Xcode 26.3 Lets AI Agents From Anthropic and OpenAI Build Apps Automatically

With Xcode 26.3, Apple is adding support for agent coding, allowing developers to use tools like Anthropic’s Claude Agent and OpenAI’s Codex right in Xcode for app development.

Coding will allow Xcode to complete complex application development tasks automatically. Claude, ChatGPT, and other types of AI have been available for use in Xcode since Apple added intelligence features to Xcode 26, but until now, AI was limited and unable to take action on its own. That will change with the option to use an AI coding assistant.

AI models can access many features of Xcode to serve a project goal, and Apple worked directly with Anthropic and OpenAI to prepare its agents for use in Xcode. Agents can create new files, check project design in Xcode, directly build a project and run tests, take snapshots to double-check work, and access Apple’s full developer documentation for AI agents.

Adding an agent to Xcode can be done with one click in Xcode settings, and agents can be automatically updated as AI companies release updates. Developers will need to set up an Anthropic or OpenAI account to use those coding tools in Xcode, paying fees based on API usage.

Apple says it intends to ensure that Claude Agent and Codex work properly, by reducing the use of tokens. It’s easy to swap agents for the same project, giving developers the ability to choose the agent best suited for a given task.

While Apple is working with OpenAI and Anthropic for Xcode integration, Xcode 26.3 features can be used with any agent or tool that uses the standard open Model Context Protocol. Apple releases documentation to enable developers to program and connect MCP agents to Xcode.

Using natural language commands, developers are able to instruct AI agents to complete a project, such as adding a new feature to an app. Xcode then works with the agent to break down the instructions into smaller tasks, and the agent can work on itself from there. Here’s how the process works:

• A developer asks an integrated agent to add a new feature to an application.
• The agent looks at the current project to see how it is scheduled.
• The agent checks all relevant documentation, looks for code snippets, code samples, and the latest APIs.
• The agent starts working on the project, adding code as it goes.
• The agent builds the project, then uses Xcode to validate its work.
• If there are errors or warnings, the agent continues to run until all problems are resolved. It has access to building logs and updates until the project is complete.
• The agent ends by providing a summary of everything that happened so that developers have a clear view of the implementation.

In the project sidebar, developers can follow what the agent is doing using the script, and can click to see where code is added to track what the agent is doing. At any point, developers can go back before the agent or model makes the change, so there are options to undo unwanted results or try multiple options to introduce a new feature.

Apple says coding will allow developers to streamline workflows, make changes faster, and bring new ideas to life. Apple also sees it as a learning tool that gives developers the opportunity to learn new ways to build something or use an API in an app.

“At Apple, our goal is to create tools that put industry-leading technology directly into the hands of developers to create the best apps,” said Susan Prescott, Apple’s vice president of Worldwide Developer Relations. “Agentic coding dramatically increases productivity and creativity, simplifying the development workflow so developers can focus on innovation.”

The Xcode 26.3 release candidate is available to developers starting today, and the launch may follow in the next week or so.