rolled out their AI Teaching Assistant and Interview Coach to production much faster than they normally could. “What used to take weeks, now takes days,” said Jackson. “And what used to take hours, now takes minutes.”

Tool integration reduces context switching

Gemini in Android Studio has changed the game for Entri’s developers, removing the need to break focus to switch between tools or hunt through external documentation. Now the team receives instant answers to common questions about Android APIs and Kotlin syntax without leaving the application.

For debugging crashes, Gemini was especially useful when paired with App Quality Insights in Android Studio. By sharing stack traces directly with Gemini, developers received targeted suggestions for possible root causes and quick fixes directly in the IDE. This guidance allowed them to resolve crashes reported by Firebase and Google Play more efficiently and with less context switching. Gemini surfaced overlooked edge cases and offered alternative solutions to improve app stability, too.

Shifting focus from routine tasks to innovation

Entri developers also wanted to test the efficiency of Gemini in Android Studio on personal projects as well. They leaned on the tool to create a weather tracker, password manager, and POS billing system—all on top of their core project work at Entri. They enjoyed trying it out in their personal projects and experimenting with different use cases.

By offloading repetitive tasks and expediting initial UI and screen generation, Gemini has allowed developers to focus more on innovation, exploration, and creativity—things that often get sidelined when dealing with routine coding work. Now the team is able to spend their time refining final products, designing smarter UX, and strategizing, making their day-to-day work more efficient, collaborative, and motivating.

Get started

Ramp up your development processes with Gemini in Android Studio.

The post Entri cut UI development time by 40% with Gemini in Android Studio appeared first on InShot Pro.

Android Studio Narwhal Feature Drop is stable – start using Agent Mode

Seharakram60 — Thu, 31 Jul 2025 17:30:00 +0000

Posted by Paris Hsu – Product Manager, Android Studio

The next wave of innovation is here with Android Studio Narwhal Feature Drop. We’re thrilled to announce that Gemini in Android Studio’s Agent Mode is now available in the stable release, ready to tackle your most complex coding challenges. This release also brings powerful new tools for XR development, continued quality improvements, and key updates to enhance your productivity and help you build high-quality apps.

Dive in to learn more about all the updates and new features designed to supercharge your workflow.

Gemini in Android Studio: Agent Mode

Develop with Gemini

Try out Agent Mode

Go beyond chat and assign tasks to Gemini. Gemini in Android Studio’s Agent Mode is a powerful AI feature designed to handle complex, multi-stage development tasks. To use Agent Mode, click Gemini in the sidebar and then select the Agent tab. You can describe a high-level goal, like adding a new feature, generating comprehensive unit tests, or fixing a nuanced bug.

The agent analyzes your request, breaks it down into smaller steps, and formulates an execution plan that uses IDE tools, such as reading and writing files and performing Gradle tasks, and can span multiple files in your project. It then iteratively suggests code changes, and you’re always in control—you can review, accept, or reject the proposed changes and ask the agent to iterate based on your feedback. Let the agent handle the heavy lifting while you focus on the bigger picture.

After releasing Agent Mode to Canary, we had positive feedback from the developers who tried it. We were so excited about the feature’s potential, we moved it to the stable channel faster than ever before, so that you can get your hands on it. Try it out and let us know what you build.

Gemini in Android Studio: Agent Mode

Currently, the default model offered in the free tier in Android Studio has a shorter context length, which can limit the depth of response from some agent questions and tasks. In order to get the best performance from Agent Mode, you can bring your own key for the public Gemini API. Once you add your Gemini API key with a paid GCP project, you’ll then be able to use the latest Gemini 2.5 Pro with a full 1M context window from Android Studio. Remember to pick the “Gemini 2.5 Pro” from the model picker in the chat and agent input boxes.

Gemini in Android Studio: model selector

Rules in prompt library

Tailor the response from Gemini to fit your project’s specific needs with Rules in the prompt library. You can define preferred coding styles, tech stacks, languages, or output formats to help Gemini understand your project standards for more accurate and personalized code assistance. You can set these preferences once, and they’ll be automatically applied to all subsequent prompts sent to Gemini. For example, you can create a rule such as, “Always provide concise responses in Kotlin using Jetpack Compose.” You can also set rules at the IDE level for personal use across projects, or at the project level, which can be shared with teammates by adding the .idea folder to your version control system.

