The Verge says Codex can now use your macOS apps on its own, taking aim at Claude Code
The Verge reports that OpenAI has rolled out a major Codex update that lets the coding agent interact with macOS apps directly, moving beyond code generation into end-to-end ‘build and verify’ workflows. The update is positioned as a direct challenge to Claude Code and the broader wave of desktop-native coding agents.
Coding agents are converging on the same next capability: computer use. Once an agent can drive real apps, it can reproduce bugs, run UI tests, and validate changes instead of just writing code. That shifts the competition from model quality to reliability, guardrails, and developer trust, and it’s where ‘agent productivity’ becomes measurable.
Build a case study repository showing how organizations achieved outcomes
Get access to 200+ AI prompts like this one.
Join The Vault for full access to all prompts, custom GPTs, and more.