Apple updates Xcode with AI agents that can build and test apps for you

Apple has released a new version of its developer software that adds support for AI-powered coding agents directly inside Xcode. We saw signs of this last fall in the beta version of Xcode and now it’s official.

According to Apple, Xcode 26.3 introduces what it calls “agentic coding,” allowing developers to use AI tools such as Anthropic’s Claude Agent and OpenAI’s Codex to help build apps with less manual work.

With the update, developers can ask these coding agents to handle more complex tasks on their own. Apple says the agents can break down tasks, explore project files, search documentation, adjust settings, run builds, and even check their work using Xcode Previews.

The feature builds on AI tools Apple added in Xcode 26, which introduced a coding assistant focused on writing and editing Swift code. The new release expands that idea by letting external AI agents work across more parts of the development process, from setup to testing.

“At Apple, our goal is to make tools that put industry-leading technologies directly in developers’ hands so they can build the very best apps,” said Susan Prescott, Apple’s vice president of Worldwide Developer Relations. “Agentic coding supercharges productivity and creativity, streamlining the development workflow so developers can focus on innovation.”

Apple says developers are not limited to Claude or Codex. Xcode 26.3 also supports the Model Context Protocol, an open standard that allows other compatible AI agents and tools to plug into Xcode.

Xcode 26.3 is now available as a release candidate for Apple Developer Program members, with a public release expected soon through the Mac App Store.

Just yesterday, OpenAI announced its Codex app for macOS and today’s announcement looks to tie into Apple’s next version of capabilities for Xcode.