Apple Plans AI Agent for Browsing, Apps and Code
Apple plans a general-purpose AI agent that can browse the web, use apps and write code, with a launch possibly as soon as late 2027.

KEY TAKEAWAYS
- Apple plans a general-purpose AI agent that uses apps, browsers and code.
- Job listings describe multistep agents coordinated by specialized subagents, overlapping OpenAI and Anthropic efforts.
- Development remains early-stage, with a launch possibly as soon as the end of 2027.
HIGH POTENTIAL TRADES SENT DIRECTLY TO YOUR INBOX
Add your email to receive our free daily newsletter. No spam, unsubscribe anytime.
Apple (AAPL) was reported on Nov. 20, 2026, to be developing a general-purpose AI agent that can browse the web, work across apps, run commands and write code, with a launch possibly as soon as the end of 2027.
Apple Agent Job Listings Outline Capabilities
Apple job listings describe an agent that can browse the web, work across apps, run commands, write and debug code, call services and choose the right tool for each step. The listings describe general-purpose computer-use agents that plan and carry out multistep tasks across apps, browsers, command lines, code and application programming interfaces, coordinated by specialized subagents.
One listing sought a senior engineering manager for a proactive, agentic AI assistant, to work with the Siri, UI Frameworks and Apple Foundation Models teams. Those capabilities overlap with computer-use agents being pursued by OpenAI, Anthropic and Meta.
Privacy Design and Timing Remain Early
Development remains early-stage, and the timing is a reported possibility rather than company guidance. The listings say the agent would operate privately, and that agents able to run code, use credentials and act for users require permission models, sandboxing and transparency.





