Skip to content

AI & Automation1 min read

Google opens Android Studio to third-party AI models

Google is allowing developers to integrate Anthropic and OpenAI models into Android Studio, impacting how Swiss software teams build mobile applications.

by Fini MironFounder @ Balkaris
An abstract composition printed flat in deep teal, pale sand, muted slate blue and bright marigold orange: one large quarter circle anchored in the top left corner and a single straight bar running clear across it from the left edge to the right, the rest one flat field.
Drawn for this article on our own machine. It is not a photograph.

Google announced updates to its Android development environment at the Android Dev Summit. According to The-decoder, the company is opening Android Studio to third-party AI agents. This includes support for models from Anthropic and OpenAI. Google also unveiled new APIs for local smartphone agents and partnered with XREAL to launch the AURA smart glasses. The updates focus on integrating AI into the developer workflow and expanding hardware compatibility.

Why it matters

Swiss companies can now choose specific AI models for their internal development workflows rather than relying on a single provider. This shift allows for better control over data privacy and tool selection. You can integrate agents that understand your specific project structure and local documentation to automate repetitive coding tasks.

  • Reduced costs by using CLI tools that cut token usage for UI tasks.
  • Faster debugging of memory leaks using on-device evaluation.
  • Easier expansion to new hardware like smart glasses and large screens.

What to watch

Check how your current development stack interacts with the Agent Client Protocol. You should evaluate if your team can benefit from the new Android CLI tools to reduce token costs. If you build for mobile, test the new AppFunctions API to see how your app can share features with system-wide agents.

You will likely switch to a non-Google model by next year. This happens if your data privacy requirements exceed the terms of Google's proprietary ecosystem.

Key takeaways

  • You can choose non-Google models to meet specific data privacy requirements.
  • New CLI tools aim to reduce token costs for UI tasks.
  • The AppFunctions API allows your app to share features with system-wide agents.

Frequently asked

Which specific Anthropic or OpenAI models are currently supported in the preview?

The announcement does not list specific model names, only that support for these providers is being opened.

Does the AURA smart glasses partnership mean my app will automatically appear on the glasses?

The text does not state this; it only confirms a partnership to launch the hardware and new APIs for local agents.