برچسب: Takes

  • Agentic AI takes Gemini in Android Studio to the next level



    Posted by Sandhya Mohan – Product Manager, and Jose Alcérreca – Developer Relations Engineer

    Software development is undergoing a significant evolution, moving beyond reactive assistants to intelligent agents. These agents don’t just offer suggestions; they can create execution plans, utilize external tools, and make complex, multi-file changes. This results in a more capable AI that can iteratively solve challenging problems, fundamentally changing how developers work.

    At Google I/O 2025, we offered a glimpse into our work on agentic AI in Android Studio, the integrated development environment (IDE) focused on Android development. We showcased that by combining agentic AI with the built-in portfolio of tools inside of Android Studio, the IDE is able to assist you in developing Android apps in ways that were never possible before. We are now incredibly excited to announce the next frontier in Android development with the availability of ‘Agent Mode’ for Gemini in Android Studio.

    These features are available in the latest Android Studio Narwhal Feature Drop Canary release, and will be rolled out to business tier subscribers in the coming days. As with all new Android Studio features, we invite developers to provide feedback to direct our development efforts and ensure we are creating the tools you need to build better apps, faster.

    Agent Mode

    Gemini in Android Studio’s Agent Mode is a new experimental capability designed to handle complex development tasks that go beyond what you can experience by just chatting with Gemini.

    With Agent Mode, you can describe a complex goal in natural language — from generating unit tests to complex refactors — and the agent formulates an execution plan that can span multiple files in your project and executes under your direction. Agent Mode uses a range of IDE tools for reading and modifying code, building the project, searching the codebase and more to help Gemini complete complex tasks from start to finish with minimal oversight from you.

    To use Agent Mode, click Gemini in the sidebar, then select the Agent tab, and describe a task you’d like the agent to perform. Some examples of tasks you can try in Agent Mode include:

      • Build my project and fix any errors
      • Extract any hardcoded strings used across my project and migrate to strings.xml
      • Add support for dark mode to my application
      • Given an attached screenshot, implement a new screen in my application using Material 3

    The agent then suggests edits and iteratively fixes bugs to complete tasks. You can review, accept, or reject the proposed changes along the way, and ask the agent to iterate on your feedback.

    moving image showing Gemini breaking tasks down into a plan with simple steps, and the list of IDE tools it needs to complete each step

    Gemini breaks tasks down into a plan with simple steps. It also shows the list of IDE tools it needs to complete each step.

    While powerful, you are firmly in control, with the ability to review, refine and guide the agent’s output at every step. When the agent proposes code changes, you can choose to accept or reject them.

    screenshot of Gemini in Android Studio showing the Agent prompting the user to accept or reject a change

    The Agent waits for the developer to approve or reject a change.

    Additionally, you can enable “Auto-approve” if you are feeling lucky 😎 — especially useful when you want to iterate on ideas as rapidly as possible.

    You can delegate routine, time-consuming work to the agent, freeing up your time for more creative, high-value work. Try out Agent Mode in the latest preview version of Android Studio – we look forward to seeing what you build! We are investing in building more agentic experiences for Gemini in Android Studio to make your development even more intuitive, so you can expect to see more agentic functionality over the next several releases.

    moving image showing that Gemini understanding the context of an app

    Gemini is capable of understanding the context of your app

    Supercharge Agent Mode with your Gemini API key

    screenshot of Gemini API key prompt in Android Studio

    The default Gemini model has a generous no-cost daily quota with a limited context window. However, you can now add your own Gemini API key to expand Agent Mode’s context window to a massive 1 million tokens with Gemini 2.5 Pro.

    A larger context window lets you send more instructions, code and attachments to Gemini, leading to even higher quality responses. This is especially useful when working with agents, as the larger context provides Gemini 2.5 Pro with the ability to reason about complex or long-running tasks.

    screenshot of how to add your API Key in the Gemini settings

    Add your API key in the Gemini settings

    To enable this feature, get a Gemini API key by navigating to Google AI Studio. Sign in and get a key by clicking on the “Get API key” button. Then, back in Android Studio, navigate to the settings by going to File (Android Studio on macOS) > Settings > Tools > Gemini to enter your Gemini API key. Relaunch Gemini in Android Studio and get even better responses from Agent Mode.