Rules in prompt library

Transform UI with Gemini [Studio Labs]

You can now transform UI code within the Compose Preview environment using natural language, directly in the preview. This experimental feature, available through Studio Labs, speeds up UI development by letting you iterate with simple text commands. To use it, right-click in the Compose Preview and select Transform UI With Gemini. Then enter your natural language requests, such as “Center align these buttons,” to guide Gemini in adjusting your layout or styling, or select specific UI elements in the preview for better context. Gemini will then edit your Compose UI code in place, which you can review and approve.

Immersive development

XR Android Emulator and template

Kickstart your extended reality development! Android Studio now includes:

XR Android Emulator: The XR Android Emulator now launches embedded within the IDE by default. You can deploy your Jetpack app, navigate the 3D space, and use the Embedded Layout Inspector directly inside Android Studio.

XR template: Get a head start on your next project with a new template specifically designed for Jetpack XR. This provides a solid foundation with boilerplate code to begin your immersive experience development journey right away.

XR Android Emulator

XR Android template in new project template

Embedded Layout Inspector for XR

The embedded Layout Inspector now supports XR applications, which lets you inspect and optimize your UI layouts within the XR environment. Get detailed insights into your app’s component structure and identify potential layout issues to create more polished and performant experiences.

Embedded Layout Inspector for XR

Android Partner Device Labs available with Android Device Streaming

Android Partner Device Labs are device labs operated by Google OEM partners, such as Samsung, Xiaomi, OPPO, OnePlus, vivo, and others, and expand the selection of devices available in Android Device Streaming. To learn more, see Connect to Android Partner Device Labs.

Android Device Streaming supports Android Partner Device Labs

Optimize and refine

Jetpack Compose preview quality improvements

We’ve made several enhancements to Compose previews to make UI iteration faster and more intuitive:

Improved code navigation: You can now click on a preview’s name to instantly jump to its @Preview definition, or click an individual component within the preview to navigate directly to the function where it’s defined. Hover states and improved keyboard arrow navigation make moving through multiple previews a breeze.

Preview picker: The new Compose preview picker is now available. You can click any @Preview annotation in your Compose code to access the picker and easily manage your previews.

Compose preview: Improved code navigation

Compose preview picker

K2 mode by default

Android Studio now uses the K2 Kotlin compiler by default. This next-generation compiler brings significant performance improvements to the IDE and your builds. By enabling K2, we are paving the way for future Kotlin programming language features and an even faster, more robust development experience in Kotlin.

K2 mode setting

16 KB page size support

To help you prepare for the future of Android hardware, this release adds improved support for transitioning to 16 KB page sizes. Android Studio now offers proactive warnings when building apps that are incompatible with 16 KB devices. You can use the APK Analyzer to identify which specific libraries in your project are incompatible. Lint checks also highlight the native libraries which are not 16 KB aligned. To test your app in this new environment, a dedicated 16 KB emulator target is also available in the AVD Manager.

16 KB page size support: APK Analyzer indication

16 KB page size support: Lint checks

Services compatibility policy

Android Studio offers service integrations that help you and your team make faster progress as you develop, release, and maintain Android apps. Services are constantly evolving and may become incompatible with older versions of Android Studio. Therefore, we are introducing a policy where features that depend on a Google Cloud service are supported for approximately a year in each version of Android Studio. The IDE will notify you when the current version is within 30 days of becoming incompatible so you can update it.

Example notification for services compatibility policy

Summary

To recap, Android Studio Narwhal Feature Drop includes the following enhancements and features:

Develop with Gemini

Gemini in Android Studio: agent mode: use Gemini for tackling complex, multi-step coding tasks.
Rules in Prompt Library: Customize Gemini’s output for your project’s standards.
Transform preview with Gemini [Studio Labs]: Use natural language to iterate on Compose UI.

Immersive development

Embedded XR Android Emulator: Test and debug XR apps directly within the IDE.
XR template: A new project template to kickstart XR development.
Embedded Layout Inspector for XR: Debug and optimize your UI in an XR environment.
Android Partner Device Labs available with Android Device Streaming: access more Google OEM partner devices.

Optimize and refine

Compose preview improvements: Better navigation and a new picker for a smoother workflow.
K2 mode by default: Faster performance with the next-gen Kotlin compiler.
16KB page size support: Lint warnings, analysis, and an emulator to prepare for new devices.
Services compatibility policy: Stay up-to-date for access to integrated Google services.

Get started

Ready to accelerate your development? Download Android Studio Narwhal Feature Drop and start exploring these powerful new features today! As always, your feedback is crucial to us.

Check known issues, report bugs, suggest improvements, and be part of our vibrant community on LinkedIn Medium, YouTube, or X. Let’s build the future of Android apps together!

The post Android Studio Narwhal Feature Drop is stable – start using Agent Mode appeared first on InShot Pro.