    Be sure to safeguard your Gemini API key, as additional charges apply for Gemini API usage associated with a personal API key. You can monitor your Gemini API key usage by navigating to AI Studio and selecting Get API key > Usage & Billing.

    Note that business tier subscribers already get access to Gemini 2.5 Pro and the expanded context window automatically with their Gemini Code Assist license, so these developers will not see an API key option.

    Model Context Protocol (MCP)

    Gemini in Android Studio’s Agent Mode can now interact with external tools via the Model Context Protocol (MCP). This feature provides a standardized way for Agent Mode to use tools and extend knowledge and capabilities with the external environment.

    There are many tools you can connect to the MCP Host in Android Studio. For example you could integrate with the Github MCP Server to create pull requests directly from Android Studio. Here are some additional use cases to consider.

    In this initial release of MCP support in the IDE you will configure your MCP servers through a mcp.json file placed in the configuration directory of Studio, using the following format:

    {
      "mcpServers": {
        "memory": {
          "command": "npx",
          "args": [
            "-y",
            "@modelcontextprotocol/server-memory"
          ]
        },
        "sequential-thinking": {
          "command": "npx",
          "args": [
            "-y",
            "@modelcontextprotocol/server-sequential-thinking"
          ]
        },
        "github": {
          "command": "docker",
          "args": [
            "run",
            "-i",
            "--rm",
            "-e",
            "GITHUB_PERSONAL_ACCESS_TOKEN",
            "ghcr.io/github/github-mcp-server"
          ],
          "env": {
            "GITHUB_PERSONAL_ACCESS_TOKEN": "<YOUR_TOKEN>"
          }
        }
      }  
    }
    
    Example configuration with two MCP servers

    For this initial release, we support interacting with external tools via the stdio transport as defined in the MCP specification. We plan to support the full suite of MCP features in upcoming Android Studio releases, including the Streamable HTTP transport, external context resources, and prompt templates.

    For more information on how to use MCP in Studio, including the mcp.json configuration file format, please refer to the Android Studio MCP Host documentation.

    By delegating routine tasks to Gemini through Agent Mode, you’ll be able to focus on more innovative and enjoyable aspects of app development. Download the latest preview version of Android Studio on the canary release channel today to try it out, and let us know how much faster app development is for you!

    As always, your feedback is important 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!





    Source link

  • When Automation Takes Over, Creation Will Take Off

    When Automation Takes Over, Creation Will Take Off


    Opinions expressed by Entrepreneur contributors are their own.

    When I think about the future, I don’t picture humans cleaning gutters or mowing lawns. I picture something else entirely — something more imaginative. We’re quickly approaching a world where menial tasks are handled by machines that don’t sleep, don’t take breaks and never get tired. And once that shift is fully realized, we’re left with a bigger question: what do we do with all that time?

    For me, the answer is creation.

    We’re at the edge of something massive. Automation is coming, and it’s going to be fast, sweeping and disruptive. But if we embrace what makes us human — our creativity, our ability to connect, to imagine, to express — we won’t be displaced. We’ll be elevated.

    Automation isn’t the end — It’s the beginning

    When the robots start working 24 hours a day and only need an hour to re-oil or recharge, there’s no way we’ll compete with that kind of efficiency — and we shouldn’t want to. That’s not where our value lies. Once those menial jobs are taken care of, it opens a door. A door back to something we’ve been losing: time to think, to philosophize, to explore the meaning of life, just like they did in Roman and Grecian times.

    We’ll spend less time doing tasks like driving cars, which honestly can’t happen soon enough. The number of people who die every year in car accidents is staggering. Imagine a world where those wrecks, the repairs, the hospital visits, all of that… gone. That’s what’s ahead.

    But with that change comes a shift in identity. A lot of people find purpose in their jobs, even the repetitive ones. If we lose those, we’ve got to find purpose elsewhere. I believe that the purpose is in creating.

    So if you’re leading a company, start carving out space for that now. Give your people room to create. I don’t mean just artistic stuff — I mean letting them bring ideas, build something new, try things out because the ones who learn how to create in this new world are the ones who’ll stay valuable.

    Related: 90% of Your Business Could Be Automated With Just These 4 Tools

    Art will lead the next revolution

    We’re going to see an onslaught of art in every form — music, film, writing, you name it. That’s not speculation; it’s already happening. I was just on a call about launching an AI film company focused on short-form video and commercials. Things are moving so fast that it’s hard to keep up.

    There was a commercial shot with a person filmed using just an iPhone. A few back-and-forth shots, handed over to AI — and boom, it became a full ad. That’s all it took. And now imagine what happens when that speed, that capability, meets human creativity.

    But even with AI in the mix, there’s a twist only we can bring. AI is just remixing what we’ve already done. We, on the other hand, can create things that have never been seen before. Entire worlds. New perspectives. Things that AI might eventually mimic, sure — but we’ll always be a step ahead in originality.

    We’re not just going to consume more art. We’re going to make more of it, and we’ll make it differently. In music, for example, AI is already writing songs. I’ve got a friend who used AI to turn one of his poems into a bluesy song. My friend told the program what kind of voice, what style, and that was it. When I played it for people here at the studio, they didn’t even realize it was AI. They just said, “Yeah, that’s not bad.”

    And that’s where it gets interesting. What happens when someone who is musically gifted takes that tool and uses it as a conductor, controlling everything from rhythm to tone to background strings, crafting something original? That’s the revolution we’re heading into—not one where AI replaces us, but where it gives creators the power to be the entire orchestra.

    That’s where leaders need to pay attention. Don’t just chase the tech—figure out how to get it into the hands of your most creative people. Let them drive it.

    The human touch is irreplaceable

    Sure, you can make a song or a film with AI. But you can’t replicate the feeling of a live concert. I just came back from a Vivaldi concert in Vienna — nine musicians, mostly violinists, playing The Four Seasons. You can’t AI that. Not really. Not the energy, not the emotion of watching someone perform right in front of you.

    That’s where the human part stays irreplaceable. We’ll use AI to create better art, sure. But we’ll still crave the live experience, the human behind the music, the emotion behind the words.

    And maybe, just maybe, this opens doors for people who’ve never had access before. Before, you had to go through all these steps— find a band, book studio time and get a label deal. Now? Anyone with talent and drive can make music, make films, tell stories. That levels the playing field in a big way. The truly creative people, who know how to use the tools, are the ones who will rise.

    If you’re running a business, that shift matters. You’re not just looking at resumes anymore — you’re looking for raw creativity and people who know how to work with these tools. That’s who’ll bring new ideas to the table and move things forward.

    Related: Why Automation is Killing Your Productivity and Draining Profits

    Let the machines work — we’ll create

    The speed at which this is happening — it’s not 10 to 20 years. It’s 10 to 20 months. And we’ll be in a whole new creative realm. So yes, automation is coming. Yes, AI is here. But it’s not something to fear.

    Because what’s left — what remains — is us. Our ability to interact, to live with each other, to make life something beautiful. What automation leaves behind is not emptiness. It’s space. Space for imagination. Space for art. Space to figure out what it really means to be human.

    And that, to me, is worth everything.

    When I think about the future, I don’t picture humans cleaning gutters or mowing lawns. I picture something else entirely — something more imaginative. We’re quickly approaching a world where menial tasks are handled by machines that don’t sleep, don’t take breaks and never get tired. And once that shift is fully realized, we’re left with a bigger question: what do we do with all that time?

    For me, the answer is creation.

    We’re at the edge of something massive. Automation is coming, and it’s going to be fast, sweeping and disruptive. But if we embrace what makes us human — our creativity, our ability to connect, to imagine, to express — we won’t be displaced. We’ll be elevated.

    The rest of this article is locked.

    Join Entrepreneur+ today for access.



    Source link